Research Methods
454 articles
Learn qualitative research methodologies — from user interviews and Jobs-to-be-Done to thematic analysis and affinity mapping.
Availability, Not Uptime: Why Time-to-Repair Is Half Your Retention Equation (2026)
Availability is a ratio with two terms, and product teams fund only one of them. Halving repair time and halving failure rate produce exactly the same result. Here is the arithmetic, the invisible parts of the customer repair clock, and how to measure them.
Why Your First Three Interviews Always Go Worst: The Failure-Rate Curve of an Interview Guide
Interview guides fail on a curve, not at a constant rate. Learn the three regions - early-life, useful life, and wear-out - and the opposite fixes each one needs.
Switch Interviews: The JTBD Method for Understanding Why Customers Buy (and Leave)
Switch interviews uncover the four forces of progress that cause customers to switch from one product to another. Learn the Bob Moesta playbook and how to run switch interviews with AI at scale.
Snowball Sampling: A Complete Guide for Hard-to-Reach Participants (2026)
Learn how snowball sampling works, when to use it for hidden and hard-to-reach populations, how to control referral bias, and how AI-native tools scale recruitment and interviews at once.
Interviewer Bias: How Moderators Distort Research (and How AI Removes the Variance)
Interviewer bias is the distortion caused by a moderator's wording, reactions, expectations, and characteristics. Learn the types, the evidence, mitigation techniques, and why an AI interviewer eliminates interviewer variance.
How to Create a Customer Feedback Form (with Examples)
A step-by-step guide to building customer feedback forms that people actually complete, with question examples by use case and how to upgrade a static form into an AI conversation that probes the "why."
Go-to-Market Research: The Complete Guide to De-Risking Your Launch (2026)
A complete guide to go-to-market (GTM) research: the five research questions every launch must answer, the methods that answer them, why most launches fail, and how AI-native interviews let you validate buyers, messaging, and pricing in days instead of months.
When to Stop Piloting: The Defect-Decay Stopping Rule for Interview Guides
"Pilot until nothing new comes up" is not a stopping rule - the defect curve never reaches zero. Here is the economic rule that replaces it, with a worked example.
User Research for Mobile Apps: The Complete Guide
How to run effective user research for mobile apps — covering methods, study design, in-context AI interviews, and building a continuous mobile research program.
Transactional vs Relational NPS: When to Use Each (2026 Guide)
A practical guide to transactional vs relational NPS - what each measures, when to send them, how to benchmark them, and how AI follow-up turns both into root-cause insight.
The Hawthorne Effect: How Being Observed Changes Research Results
The Hawthorne effect is when people change their behavior simply because they know they are being watched. Learn where it came from, how it quietly distorts usability tests and interviews, and the proven ways to design research that captures real behavior.
Perceptual Mapping: How to Visualize Brand Positioning
A complete guide to perceptual mapping — what it is, the attribute-based vs MDS approaches, how to build one step by step, real examples, and how AI-moderated research collects the perception data fast.
Power User Interviews: How to Learn from Your Best Customers to Drive Growth
Learn how to identify and interview your power users to understand what drives product mastery, advocacy, and expansion — and how AI interviews make this research scalable.
Psychographic Segmentation: The Complete Guide to Segmenting Customers by Values, Attitudes & Lifestyle (2026)
A complete, practical guide to psychographic segmentation: what it is, how it differs from demographics and behavior, the VALS framework, how to collect psychographic data, and how to build segments faster with AI-moderated interviews.
Design Thinking Research: The Complete Guide to the Empathize Phase
Master the Design Thinking empathize phase with proven user research techniques. Learn empathy mapping, immersion, observation, and how AI-powered interviews accelerate human-centered design.
Smoke Tests and Fake Door Tests: How to Validate Demand Before You Build
Smoke tests and fake door tests measure real user demand for an idea before any code is written. Learn the playbook used by Buffer, Dropbox, and modern product teams — and how to pair it with AI interviews.
AI Market Research: The Complete 2026 Guide to Faster, Smarter Insights
A complete guide to AI market research in 2026 — what it is, what it actually replaces, how it compares to legacy methods, and how to run a full study with AI-moderated interviews in days instead of weeks.
How to Conduct User Interviews: The Complete Step-by-Step Guide
A complete step-by-step guide to planning, conducting, and analyzing user interviews—covering discussion guide writing, participant recruitment, facilitation techniques, sample size, and modern AI-powered approaches.
Problem Interviews vs. Solution Interviews: When to Use Each
Problem interviews uncover whether a pain is real and worth solving; solution interviews test whether your proposed answer actually fixes it. Learn the difference, when to run each, the questions to ask, and how to run both at scale with AI.
Lean User Research: How to Run Meaningful Research with No Time or Budget
A practical guide to lean user research — the techniques, principles, and AI tools that let small teams run effective research in hours, not weeks. Includes guerrilla testing, rapid prototyping, and how Koji automates the process.
Customer Needs Analysis: How to Uncover What Customers Actually Want
A practical guide to customer needs analysis — how to identify, prioritize, and act on what customers genuinely need, with frameworks, research methods, and real-world examples.
Cross-Cultural User Research: The Complete Guide for Global Product Teams
Master cross-cultural user research with frameworks for cultural adaptation, language localization, and AI-powered global insights. Avoid the bias that breaks products in new markets.
Focus Group Questions: 50+ Examples and How to Write Them
A complete bank of 50+ focus group question examples organized by session stage and research goal, plus rules for writing unbiased questions and a faster AI-moderated alternative.
Empathy Map: The Complete Guide to Building User Empathy
Learn how to create an empathy map from scratch — the 6-section framework, step-by-step process, common mistakes, and how AI-powered interviews with Koji give you richer empathy data in less time.
Forced-Choice Questions: How to Eliminate Fence-Sitting and Get Decisive Data
Forced-choice questions remove the neutral or "no opinion" escape hatch so respondents have to commit to a real preference. Learn when to use them, how to write them without bias, and how AI interviews recover the reasoning you would otherwise lose.
WSJF Prioritization: Weighted Shortest Job First Explained (2026 Guide)
A complete guide to Weighted Shortest Job First (WSJF): Cost of Delay divided by job size, the three CoD components, a worked example, and how customer research turns WSJF scores from guesswork into defensible estimates.
Pre-Launch User Research: How to Validate Before You Ship
A complete framework for running user research in the weeks before a product launch — covering concept validation, messaging testing, and onboarding validation using AI interviews.
Gabor-Granger Pricing Method: Find Your Revenue-Maximizing Price
A practical guide to the Gabor-Granger pricing method — how it works, a worked revenue-curve example, its limitations, how it compares to Van Westendorp and conjoint, and how to run it with AI.
TAM SAM SOM for Product Researchers: How to Size Markets With Real Customer Data (2026 Guide)
TAM SAM SOM is the three-layer market sizing model — Total Addressable, Serviceable Addressable, and Serviceable Obtainable. Learn the bottom-up formula, the research-backed inputs, the methodology mistakes that sink fundraising decks, and how AI-moderated interviews turn market sizing from desk research into evidence.
Concierge MVP: How to Validate a Startup Idea by Manually Delivering the Service (2026 Guide)
A concierge MVP tests whether an idea is worth building by manually delivering the service to a small group of paying customers — no product, no automation. Learn the 7-step playbook, how Airbnb and Food on the Table used it, the mistakes that burn founders, and how AI-moderated interviews scale the learning without scaling the manual work.
The AEIOU Framework: How to Structure Field Observations for UX Research (2026 Guide)
AEIOU — Activities, Environments, Interactions, Objects, Users — is a five-letter framework for coding observations during field research and contextual inquiry. Created at Doblin in 1991, AEIOU gives researchers a MECE scaffold that turns field-study chaos into themed insights. Learn the template, the 5-step workflow, common mistakes, and how to extend AEIOU to remote research with AI interviews.
Usage and Attitudes (U&A) Studies: The Complete Guide to Mapping a Market
A Usage and Attitudes (U&A) study maps how a market actually behaves and what it believes — habits, frequency, drivers, and barriers. Learn how to design one, what to measure, and how AI interviews make U&A faster and deeper than traditional surveys.
Constant-Sum Questions: How to Measure Trade-Offs by Asking People to Allocate
Constant-sum questions ask respondents to divide a fixed total — usually 100 points — across a set of options, revealing the relative weight of each. Learn how to design them, avoid math errors, and capture the reasoning behind every allocation.
Accessibility Research: How to Include Users with Disabilities in Your Studies
A practical guide to designing and conducting accessible user research — how to recruit participants with disabilities, adapt your methods, and use async AI interviews to remove barriers to participation.
Brand Research Interviews: How to Understand Brand Perception Through Conversation
A complete guide to running qualitative brand research interviews — covering brand perception, positioning validation, competitive differentiation, and brand equity — using AI-moderated conversations at scale.
Survivorship Bias in Customer Research: Why You're Only Hearing Half the Story
Survivorship bias makes customer research dangerously optimistic by only sampling the customers who stayed. Learn how to spot it, why it inflates every metric, and how to systematically capture the voices of the customers who left.
k-Anonymity for Segment Reporting: How Small Is Too Small to Publish? (2026)
The rule for minimum base size in research reporting, stated exactly: every visible combination of attributes must be shared by at least k respondents - and why generalisation beats suppression.
Competitive Research: A Practical Guide to Studying Your Market and Rivals (2026)
How to run competitive research that drives decisions — combining desk research with primary interviews to uncover why customers choose, switch, or reject competitors.
Win-Loss Analysis: How to Learn Why Deals Are Won and Lost
A complete guide to win-loss analysis—covering interview methodology, why CRM data fails, internal vs. third-party programs, what questions to ask buyers, and how to use findings to improve win rates, messaging, and product roadmaps.
How to Identify and Validate Customer Pain Points Through Research
A complete guide to discovering the real problems customers face — using AI interviews, structured questions, and proven frameworks to surface pain points that drive product decisions.
Mental Models in UX Research: How to Understand How Your Users Think
Mental models are the invisible assumptions users bring to your product. This guide covers how to research user mental models through interviews, card sorting, and think-aloud protocols — and how to apply findings to close the gap between user expectations and product behavior.
Customer Feedback Questions: 60+ Examples by Lifecycle Stage
A complete bank of 60+ customer feedback questions organized by lifecycle stage - onboarding, product, support, pricing, churn, and advocacy - plus how AI follow-up turns one question into a real conversation.
What Is Customer Research? The Complete Guide for 2026
Customer research is the systematic practice of studying your customers to understand their needs, behaviors, and decisions. Learn the types, methods, and how AI makes it faster.
Trust the Delta, Not the Level: Common-Mode Bias in Research (2026)
A bias that hits every arm equally cancels when you subtract and survives intact in any absolute number. How to tell which kind of bias you have.
UX Research Deliverables: The Complete Guide to Research Outputs That Drive Action
A comprehensive guide to UX research deliverables — from research reports and user personas to journey maps and insight statements — with guidance on matching deliverables to audiences and using AI to eliminate manual production time.
Nobody Mentioned It: What Zero Occurrences Actually Rules Out (2026)
Zero mentions in 20 interviews does not mean a rate of zero. The rule of three converts an absence into the only honest number: an upper bound.
Types of Customer Feedback: The Complete Guide (7 Types + How to Act on Each)
Customer feedback comes in more forms than a support ticket. Learn the 7 core types — solicited vs unsolicited, direct vs indirect, and the NPS/CSAT/CES metrics — and how to turn each into action.
Why the Feature Request That Reaches You Is Bigger Than the Problem (2026)
Relayed feedback does not fade, it amplifies. The bullwhip effect explains why a request arrives louder and lumpier than the experience behind it.
Buying Committee Interviews: Multi-Stakeholder B2B Research Without the Scheduling Nightmare
Run research interviews with every member of a B2B buying committee — economic buyers, end users, IT, security, finance, legal — without coordinating six calendars. Use Koji's personalized AI interview links to capture role-specific perspectives at each stakeholder's convenience, then synthesize the full account view in one report.
HEART Framework: Google’s 5-Metric Model for Measuring User Experience (2026 Guide)
The complete guide to Google’s HEART framework — the five user-centered metrics (Happiness, Engagement, Adoption, Retention, Task Success), the Goals–Signals–Metrics process, and how to collect each metric in days, not quarters, with AI-moderated research on Koji.
Nobody Made the Decision: How to Research a Purchase No Single Person Chose (2026)
58% of CEOs' retrospective accounts of their own firm's strategy disagreed with their own earlier validated reports. Why 'why did you buy' is unanswerable for group decisions - and what to measure instead.
Customer Experience Benchmarking: How to Measure Against Industry Standards
A complete guide to CX benchmarking — how to measure your customer experience performance against competitors and industry standards using both quantitative metrics and qualitative interviews.
Central Tendency Bias: Why Respondents Cluster on the Middle (and How to Fix It)
Central tendency bias is the tendency of respondents to avoid the extreme ends of a rating scale and pick the middle. Learn why it happens, how much it flattens your data, the neutral-midpoint debate, and how to design questions that capture real opinion.
Proxy Response Bias: Why the Question, Not the Person, Decides How Wrong a Proxy Is (2026)
Observability and interaction explain over 60% of the gap between self-reports and proxy reports. Proxy error is systematic and directional, which is why adding more proxies makes you more confident and no more correct.
Friction Log: How to Turn Everyday Product Friction Into Prioritized Research
A practical guide to running a friction log — capture, categorize, and prioritize product friction, then validate it at scale with AI-moderated interviews. Includes a template, severity scale, and step-by-step workflow.
Key Informant Interviews: Why One Person Cannot Speak for a Whole Company (2026)
A key informant's report correlates only .612 with an independent source - and just .502 on internal process questions. What the measurement literature says about interviewing one person about a whole organization.
Statistical Significance in Survey Research: A Plain-English Guide (2026)
A plain-English guide to statistical significance for survey and market researchers: what p-values and confidence levels really mean, how to test differences, the myths to avoid, and when significance matters less than insight.
NPS Follow-Up Interviews: How to Turn Your Score Into Actionable Insights
NPS tells you the score. Follow-up interviews tell you what to do about it. Learn how to run qualitative interviews with Promoters, Passives, and Detractors to unlock the real story behind your Net Promoter Score.
Mm Hm, Right, Oh: How Your Listening Noises Change the Answer (2026)
The small sounds an interviewer makes while listening are not interchangeable. Learn what mm hm, right, and oh each do to the next thing a participant says.
The Zero Point Moved: Adaptation and Response Shift in Long-Running Research (2026)
Your satisfaction tracker is flat while the product got better. That is not a measurement failure: the internal scale users rate against re-zeroes itself every time you ship.
The Theme Is Real and the Percentage Is Noise: Detection vs Quantification Limits (2026)
Finding a theme and measuring how common it is are two different instruments with two different thresholds. Analytical chemistry separates them formally, and qualitative research should too.
Why the Loudest Complaint Hides the Real One: Masking in Customer Interviews (2026)
One dominant complaint does not just take up airtime - it raises the threshold for everything quieter, asymmetrically, and your analysis then discards what was buried. A protocol for hearing the masked signal.
Um, Uh, and the False Start: What Transcript Cleanup Deletes (2026)
Filled pauses are not noise. See what um and uh signal, why listeners benefit from them, and why your transcription tool removes them by default.
Types of Surveys: A Complete Guide to Survey Types and When to Use Each
From cross-sectional to longitudinal, satisfaction to concept-testing surveys — learn the major types of surveys, how they differ, when to use each, and why AI-moderated conversations often beat a static form.
Topic Modeling for Customer Feedback: How to Find Themes in Open-Ended Responses at Scale
A practical guide to topic modeling for customer feedback — how LDA and modern NLP surface hidden themes in open-ended survey responses and reviews, the limitations of traditional methods, and the faster AI-native alternative.
Qualitative Data Visualization: How to Turn Interviews and Open-Ended Feedback Into Visuals That Persuade
A complete guide to qualitative data visualization — word clouds, thematic maps, affinity diagrams, journey maps, sentiment charts, and quote boards — plus best practices and how AI generates them automatically.
Always, Never, Everyone: What Extreme Wording Actually Signals (2026)
When a participant says it never works, the extremity is evidence about their expected audience, not about the failure rate. How to analyse extreme case formulations.
SUPR-Q: The Standardized Questionnaire for Measuring Website Quality, Trust & Loyalty (2026 Guide)
SUPR-Q is an 8-item questionnaire that scores your website or app on usability, trust, appearance, and loyalty — then converts it to a percentile rank against a normative database. Here is how to run, score, and interpret it (and how to do it faster with AI).
Nonresponse Bias: How Missing Respondents Skew Your Data
Nonresponse bias occurs when the people who do not answer your survey differ systematically from those who do. Learn why a low response rate is not the same as bias, how to detect it, and how to reduce it.
B2B vs B2C Customer Research: Key Differences and How to Run Each (2026)
How B2B and B2C customer research differ across sample size, recruiting, buying units, depth, and cadence — plus how to run each well and why AI interviews fit both the hard-to-reach B2B buyer and the high-volume B2C audience.
Survey Fatigue: Why It's Getting Worse (And How AI Interviews Solve It)
Survey fatigue is driving response rates to historic lows. This guide explains why it is happening, what it costs your research, and how AI-moderated interviews deliver better data without burning out respondents.
Market Research Surveys: The Complete 2026 Guide
A complete guide to designing, running, and analyzing market research surveys — survey types, question design, sample size, and analysis. Plus why AI-moderated conversational research now beats static questionnaires for understanding the "why" behind the data.
Focus Groups: Advantages and Disadvantages (2026)
A clear-eyed breakdown of the advantages and disadvantages of focus groups — group dynamics, groupthink, cost, and bias — plus how AI-moderated 1:1 interviews keep the upside while eliminating the downsides.
Information Architecture Research: The Complete Guide (2026)
Information architecture research uncovers how users mentally organize information so your navigation, labels, and structure match their expectations. Learn the core methods — card sorting, tree testing, first-click testing, and mental-model interviews — and how to run them faster with AI.
How to Conduct Market Research: A Step-by-Step Guide (2026)
A practical, step-by-step guide to conducting market research — from defining objectives to primary and secondary research, analysis, and action. Includes real industry data and how AI-native tools compress a months-long process into days.
Concept Testing: The Complete Methodology Guide
How to evaluate product and marketing ideas with target audiences before development — covering methods, metrics, sample sizes, and AI-powered approaches.
The Novelty Effect: Why New Features Fool Your Metrics
The novelty effect is a temporary spike in engagement caused by the newness of a feature rather than its durable value. Learn how it distorts A/B tests and launch metrics, how to detect it, and how longitudinal research tells novelty from real value.
Aha Moment Research: How to Find, Validate, and Engineer Your Product's Activation Moment (2026 Guide)
The complete 2026 guide to Aha moment research: the four-step discovery method, famous examples (Facebook, Twitter, Slack, Pinterest) with source confidence, common mistakes, and the AI-native research workflow that compresses discovery from quarters to weeks.
Customer Experience (CX) Research: The Complete Guide
A complete guide to customer experience (CX) research: what it is, the core methods and metrics, a 7-step process, common pitfalls, and how AI-native tools run it in hours instead of weeks.
When Participants Ask What You Meant: Repair in Research Interviews (2026)
Conversation repair happens about once every 1.4 minutes. In an interview, the moderator's improvised answer to what do you mean is the question that actually got answered.
A Fast No and a Slow Yes: What Response Timing Really Tells You (2026)
The fastest responses in conversation are blunt rejections and the slowest are hedged acceptances. Below 700 ms, timing does not distinguish a yes from a no at all.
Interviewer Variance: Every Participant Answered a Slightly Different Question (2026)
Nothing is malformed, nobody lied, the arithmetic is right -- and the study is still wrong, because the stimulus was not held constant and the transcript shows a constant one.
What Participants Mean But Never Say: Implicature in Interview Answers (2026)
Participants routinely convey more than their words state. Learn to read conversational implicature, run the cancellation test, and stop coding interviews literally.
Heterogeneous Treatment Effects: Nobody Experienced Your Average (2026)
A modest average lift can hide substantial benefit for some, nothing for most, and real harm for a few. How to look for that without manufacturing false findings.
How to Analyze Survey Data: A Step-by-Step Guide for Real Insights (2026)
A practical, step-by-step guide to analyzing survey data: cleaning responses, choosing the right analysis (frequencies, cross-tabs, significance testing), coding open-ended answers, avoiding bias, and using AI to turn raw responses into decisions in minutes.
Survey Sample Size: How Many Responses Do You Really Need? (2026 Guide)
A practical guide to survey sample size — formulas, calculators, real benchmarks by use case, and why AI-moderated interviews change the qual-vs-quant tradeoff entirely.
Thematic Analysis vs Content Analysis: Which Qualitative Method Should You Use? (2026)
A clear comparison of thematic analysis and content analysis — what each method is, how they differ on quantification and depth, when to use which, whether to combine them, and how AI-assisted analysis speeds both.
Multi-Armed Bandits vs A/B Tests: When Adaptive Allocation Costs You the Answer (2026)
Bandits minimise regret; A/B tests minimise estimation error. You cannot fully have both. The power arithmetic, the bias in adaptively collected data, and how to choose for a given decision.
Interference Between Users: Why Your A/B Test Control Group Is Not a Control Group (2026)
When one user's treatment affects another user's outcome, your A/B test is biased, not noisy. The four interference channels, the three designs that fix them, and how to detect the problem before you spend the traffic.
Usability Benchmarking: How to Run a Benchmark UX Study and Track Metrics Over Time
The complete guide to UX benchmarking — what it is, the metrics to track, how to run a repeatable benchmark usability study, sample sizes, and how AI-moderated research makes continuous benchmarking practical.
Landing Page Testing: How to Find Out Why Your Page Does Not Convert
A complete guide to landing page testing beyond A/B tests — how to measure whether your page communicates value, why visitors bounce, and how to interview real visitors to fix the message, not just the button color.
Convenience Sampling: When Fast and Cheap Is the Right Call (2026)
A practical guide to convenience sampling — what it is, its advantages and hidden biases, when it is acceptable, how to reduce bias, and how AI-native research makes rigor almost as fast as convenience.
Courtesy Bias: Why Respondents Tell You What You Want to Hear
Courtesy bias is when respondents give overly positive, agreeable answers to avoid offending the interviewer or sponsor. Learn where it shows up, the evidence, and how neutral moderation, anonymity, and behavior-based questions fix it.
Why Anything You Measure Mid-Flight Looks Longer Than It Is (2026)
Sampling items that are still in progress oversamples long ones. Learn why snapshot duration estimates are inflated by variance over mean, and how to fix the frame.
Day-in-the-Life Research: How to Shadow Customers and Map Their Real Workflows
A complete guide to day-in-the-life (DITL) research — how to shadow customers through their real routines to uncover context, workarounds, and unmet needs, and how to run it at scale with async AI-moderated interviews.
Question Order Bias: How Survey & Interview Sequencing Skews Your Data (2026)
Why the sequence of your questions changes the answers — the classic Pew and Schwarz findings, the four main order effects, a practical sequencing checklist, and how AI moderation neutralizes the risk.
Slips vs Mistakes: How to Classify User Errors in Usability Testing (2026)
Slips, lapses and mistakes need opposite fixes. How to classify user errors in usability tests using Norman, Reason and Rasmussen, and why only asking can tell them apart.
Solution Validation: How to Test a Solution Before You Build It (2026)
A practical guide to solution validation — how to prove your proposed solution actually solves the problem and delivers value before you commit engineering time. Covers solution interviews, prototype testing, fake-door and concierge tests, the signals that count, and how to validate at scale with AI.
Customer Needs vs. Wants: How to Tell What Users Actually Need (2026)
Customers ask for wants but buy to satisfy needs. This guide explains the difference between customer needs and wants, why building to stated wants leads to feature bloat, and how to uncover the underlying need with Jobs-to-Be-Done, laddering, and AI-moderated research.
The Framing Effect in Surveys and Research: How Question Wording Reverses Answers
The framing effect means the same question, worded as a gain or a loss, produces opposite answers. Learn how framing distorts surveys and interviews — and how neutral, AI-moderated question design keeps your data honest.
Clumsy Automation: Researching AI Features That Fail at Peak Workload (2026)
Clumsy automation saves time on quiet days and costs it on the worst ones. How to research AI features by workload phase instead of trusting average time saved.
Threshold Testing: How to Find the Level Where Users Start to Notice (2026)
Testing every level wastes most of your participants. How adaptive staircases converge on a perception threshold in 20 trials instead of 200, and how to run one with AI-moderated interviews.
Solicited vs Spontaneous Feedback: Why Pooling Them Corrupts Both
Feedback you asked for and feedback that arrived unasked are two different data-generating processes. Merging them into one ranked list is an arithmetic error, not a shortcut.
Ranking vs. Rating Questions: Which to Use and When
Rating questions score each item independently and scale easily; ranking questions force trade-offs and reveal true priorities. Learn the strengths, weaknesses, and biases of each, and how to choose the right format for clean, decision-ready data.
Stratified Sampling: How to Get Precise, Representative Results (2026)
A complete guide to stratified random sampling — how it works, proportionate vs disproportionate strata, the calculation, why it beats simple random sampling on precision, and how to run it in modern research.
The Taphonomy of Customer Feedback: Which Complaints Survive to Reach You (2026)
Most customer feedback is destroyed before it reaches you, and the filter has a predictable shape. A taphonomic method for naming the evidence classes your channels systematically lose.
Advertising Claim Substantiation: How to Design Survey Research That Backs a Marketing Claim
A claim like "9 out of 10 customers recommend us" is a regulated assertion, and the evidence has to exist before the ad runs. This is how to design the study so the number survives a challenge from a regulator, a competitor, or a self-regulatory body.
Sampling Bias: Types, Examples, and How to Avoid It
Sampling bias is when some people in your population are systematically more likely to end up in your sample than others — quietly invalidating your findings. Learn the six main types, classic examples, and how to build a representative sample at scale.
Social Desirability Bias: What It Is and How to Eliminate It in Research
Social desirability bias makes people tell you what sounds good instead of what is true. Learn what causes it, why it quietly wrecks product decisions, and the seven evidence-based ways to reduce it — including why AI-moderated interviews get more honest answers.
Presupposition: The Part of Your Question Participants Cannot Decline (2026)
A leading question pushes toward an answer. A presupposing question embeds a premise the participant must accept to answer at all -- and neutral rewording does not remove it.
How Long Should a Survey Be? Ideal Survey Length and Question Count
The data-backed guide to ideal survey length — how many questions to ask, how completion rate drops with each question, the 7-minute abandonment cliff, and why conversational AI interviews beat long static surveys.
Inter-Rater Reliability in Qualitative Research: A Practical Guide to Coding Agreement
Learn how to measure inter-rater (intercoder) reliability in qualitative research using Cohen's kappa and Krippendorff's alpha, what thresholds count as reliable, and how AI-native tools make consistent coding the default.
The Delphi Method: A Complete Guide to Reaching Expert Consensus
A practical guide to the Delphi method — the structured, multi-round technique for building expert consensus through anonymous questionnaires and controlled feedback. Learn the process, panel size, rounds, and modern AI-assisted alternatives.
Competing Risks: Why Your Retention Curve Overstates the Churn You Care About (2026)
Your retention curve treats acquisitions, downgrades and payment failures as if those accounts were still at risk of cancelling. That inflates the number. Here is the correction, the size of the error, and the interview that produces the missing field.
Stated vs. Revealed Preferences: Why Customers Say One Thing and Do Another (2026)
Customers routinely say one thing and do another — the say-do gap. This guide explains stated vs. revealed preferences, why the gap exists, what the data shows about its size, and how to design research that gets past what people claim to what they actually do.
Unmoderated Usability Testing: Moderated-Quality Insight at Scale
What unmoderated usability testing is, when to use it, how to write good tasks and measure results, and how AI moderation solves its classic "missing why" problem.
Single Ease Question (SEQ): The 7-Point UX Metric for Task-Level Usability (2026)
The complete 2026 guide to the Single Ease Question (SEQ): the verbatim 7-point scale wording, Sauro–MeasuringU benchmarks (5.3–5.5 average), correlation with task completion, when to use SEQ vs SUS, and how to bundle SEQ into AI-moderated interviews on Koji to get task-level usability scores in days.
Attention Check Questions: How to Catch Low-Effort Survey Responses Without Annoying Real Participants
Attention check questions catch inattentive, low-effort, and fraudulent survey responses. Learn the main types, how many to use, the pitfalls, and why a conversational AI interview reduces the need for them in the first place.
Heuristic Evaluation: The Complete UX Review Guide
Learn how to conduct heuristic evaluations using Nielsen's 10 usability heuristics. Discover when to use expert review vs. user testing, how many evaluators you need, and how AI-assisted research accelerates the process.
Cognitive Walkthrough: The Complete Guide to Learnability Inspection (2026)
Master the cognitive walkthrough — the four-question, task-based usability inspection method developed by Wharton, Polson, Lewis, and Rieman. Learn the original 4-question protocol, Spencer’s streamlined 2-question version, when to choose it over heuristic evaluation, and how to validate the findings with real users in days using AI-moderated interviews on Koji.
When No Study Was Wrong: Why Research Programs Fail Without a Defective Study
Some of the worst research-driven decisions trace to no bad study at all. Every study was true; the loss came from the interactions between them. The safety-engineering framework for losses with no component failure, applied to research.
Statistical Power and Minimum Detectable Effect: Can Your Survey Detect the Change You Care About? (2026)
Margin of error tells you how precise one number is. Minimum detectable effect tells you how big a change has to be before you can see it — and it is roughly twice as large. Includes MDE tables for proportions, scales and NPS.
Scoring Answers You Cannot Verify: Incentive-Compatible Research (2026)
How to score honest answers in customer research when no ground truth exists, using peer prediction, Bayesian truth serum and the surprisingly popular rule.
Why 100 Customers Once Is Not One Customer 100 Times (2026)
Cross-sectional averages do not describe individual customers. What ergodicity requires, why within-person variance is far larger, and when your dashboard is right about the level and wrong about the direction.
Questionnaire Design: The Complete Guide to Writing Questions That Get Honest Answers
A research-backed guide to questionnaire design — defining your constructs, writing unbiased questions, choosing response scales, ordering for flow, pre-testing, and avoiding the biases that quietly ruin your data.
Falsifiable Research Questions: Can Your Study Produce the Answer You Do Not Want? (2026)
A question is falsifiable when you can name the answer that kills the belief and your protocol can produce it. Sharp questions beat big samples by about 78 to 1.
The Misinformation Effect: How Interview Questions Rewrite What Customers Remember (2026)
Leading questions bias the answer you get now. The misinformation effect goes further: words the researcher introduces become part of the participant's memory and contaminate every later answer. The evidence, where it enters a study, and a contamination-safe interview sequence.
Extreme Response Bias: Why Some Respondents Always Pick the Extremes
Extreme response bias (ERS) is the tendency of some respondents to over-use the endpoints of a rating scale regardless of the question. Learn why it happens, how much it distorts your data, and how to design scales and AI follow-ups that capture real opinion.
5-Point vs 7-Point Likert Scale: How Many Scale Points Should You Use? (2026)
A decision guide for rating-scale length — what the reliability research actually says about 5 vs 7 points, the odd-vs-even and neutral-midpoint debates, when each fits, and how AI follow-ups make any scale richer.
Recall Bias: How Faulty Memory Distorts Research (and How to Prevent It)
Recall bias is the systematic error that arises when respondents remember past events inaccurately or incompletely. Learn why memory is reconstructed not retrieved, how telescoping distorts data, and how to design around it.
Participant Confidence Is Not Accuracy: How Interviewer Feedback Inflates Certainty (2026)
A single "good, that is helpful" can inflate how certain a participant says they were, and how well they say they saw. The post-identification feedback research, why first-telling confidence is still informative, and how to capture it before you contaminate it.
Memory Conformity: Why Participants Who Talk to Each Other Start Remembering the Same Thing (2026)
Groupthink bends opinions. Memory conformity bends recalled facts: in Gabbert, Memon and Allan's study, 71% of witnesses who discussed an event reported details only their partner had seen. Where co-witnesses hide in customer research, and how to keep accounts independent.
Problem Validation: How to Prove a Problem Is Worth Solving (2026)
A step-by-step guide to problem validation — how to confirm a problem is real, frequent, and painful enough to build for, before you write a line of code. Includes interview techniques, signals to look for, and how to validate at scale with AI.
Fake Door Testing (Painted Door Test): Validate Demand Before You Build
A practical guide to fake door and painted door testing — how to measure real demand for a feature before writing code, what metrics to track, the ethics, and how to learn the why behind every click.
Prototype Testing and Concept Validation: A Researcher's Complete Guide
Learn how to validate product concepts and prototypes through research interviews before committing to build. Covers when to use each approach, question frameworks, and how AI interviews scale concept validation 10x faster.
How Many User Interviews Do You Need? The Sample Size Guide for Qualitative Research
Discover the right number of user interviews for your research. Learn about data saturation, theoretical saturation, and practical frameworks for knowing when you've collected enough qualitative data.
Negative Controls in User Research: Test Your Process on a Signal That Is Not There (2026)
Run your research process where the answer must be nothing. If it still returns a confident finding, the finding is the process. Three controls you can run this quarter.
Research Design Sensitivity: Would Your Study Have Caught It If You Were Wrong? (2026)
Coverage is the list of topics your guide touches. Sensitivity is whether any answer could have contradicted you. Measure it by seeding falsehoods into your own plan.
Customer Segmentation Research: How to Build Segments That Actually Drive Decisions
How to use qualitative interviews — rather than demographic surveys — to build behavioral and motivational customer segments that product, marketing, and sales teams actually use.
Is 4.1 Good? How to Build Internal Benchmarks and Percentile Norms
A raw score means nothing on its own. When no industry benchmark fits your metric, build a norm bank from your own history and convert scores to percentile ranks. Here is the method, the arithmetic, and the sample size below which it is noise.
The Halo Effect in Customer Research: Why One Good Impression Distorts Every Rating
The halo effect makes one positive impression inflate judgments about everything else — corrupting satisfaction scores, brand ratings, and usability tests. Learn where it hides and how structured, AI-moderated research neutralizes it.
The Dumping Effect: Why the Attributes You Leave Out Change the Scores of the Ones You Keep (2026)
When a perception has no matching scale it lands on the nearest one. The experimental evidence, why it is invisible in the data, and the only structural defense.
Just-About-Right Scales: The Rating Question Whose Average Means Nothing (2026)
JAR scales measure signed distance from an optimum, so their mean is not a summary. How to field, report and interpret them without averaging away the answer.
Attribute Lexicons and Reference Anchors: Getting Every Rater to Mean the Same Thing (2026)
How to pin rating-scale attributes to external reference anchors so two raters produce comparable numbers, with a convergence test and thresholds you can ship against.
Customer Needs Gap Analysis: How to Find Unmet Needs Before You Build (2026 Guide)
A step-by-step guide to running a customer needs gap analysis — comparing what customers need against what your product delivers, scoring importance vs. satisfaction, and ranking the underserved opportunities worth building.
Margin of Error in Surveys: What It Means and How to Calculate It (2026)
A plain-English guide to survey margin of error — the formula, a worked example, what changes it, common misreadings, and why AI-moderated interviews sidestep the breadth-vs-depth trade-off entirely.
MVP Validation: 9 Proven Methods to Test Your Minimum Viable Product (2026 Guide)
A complete guide to MVP validation — what to test, the 9 best methods (smoke tests, concierge, Wizard of Oz, paid pilots, and more), success metrics, and how Koji runs MVP validation interviews in days.
UX Research Methods: The Complete Toolkit for Researchers and Product Teams
A comprehensive guide to every major UX research method — qualitative and quantitative, generative and evaluative — with frameworks for choosing the right method and how AI-powered tools are transforming qualitative research at scale.
The Differencing Attack: Why Suppressing the Small Segment Publishes It (2026)
Hiding a small cell and publishing the totals discloses the cell exactly, by subtraction. The same arithmetic works on dashboards - and rounding does not save you.
Qualitative Research Validity and Reliability: How to Build Studies You Can Trust
A practical guide to Lincoln and Guba's trustworthiness framework — credibility, transferability, dependability, and confirmability — and how to build each into your qualitative research studies.
Eye Tracking in UX Research: What It Measures and When to Use It
Eye tracking reveals where users look, in what order, and for how long — the attention data behind the famous F-shaped reading pattern. Learn what eye tracking can and cannot tell you, the key patterns, and how to pair it with AI interviews to capture the "why" behind the gaze.
Qualitative Data Collection Methods: The Complete Guide
A comprehensive guide to every major qualitative data collection method — in-depth interviews, focus groups, observation, ethnography, diary studies, and more — with sample sizes, ethical considerations, and how to choose the right method.
Firmographic Segmentation: The Complete B2B Guide
A complete guide to firmographic segmentation — the core variables, how it differs from demographic and other B2B segmentation, a step-by-step process, real examples, and how AI-moderated research validates segments fast.
No Summary Preserves Everything: What Map Projections Teach About Research Reporting (2026)
Every research summary is a projection, and the impossibility of a lossless one is a theorem rather than a craft failure. Why spot-checking quotes cannot detect the distortion, and what to publish instead.
MoSCoW Method: How to Prioritize Features with Must, Should, Could, and Won't Have
Master the MoSCoW prioritization method. Learn the 60-20-20 effort rule from DSDM, how to run a MoSCoW workshop, and how customer research validates which features truly belong in Must Have.
Observer Bias in Research: How the Researcher's Expectations Skew What They See
Observer bias is when a researcher's expectations unconsciously shape what they record and how they interpret it. Learn how it works, the evidence behind it, and how to design it out — including with a neutral AI moderator.
You Cannot Spot-Check Your Way to Data Quality: The All-or-None Rule for Research QA
A ten-item spot check accepts a 5 percent defective batch 59.9 percent of the time. Deming's all-or-none rule says inspect nothing or inspect everything, and sampling is optimal essentially never.
Did Users Actually Notice? Sensitivity vs Criterion in Did-You-Notice Questions (2026)
The percentage of users who say they noticed your change is not a measurement of whether they noticed. Signal detection theory separates detection from willingness to say yes.
When the Human Baseline Is Wrong: Validating AI Analysis Against an Imperfect Gold Standard (2026)
Checking AI coding against one senior researcher does not measure accuracy - it measures agreement with that person, errors included. Here is how imperfect reference standards bias the number, which direction, and what to do instead.
Usability Metrics: Task Success Rate, Time on Task, and Error Rate Explained
The complete guide to the core usability metrics — task success rate, time on task, and error rate — including industry benchmarks, formulas, sample sizes, and how to capture them automatically with AI-moderated research.
Anchoring Bias in Research and Surveys: How the First Number Skews Every Answer
Anchoring bias makes the first number a respondent sees pull every later judgment toward it — distorting pricing research, scale questions, and willingness-to-pay studies. Learn how to design anchors out, including with AI-moderated interviews.
Van Westendorp Price Sensitivity Meter: The Four-Question Pricing Research Method
The Van Westendorp Price Sensitivity Meter uses four questions to identify the optimal price for any product. Learn how to run the PSM with AI interviews at scale and combine the four numbers with qualitative reasoning.
TURF Analysis: How to Maximize Product and Message Reach
A complete guide to TURF analysis (Total Unduplicated Reach and Frequency): how it works, when to use it, how to run one, and how AI-native research collects the data in days instead of weeks.
Acquiescence Bias: Why Respondents Say Yes (and How to Stop It)
Acquiescence bias is the tendency to agree with survey statements regardless of their content. Learn why it happens, how much it distorts data, and how to design questions that measure genuine opinion.
Usability Testing Questions: What to Ask Before, During, and After a Test
A complete bank of usability testing questions for the pre-test, in-task, and post-test phases, including screening, think-aloud probes, and standardized post-test metrics like SUS and SEQ.
Word-of-Mouth Research: How to Discover Why Customers Actually Recommend You
Learn how to run word-of-mouth research — interviewing customers to uncover why, when, and to whom they recommend you — and how to quantify advocacy drivers at scale with AI-moderated interviews.
How to Conduct Market Research Interviews: Questions, Methods, and AI Automation
A complete guide to market research interviews — including when to use them, how to design effective question guides, and how AI automation makes qualitative market research scalable.
Product Discovery Research: How to Validate Ideas Before Building
Learn how to run effective product discovery research — using AI interviews, problem interviews, concept testing, and JTBD techniques — to build products users actually want.
Every Input Was Accurate and the Difference Was Not: Catastrophic Cancellation in Research Metrics (2026)
Two averages measured to better than 2% produce a gap uncertain by 87%. Subtraction is the one operation that can destroy every significant figure you paid for.
Focus Group vs. Survey: Which Research Method to Use
Focus groups produce rich group discussion but cost thousands and suffer from groupthink; surveys reach scale cheaply but can't probe and face collapsing response rates. Learn when to use each — and how AI interviews give you the depth of a focus group at the scale of a survey.
Generative Research: How to Uncover User Needs You Didn't Know Existed
A complete guide to generative (exploratory) user research — what it is, when to use it, which methods work best, and how AI-powered platforms like Koji make it faster and more scalable than ever.
Survey Randomization: How to Rotate Questions and Answer Options Without Wrecking Your Data (2026)
Randomizing answer order cancels primacy and recency bias — but randomize the wrong thing and you break your tracker, your skip logic and your comparability. The rules for what to rotate, what to anchor, and what to leave alone.
Market Research Methods: The Complete Guide (2026)
A complete, practitioner-focused guide to market research methods — qualitative vs quantitative, primary vs secondary, when to use each, and how AI-native research compresses months of fieldwork into hours.
Crossdating Customer Stories: Placing an Account by Pattern, Not by Counting (2026)
Tenure and adoption counts are ring counts with no internal check. How dendrochronology places a sample by matching its pattern against a master chronology, and how to build one for accounts.
What Is User Research? The Complete Beginner's Guide
A complete guide to user research — what it is, why it matters, the different types and methods, and how to get started.
Zero-Party Data: What It Is and How to Collect It with AI Interviews (2026)
Zero-party data is information customers intentionally and proactively share — their preferences, intentions, and motivations. Learn what it is, how it differs from first-party data, and why AI conversational interviews are the richest, most consent-first way to collect it.
AI-Powered Concept Testing: How to Validate Ideas Through Conversation
How to run concept testing with AI interviews instead of surveys. Get richer feedback on product concepts, messaging, and design directions — automatically, at scale, with no moderator needed.
Just-Noticeable Difference: The Smallest Product Change Users Can Actually Perceive (2026)
A change can be statistically significant and completely invisible. How Weber's law sets the smallest product change users can perceive, and how to measure your own thresholds.
Why Your Theme Discovery Curve Flattens: Dependent Samples and the Illusion of Saturation (2026)
A flat theme curve measures your recruiting as much as your coverage. When both passes come from one channel, reported coverage rises to 99 percent while real coverage falls to 66.
The Priming Effect in Surveys and Interviews: How Earlier Questions Shape Later Answers
The priming effect is when an earlier question or word makes related ideas more accessible and quietly steers later answers. Learn how question-order effects work, the evidence, and how to prevent them — including at scale with AI.
Research Pipeline Yield: Why Every Stage Passes and the Finding Still Arrives Wrong
Research stages sit in series, so their pass rates multiply rather than average. Seven stages at 95 percent deliver a correct finding 69.8 percent of the time. How to run a yield audit and fund the lowest stage.
B2B Buyer Journey Research: How to Map the Modern Buying Committee in 2026
The complete guide to B2B buyer journey research in 2026. Learn how to map the 13-person buying committee, run continuous journey interviews, and turn buyer truth into positioning, content, and sales enablement with Koji.
Churned Customer Interviews: How to Talk to Users Who Left (and Win Them Back)
Learn how to conduct churned customer interviews that reveal why users really left — and how AI-moderated interviews make it scalable. Includes questions, structure, and templates.
Pricing Page Research: How to Test Pricing Pages With Real Customer Interviews (2026 Playbook)
The complete guide to pricing page research and testing. Learn how to combine A/B testing with qualitative customer interviews to lift pricing page conversion 30-50% without changing your price — using AI-moderated research from Koji.
Demand Characteristics: When Participants Tell You What They Think You Want
Demand characteristics are the cues in a study that let participants guess your hypothesis and change their behavior to fit it. Learn where they come from, how they differ from social desirability and the Hawthorne effect, and how to design research that captures honest behavior.
Quota Sampling: A Practical Guide to Getting a Representative Sample
What quota sampling is, when to use it, how to set quotas, and how it differs from stratified and convenience sampling. Includes a step-by-step workflow and how to enforce quotas with screeners and structured questions.
Pretotyping: Build the Right It Before You Build It Right (Complete Guide)
The complete guide to pretotyping — Alberto Savoia's methodology for testing whether you should build a product at all before you build it. Learn the 7 core pretotype techniques, see the Palm Pilot and IBM speech-to-text case studies, and discover how AI-moderated interviews validate pretotype signal in days.
Tenure, Calendar, or Vintage: The Three Effects Hiding in Every Cohort Chart (2026)
Every cohort chart contains three clocks at once: time since signup, calendar date, and signup vintage. Learn the grid-reading diagnostic that tells them apart on sight.
Three Stories, One Grid: The Question Your Cohort Data Cannot Answer (2026)
Tenure, calendar and vintage are exactly collinear, so infinitely many contradictory explanations fit a cohort grid perfectly. No amount of data resolves it. Interviews do.
Dot Voting: A Facilitation Guide for Prioritizing Ideas with Teams and Customers
A practical guide to dot voting — how to run it, allocation rules, variants, common pitfalls like groupthink and anchoring, and how to scale a vote beyond the room to hundreds of real customers with AI interviews.
User Research for Product Redesign: How to Validate Before You Rebuild
A three-phase research framework for product redesigns — covering discovery, concept testing, and launch validation — that prevents the most expensive redesign mistake: building what looks good internally but alienates existing users.
How to Avoid Leading Questions in Surveys and Interviews
Leading questions quietly bias your research data. Learn how to spot and rewrite leading, loaded, and double-barreled questions — and how Koji's AI writes neutral questions and probes without steering respondents.
Grounded Theory in Qualitative Research: A Practical Guide
A practical guide to grounded theory methodology — how to collect, code, and analyze qualitative data to develop theory from the ground up, and how AI-powered tools accelerate the iterative analysis process.
Experience Sampling Method (ESM): A Complete Guide to In-the-Moment Research
What the experience sampling method is, how it differs from diary studies and surveys, when to use it, how to design an ESM study, and how AI-native async interviews make in-the-moment research practical at scale.
RICE Prioritization Framework: How to Score and Rank Product Ideas
Master the RICE scoring framework (Reach, Impact, Confidence, Effort) for product prioritization. Includes the formula, worked examples, free template, and how customer research transforms Confidence scores.
Netnography: How to Research Online Communities (2026 Guide)
A complete guide to netnography — the qualitative method for studying online communities. Learn Kozinets' framework, the six steps, ethics, examples, and how AI accelerates analysis of community data.
Ideal Customer Profile (ICP): Definition, Template, and How to Build One with AI Interviews (2026)
A complete guide to building an Ideal Customer Profile — definition, B2B and B2C templates, ICP vs persona, real examples, and how to validate your ICP with Koji's AI interviewer in days, not months.
Lean Startup Methodology: The Complete 2026 Guide to Build-Measure-Learn
A practical guide to Lean Startup — Eric Ries's Build-Measure-Learn loop, validated learning, MVPs, pivot vs persevere, and how Koji's AI interviewer accelerates every loop.
Product Marketing Research: The 2026 Playbook for PMMs Who Need Buyer Truth on Demand
The complete playbook for product marketing research in 2026. Learn the five PMM research types (win-loss, positioning, competitive intel, ICP, launch), the modern continuous-research operating model, and how Koji compresses a quarter of research into a week.
Research Bias: The Complete Guide to Cognitive Biases That Corrupt User Research
A comprehensive guide to the 9 most damaging cognitive biases in user research — from confirmation bias to social desirability bias — with practical strategies to detect and eliminate them before they corrupt your findings.
Secondary Research: The Complete Guide to Desk Research for Product and UX Teams
A complete guide to secondary research (desk research) — what it is, internal and external sources, a 5-step process, when it is not enough, and how it complements primary user research with Koji.
Why Your Satisfaction Score Stays Flat While Satisfaction Falls (2026)
Inbound feedback is a catch-per-unit-effort index, and those are famously hyperstable: they hold steady while the thing they measure collapses. The fisheries fix is a survey with a fixed design.
Projective Techniques in Market Research: The Complete Guide
A practitioner's guide to projective techniques — word association, sentence completion, collage, personification and more. Learn when to use them, real examples, and how AI moderation runs them at scale.
Product Dogfooding: A Complete Guide (And Where It Falls Short)
What product dogfooding is, where it came from, how to run it well, and the bias that makes it dangerous on its own — plus how to pair dogfooding with real customer research.
Accents, Dialects and AI Transcription: How to Check Your Voice Research Works for Everyone
Speech recognition error is not evenly distributed across your participants. Here is how to measure word error rate by speaker group, why concept error rate matters more than WER, and how to design voice studies that do not quietly exclude people.
Repertory Grid Technique: A Complete Guide for Customer Research
How to use the repertory grid technique to uncover the hidden constructs customers use to evaluate products — with triadic elicitation, laddering, analysis, and how to run it at scale with AI interviews.
Why Your Newest Cohort Always Looks Best: Reporting Lag in Customer Feedback (2026)
A recent cohort shows fewer complaints because it has had less time to report them, not because it is healthier. How to build a development triangle for feedback data and compare cohorts at equal maturity.
Survey Weighting: How to Correct a Skewed Sample
A practical guide to survey weighting — post-stratification, raking, and propensity weighting — plus how to calculate design effect and effective sample size, and when weighting cannot save your data.
Tree Testing: The Complete Guide to Testing Your Information Architecture
A comprehensive guide to tree testing — the UX research method for validating information architecture and navigation before you build.
Customer Validation: The Complete 2026 Guide to Validating Your Product With Real Customers
A practical guide to customer validation — Steve Blank's second phase of customer development, validation methods, sales-led tests, and how Koji runs validation interviews in days, not months.
A/B Testing vs. User Research: When to Use Each (And When to Use Both)
Understand when A/B testing and qualitative user research each shine, and how to combine them for better product decisions. Includes framework for choosing methods, real case studies, and how AI interviews make mixed methods accessible.
Error Propagation in Research Metrics: What Happens to Uncertainty When You Combine Numbers (2026)
Averaging four sub-scores makes your number more precise. Subtracting two averages can make it meaningless. Both follow the same rule. Here is the rule, with worked examples.
Survey Question Types: The Complete Guide to 14 Question Types with Examples (2026)
A complete reference of every survey question type — open-ended, closed-ended, Likert, matrix, ranking, semantic differential, and more. When to use each, real examples, common pitfalls, and the AI-native approach that combines them all in one conversation.
User Persona Template: 7 Free Templates and Examples for Product Teams (2026)
A complete library of user persona templates with real examples — from lightweight personas you can build in an hour to research-backed personas that drive product decisions. Includes fillable fields, expert tips, and how to generate personas from real customer interviews with AI.
The Complete Guide to AI-Powered Qualitative Research
Everything you need to know about using AI for qualitative research — from methodology selection to automated analysis. Learn how AI interviews, voice conversations, and automated theming are transforming how teams understand their customers.
Service Blueprint: A Complete Guide for UX Researchers (2026)
Master service blueprinting — the visualization technique that maps frontstage and backstage processes behind every customer touchpoint. Includes the 5-step NN/g process, real-world examples from Airbnb and Spotify, and how to use Koji to gather the cross-functional research that makes blueprints accurate.
Customer Development: The Complete Guide to Steve Blank's 4-Step Methodology (2026)
Master Steve Blank's Customer Development methodology — Discovery, Validation, Creation, and Company Building. Learn the framework that prevents the #1 reason startups fail and how AI-native research platforms like Koji compress months of customer interviews into days.
The Definitive Guide to User Interviews
Everything you need to plan, conduct, and analyze user interviews that produce actionable research insights.
AI Survey Generator: Build Smart, Adaptive Surveys in Minutes (2026 Guide)
A practical guide to AI survey generators in 2026 — how they turn a research goal into a complete questionnaire, why conversational follow-ups outperform static forms, and how Koji generates a full interview guide in under 60 seconds.
The Complete Guide to Thematic Analysis
Learn how to systematically analyze qualitative data using Braun and Clarke's six-phase thematic analysis framework.
How to Write Great Interview Questions
Learn to craft open-ended, neutral interview questions that surface genuine user insights instead of confirmation bias.
Jobs-to-Be-Done Interview Guide
Learn the JTBD interview methodology to uncover why customers switch products and what progress they're trying to make.
The Mom Test: How to Talk to Customers Without Being Misled
Learn Rob Fitzpatrick's Mom Test methodology to ask questions that even your mother can't lie to you about.
How to Find and Recruit Research Participants
A practical guide to sourcing, screening, and scheduling the right participants for your qualitative research study.
How Many Interviews Are Enough? A Guide to Sample Size
Understand saturation, practical guidelines, and research-backed recommendations for qualitative sample sizes.
Affinity Mapping: Organize Qualitative Data Into Themes
Learn how to use affinity mapping to group qualitative research data into meaningful clusters and uncover actionable patterns.
Customer Signals: Building an Always-On Insight Layer for Product Decisions
What customer signals are, where they come from, and how to build an always-on signal layer that continuously feeds product decisions — instead of relying on quarterly research projects.
Likert Scale Questions: How to Use Rating Scales in User Research
A complete guide to Likert scale questions in user research — what they are, when to use them, how to write them correctly, and how Koji's AI interviews take rating scales further by pairing quantitative scores with qualitative follow-up.
B2B User Research: How to Interview Enterprise Customers Without the Scheduling Nightmare
B2B user research is harder than consumer research — limited access, complex stakeholders, and brutal scheduling constraints. This guide explains how to run deep, qualitative enterprise research at scale using AI-moderated interviews.
Longitudinal Research: How to Track User Behavior and Attitudes Over Time
Longitudinal research captures how users change over time — not just a snapshot. This guide explains panel studies, cohort studies, and how AI-moderated interviews make multi-wave research feasible for any team.
How to Do User Research on a Budget: 12 Low-Cost Methods (2026)
You do not need a big budget for user research. 12 low-cost methods, a free tool stack, and how AI makes rigorous research nearly free for small teams.
System Usability Scale (SUS): Complete Guide with Calculator, Benchmarks & Examples
The definitive 2026 guide to the System Usability Scale (SUS): the 10-question formula, scoring calculator, Sauro–Lewis benchmark grades, and how to deploy SUS at scale with AI-moderated interviews on Koji.
Job Stories vs User Stories: Which Format Should Your Team Use?
A practical comparison of job stories and user stories — the two dominant formats for capturing what software needs to do. Includes when each format wins, how to convert one to the other, and how to source job stories directly from customer interviews.
Pilot Study in User Research: How to Pre-Test Your Methodology Before Going Live (2026)
A pilot study is a small-scale rehearsal of your full research project that catches broken questions, biased prompts, and recruiting issues before they invalidate your real data. Learn when to run one, how many participants you need, what to test, and how AI-moderated platforms compress the pilot loop from weeks to hours.
Customer Discovery vs. Customer Validation: Key Differences & When to Do Each
Customer discovery confirms a real problem; customer validation confirms people will buy your solution. Learn the differences, the order, and when to do each.
Wizard of Oz Testing: How to Validate Product Ideas Without Building Them
The complete guide to Wizard of Oz testing — a UX research method where humans simulate AI or system functionality to test concepts before any code is written. Includes when to use it, how to design a study, ethical guardrails, and how AI interview platforms like Koji extend the method.
How Might We Questions: The Complete Framework for Turning Insights Into Innovation Opportunities
Master the How Might We (HMW) question framework — its origin from Min Basadur and IDEO, the linguistic logic of why it works, the seven HMW patterns, common mistakes, real examples like P&G Coast, and how AI-native research lets you generate sharper HMWs from real customer evidence.
What Is Qualitative Research? Methods, Examples, and How AI Changes It
A complete guide to qualitative research: what it is, the five core methods, how it differs from quantitative research, real examples, and how AI-moderated interviews let any team run qualitative research at scale.
Case Study Research: The Complete Methodology Guide for UX and Product Teams (2026)
How to design and run case study research — types of case studies, when to use them, and how AI accelerates multi-source data collection.
Sean Ellis Test: The 40% Rule for Product-Market Fit (Complete 2026 Guide)
The Sean Ellis Test (40% rule) measures product-market fit with one question. Complete 2026 guide: how to run it, score interpretation, common mistakes, and how AI interviews unlock 5x richer insights.
Requirements Gathering Interviews: Techniques, Questions, and a Template
Run requirements gathering interviews that surface what users actually need — with proven elicitation techniques, a reusable question bank, a step-by-step template, and how AI tools like Koji scale them.
MaxDiff Analysis: The Complete Guide to Maximum Difference Scaling (2026)
Learn how MaxDiff (Maximum Difference Scaling) produces sharper feature and message prioritization than rating scales — and how to pair it with conversational AI interviews to capture the why behind every score.
Primary vs. Secondary Research: Differences, Examples, and When to Use Each
A clear, practical comparison of primary and secondary research — what each one is, how they differ in cost, time, and reliability, real examples of both, and how to combine them so you get exclusive insight without wasting months.
Top Tasks Analysis: How to Identify the Few Tasks That Matter Most
A complete guide to top tasks analysis — Gerry McGovern's methodology for finding the small set of tasks customers actually use your product or website to accomplish. Includes how to run a top tasks survey, calculate the long-tail, and validate the findings with AI customer interviews.
Skip Logic in Surveys: A Complete Guide to Branching, Conditional Logic, and Smarter Question Flow
Skip logic — also called branching logic — routes respondents past irrelevant questions based on what they've already said. Learn when to use it, how to design it, and why static surveys cost you up to 40% of your data quality.
Qualitative vs. Quantitative Research: When to Use Each Method
A clear breakdown of qualitative and quantitative research — what each method reveals, when to use each, and how to combine them for the most complete picture of your users.
Messaging Testing: How to Find Copy That Converts (with Real Customers)
A complete guide to messaging testing — how to validate headlines, value propositions, and ad copy with real prospects before spending on launch. Covers monadic vs sequential designs, sample sizes, MaxDiff and forced-choice methods, and how to capture both the winner and the reasoning using AI conversational research.
User Research Goals and Objectives: A Complete Guide with Examples
How to define clear, measurable user research goals and objectives that align with business outcomes. Includes 12 real examples, the SMART framework adapted for research, common pitfalls, and how AI-native tools translate goals into ready-to-run interview scripts.
Product Analytics vs. User Research: When to Use Each (2026 Guide)
Product analytics tells you what users do; user research tells you why. Learn when to use each, how they combine, and how to get the why at analytics speed.
Customer Retention Research: The Complete 2026 Playbook for Reducing Churn Before It Happens
A practitioner's guide to customer retention research — how to combine churn interviews, stay interviews, NPS follow-ups, and continuous voice-of-customer programs to reduce churn 25% or more. Includes question templates, sampling frameworks, and how AI-moderated research scales retention listening across your entire customer base.
Triangulation in Research: Combining Methods for Stronger, More Credible Insights (2026)
Triangulation is the practice of using multiple data sources, methods, researchers, or theories to validate a finding. Learn Denzin's four types, when to use each, and how AI-native research platforms make multi-method studies practical instead of aspirational.
Conjoint Analysis: The Complete Guide to Trade-Off Research (2026)
A complete guide to choice-based conjoint analysis (CBC) for pricing, feature bundling, and competitive simulation — plus how AI-native research platforms make conjoint accessible without specialist consultants.
Customer Health Score: How to Build a CHS Model for SaaS (Complete 2026 Guide)
A complete guide to designing, calculating, and acting on a Customer Health Score (CHS). Includes formulas, weighting examples, qualitative inputs from AI interviews, and rollout templates for CS and product teams.
Open-Ended vs. Closed-Ended Questions: Examples and When to Use Each
Open-ended questions reveal the "why" in respondents' own words; closed-ended questions deliver clean, countable data. Learn the difference, see examples of both, and discover why the best research pairs them — and how AI captures both at once.
Co-Design: The Complete Guide to Participatory Research and Co-Creation (2026)
How to run co-design and participatory research — methods, workshop formats, when to use it, and how AI scales the recruitment and synthesis phases.
User Acceptance Testing (UAT): A Practical Guide for Product Teams in 2026
Everything product teams need to plan, run, and sign off User Acceptance Testing (UAT) in 2026 — the 7-step process, the 6 UAT types, exit criteria, common pitfalls, and how Koji turns scattered UAT feedback into a single ranked report.
Formative vs. Summative Research: When to Use Each Method (And Why It Matters)
Formative research shapes a product while it's still being built. Summative research evaluates how it performs after it ships. Confusing the two is the most common reason research budgets get wasted on the wrong question at the wrong time.
Data Saturation in Qualitative Research: How to Know When You Have Enough
Data saturation is the point at which additional interviews stop producing new information. This guide covers the four types of saturation (theoretical, data, code, meaning), how to recognize and document them, the empirical sample sizes from Hennink and Guest, and how AI-moderated interviews let you reach saturation in days instead of months.
NPS Benchmarks 2026: Net Promoter Score by Industry (Complete Reference)
Compare your NPS to 2026 industry benchmarks for SaaS, ecommerce, financial services, healthcare, and more. Includes what counts as "good", scoring math, and how to dig into the "why" behind your score with AI follow-up interviews.
Synthetic Users in Research: Validity, Bias, and When AI Personas Are (and Aren't) Trustworthy
A research methodology guide to synthetic users — what they are, the documented bias problems (sycophancy, sign-flipping, shallow insights), the legitimate use cases, and why real AI-moderated interviews are now fast enough that the synthetic-vs-real tradeoff has fundamentally shifted.
Brand Tracking Studies: How to Measure Brand Health Over Time (2026)
A complete guide to brand tracking studies — what to measure, how often to run them, sample size, and how AI-native platforms make continuous brand tracking affordable for the first time.
Task Analysis in UX Research: A Complete Methodology Guide
Task analysis is the foundation of usability — the systematic study of how users complete goals. This guide covers hierarchical task analysis (HTA), cognitive task analysis (CTA), the 7-step process, real examples, and how AI-moderated voice interviews let teams build task models from hundreds of users in days.
Phenomenological Research: How to Study Lived Experience in UX and Product Research (2026)
A practical guide to phenomenological research and Interpretative Phenomenological Analysis (IPA) — how to study how users make sense of significant experiences.
Inductive vs Deductive Research: When to Use Each Approach (with Examples)
A clear, practical 2026 guide to inductive vs deductive research approaches: definitions, when to use each, the hybrid abductive approach, and how Koji blends both into a single AI-moderated workflow.
Conversational Surveys: How AI Interviews Replace Forms (2026)
A complete guide to conversational surveys — what they are, how they differ from chatbot surveys and AI interviews, why they produce 5-10x richer data than forms, and how to design one well.
UX Research Process: A Complete Framework for 2026
A practical end-to-end guide to the UX research process — from defining your research question to activating insights that actually change product decisions.
Content Testing: How to Test Microcopy, Labels, and UX Writing With Real Users (2026)
Six methods for testing whether your words actually work — cloze tests, highlighter tests, comprehension checks, term-choice tests, expectation tests, and label first-click — plus how to run them conversationally at scale instead of one participant at a time.
Non-User Research: How to Interview the People Who Never Chose You
Your roadmap is built entirely from the opinions of people who said yes. A guide to researching the four types of non-user — rejecters, the unaware, the DIY crowd, and the constrained — including how to recruit them and what to ask.
AI-Moderated Focus Groups: How to Run Group Research Without a Human Moderator
How AI-moderated focus groups work, when they outperform traditional groups, and how to run them at scale. Get the depth of focus group research without scheduling, moderation, or groupthink.
Kano Model: How to Prioritize Features Using Customer Research
A complete guide to the Kano Model — the feature prioritization framework that maps customer emotions to product decisions. Learn how to run Kano surveys, classify features, and build products customers love.
UX Research Plan Template: How to Structure Any Research Project
A UX research plan aligns your team on what you are studying, why it matters, and what you will do with the findings. This guide provides a complete template and instructions for writing a research plan that stakeholders will actually read and act on.
Ethnographic Research: Methods, Examples, and UX Applications
A complete guide to ethnographic research in UX and product design. Learn field study methods, how to bridge the say-do gap, remote ethnography techniques, and how AI accelerates ethnographic insight at scale.
Think-Aloud Protocol: How to Run and Analyze Think-Aloud Sessions
A complete guide to the think-aloud protocol — the most widely used usability testing method. Learn how to set up sessions, moderate effectively, analyze verbal data, and run remote think-aloud studies.
Focus Group Research: The Complete Guide
Learn when to use focus groups, how to design and moderate them, and when AI-powered individual interviews are a better fit.
First-Click Testing: The Complete Guide to Validating Navigation and Findability (2026)
Master first-click testing — the lightweight UX research method that predicts task success. Learn when to use it, how to run one, sample size guidance, and how to combine click data with AI interviews for the why behind the click.
The 5-Second Test: How to Measure First Impressions and Visual Hierarchy (2026 Guide)
A complete guide to the 5-second test — the lightweight UX research method that measures gut reactions, message clarity, and visual hierarchy. Learn how to design questions, recruit participants, analyze results, and combine 5-second tests with AI interviews.
Research Ethics and Informed Consent: A Practical Guide for UX Teams
A practical guide to ethical UX research — covering the Belmont Report's three principles, GDPR informed consent requirements, how to handle AI tools responsibly, and how to build ethical maturity in your research practice.
Sampling Methods in Qualitative Research: A Complete Guide for Choosing the Right Approach (2026)
Master the eight sampling methods used in qualitative research — purposive, theoretical, snowball, convenience, quota, criterion, maximum variation, and homogeneous. Learn when to use each, how to combine them, and how to determine sample size.
Customer Journey Mapping: The Complete Guide for UX Teams
Learn how to create customer journey maps that reveal pain points, emotional highs and lows, and opportunity areas — and how AI-powered interviews give you the research data to build them faster.
Assumption Testing: How to Validate Product Assumptions Before You Build
Learn how to identify, prioritize, and test the assumptions behind your product decisions — before building the wrong thing. Includes the assumption mapping framework, testing methods, and how AI interviews accelerate validation.
How to Run a UX Research Sprint: The Complete 5-Day Framework
A step-by-step guide to running a focused UX research sprint in 5 days — from question definition to shareable insights — using AI interviews to 10x your speed.
Feature Adoption Research: How to Interview Users Who Aren't Using Your Product
A complete guide to understanding why users ignore, avoid, or misuse features — and how to use AI-powered interviews to get honest answers at scale.
Competitive Intelligence Interviews: What Your Customers Know About Your Competitors
How to gather competitive intelligence through customer interviews — understanding why people chose you, what competitors they evaluated, and what would make them switch.
Asynchronous User Interviews: The Complete Guide to Async Research
Learn how asynchronous user interviews work, why they outperform scheduled sessions for scale, and how AI makes async research as rich as live interviews.
Survey Design Best Practices: From Question Writing to Data Collection
Learn how to design effective surveys with proven best practices for question writing, flow, bias reduction, and data collection — including when to go beyond surveys to AI-powered interviews.
Pricing Research Interviews: How to Understand What Customers Will Pay
Discover how to run qualitative pricing research interviews that reveal willingness to pay, price anchors, and the emotional logic behind buying decisions — beyond what surveys can surface.
Mixed Methods Research: How to Combine Qualitative and Quantitative Data
Learn how to design and run mixed methods research that combines the statistical power of quantitative data with the depth of qualitative insight — including how AI interview platforms like Koji make mixed methods accessible to every research team.
SERVQUAL: The Service Quality Gap Model Explained (2026)
A complete guide to SERVQUAL: the five RATER dimensions, the 22-item expectations-vs-perceptions instrument, the five gaps model, how to score it, its criticisms, and a modern AI-native alternative.
Desirability Testing: Measuring How a Design Makes Users Feel
A complete guide to desirability testing and Microsoft Reaction Cards — how to measure the emotional response to a design, and how to run it at scale with AI interviews.
The RITE Method: Rapid Iterative Testing and Evaluation
A practical guide to the RITE method (Rapid Iterative Testing and Evaluation) — fix usability problems between participants instead of waiting for a final report, and run the cycle faster with AI interviews.
Attitudinal vs. Behavioral Research: What Users Say vs. What They Do
The definitive guide to attitudinal vs. behavioral research — understand the say-do gap, NNG's 2x2 framework, when to use each method type, and how AI-powered interviews scale attitudinal research.
User Research vs. Market Research: Definitions, Differences, and When to Use Each
A complete breakdown of user research vs market research — what each discipline answers, when to use which, where they overlap, and how modern AI interview platforms are merging both into a single workflow.
Jobs to Be Done Framework: The Complete Guide
The definitive guide to the Jobs to Be Done (JTBD) framework — its history, two schools of thought, how to write JTBD statements, famous examples, how to conduct JTBD research, and how AI interviews enable JTBD at scale.
The 5 Whys Technique: Root Cause Analysis for User Research and Product Teams
Learn how to apply the 5 Whys technique in user research and product development to move from surface-level symptoms to actionable root causes — and how AI-powered interviews automate systematic probing at scale.
Double Diamond Design Process: The Research-Driven Framework for Product and UX Teams
The complete guide to the Double Diamond design process — Discover, Define, Develop, Deliver — with research methods for each phase, real case studies, and how AI-powered interviews accelerate the first diamond.
How to Write a UX Problem Statement: Templates, Examples, and Best Practices
A complete guide to writing UX problem statements grounded in user research — with three standard formats (POV, HMW, Job Story), step-by-step process, good vs. bad examples, and how Koji accelerates the research needed to define the right problem.
Conflicting Research Findings: What to Do When Qualitative and Quantitative Data Disagree (2026)
When your interviews say one thing and your analytics say another, averaging them is the worst possible move. A step-by-step protocol for diagnosing and resolving conflicting research findings.
Proxy Research: How to Run User Research When You Can't Talk to Your Users
Blocked from real users by legal, sales, or a locked-down enterprise account? A disciplined framework for using proxies — ranked by evidence quality, with the bias corrections each one requires.
Agent Trajectory Evaluation: How to Judge Multi-Step AI Agents with Real Users (2026)
Outcome-only scoring hides where AI agents actually break. Learn how to evaluate the full trajectory - every reasoning step, tool call, and hand-back to the user - using step-level rubrics and real participant evidence.
Reliability vs. Validity in Research: What They Mean and How to Get Both
A clear guide to reliability versus validity in research: precise definitions, the dartboard analogy, the types of each, how to improve them, and how AI-moderated interviews deliver consistent, accurate insight.
Semantic Differential Scale: The Complete Guide to Measuring Perception
A complete guide to the semantic differential scale — how Osgood's bipolar-adjective method works, when to use it for brand and concept perception, how it differs from a Likert scale, and how to build and analyze one with examples.
Behavioral Research Methods: The Complete Guide for Product and UX Teams
A complete guide to behavioral research methods — what people actually do, not what they say they do. Methods, examples, and how AI-native research with Koji adds the "why" behind the behavior.
Research Brief Template: How to Define Your Research Before You Start
A complete research brief template with sections for problem context, participant profile, methodology, and success criteria — the foundation of any effective user research project.
Outcome-Driven Innovation (ODI): The Ulwick Method for Identifying Unmet Customer Needs
A practical guide to Anthony Ulwick's Outcome-Driven Innovation methodology — how to capture desired outcome statements, prioritize unmet needs, and turn JTBD theory into a measurable roadmap.
User Research Mistakes: 14 Pitfalls That Sabotage Your Insights (2026)
The most common user research mistakes that lead to misleading insights — and how to avoid each one with better methodology and AI-powered interviews.
Solution Interviews: How to Validate Product Ideas Before You Build
A practical guide to running solution interviews — the second half of customer development — to test whether your proposed solution actually solves a real, painful problem.
Preference Testing: The Complete Guide to Validating Design Choices (2026)
A complete guide to preference testing in UX research — when to use it, how to write the questions, how to calculate sample size, how to analyze the results, and how AI-native research with Koji turns binary "A or B" votes into qualitative insight in minutes.
Name Testing: How to Validate a Product or Brand Name With Real Customers
Name testing is the research method for choosing a product, brand, or feature name by measuring how real customers react to it. This guide covers what to measure, how to avoid the classic "pick the favorite" trap, and how to run name testing at scale with AI interviews.
Customer Discovery Workshop: The Step-by-Step Playbook with Templates (2026)
A complete, time-boxed customer discovery workshop playbook — agenda, exercises, templates, and the AI-native interview pipeline that turns workshop hypotheses into evidence within days. Designed for founders, product trios, and discovery teams running their first or fiftieth workshop.
Matrix Questions in Surveys: When to Use Grid Questions (and When They Backfire)
Matrix (grid) questions let respondents rate many items on the same scale in one block. This guide explains how matrix questions work, the straightlining and fatigue problems they cause, design best practices, and how AI interviews capture the same data without the grid.
Survey Response Bias: The 7 Types That Distort Your Data (and How to Reduce Them)
Response bias is the systematic distortion in how people answer research questions — from telling you what they think you want to hear, to agreeing with everything, to misremembering. This guide breaks down the seven most common response biases and how to reduce each one.
Product Adoption: The Complete Guide to Getting Users to Stick (2026)
Product adoption is the journey from a user's first exposure to habitual, value-driven use. This guide breaks down the adoption curve, the stages users move through, the metrics that matter, and how to research the real reasons users adopt — or abandon — your product.
Cohort Analysis: How to Read Retention and Find the "Why" (2026)
Cohort analysis groups users by a shared starting point and tracks their behavior over time, revealing retention patterns that aggregate metrics hide. This guide explains how to build and read cohort tables, interpret the retention curve, and pair the numbers with qualitative research to explain them.
Time to Value (TTV): How to Measure and Reduce It (2026)
Time to value is how long it takes a new user to reach their first real payoff from your product. This guide defines TTV, shares 2026 benchmarks, shows how to measure and shorten it, and explains how to research the friction that slows it down.
Automation Surprise in Research: When Your Pipeline Is Not Doing What You Think (2026)
Aviation human factors has studied mode error for forty years. Your research pipeline has 128 configurations and you chose two of them. Here is the import.
The Ironies of Automation: Why a Human Reviewer Cannot Catch Your AI's Analysis Errors (2026)
Adding a human to spot-check AI coding is the reflex fix. Bainbridge showed in 1983 why it backfires, and the arithmetic is worse than teams expect.
Alarm Flooding: Why Your Research Alerts Stopped Meaning Anything (2026)
Two industries independently discovered that an alerting system has a fixed capacity measured in signals per person per hour. This guide translates the EEMUA 191 and ANSI/ISA-18.2 alarm management benchmarks into research operations, and shows how to rationalize an automated insight feed so the signals that survive still carry meaning.
Function Allocation: Deciding What AI Should Do in Your Research and What You Keep (2026)
The Fitts List asked which tasks humans are better at and which machines are better at. Seventy five years of human factors research says that framing is the problem. This guide replaces the who-does-what question with a stage-by-stage allocation method for research work, and explains why the tedious-versus-judgment split is the wrong seam.
The Swiss Cheese Model for Research: Why Bad Findings Pass Every Check (2026)
How James Reason's Swiss cheese model explains why flawed research findings get past every review, and how to map, decorrelate and strengthen your research defences.
Poka-Yoke for Research: Mistake-Proofing Studies Before Errors Become Findings (2026)
How to apply poka-yoke (mistake-proofing) from the Toyota Production System to surveys, interviews and analysis, with control vs warning devices and a catalogue of research error-proofing.
Work-as-Imagined vs Work-as-Done: Why Process Interviews Describe a Job Nobody Does (2026)
What work-as-imagined, work-as-prescribed, work-as-disclosed and work-as-done mean for user research, why the gap exists, and interview techniques that get closer to how work really happens.
Missing Answers vs. Wrong Answers: Why a Blank Is Worth Twice a Confident Guess (2026)
A missing answer and a wrong answer are not two grades of the same problem. Error-correcting codes price them differently, at exactly two to one, and that ratio should change how you design questions.
Why a Better Analysis Cannot Rescue a Bad Sample (2026)
Sampling error has a floor that no amount of analytical care can cross. Here is the model that sets the floor, the two levers that move it, and why narrowing who you talk to beats running more interviews.
Nobody Mentioned It: What Your Sample Could Not Have Detected (2026)
Silence in your interviews is not evidence a problem is rare. Here is how to compute the prevalence floor your study was blind to, and why that number belongs in every report.
Blanks and Spikes: Two Control Samples That Audit Your Research Instrument (2026)
Analytical labs run two different controls because there are two different ways to be wrong. A spike measures what your process misses; a blank measures what it invents. Here is how to run both on a research pipeline.
Social Listening: The Complete Guide to Monitoring and Acting on Customer Conversations
Learn how social listening works, how to build a program, and how to pair public conversation data with AI-moderated interviews to answer the "why" behind every trend.
Mystery Shopping: The Complete Guide to Measuring (and Modernizing) the Customer Experience
Learn how mystery shopping works, how to design a program, what it can and cannot measure, and how AI-moderated customer interviews capture real experience at a scale traditional secret shoppers never could.
Market Research Online Communities (MROCs): The Complete Guide to Insight Communities
Learn what a market research online community (MROC) is, how insight communities work, their benefits and costs, and how AI-moderated interviews deliver always-on, continuous insight without the overhead of a traditional community.
Focus Groups vs. Interviews: How to Choose the Right Method
Learn when to use focus groups vs. individual interviews in qualitative research. Includes a comparison table, decision framework, and guidance on avoiding groupthink bias.
The Mom Test at Scale: How AI Interviews Replace Manual Customer Discovery
Learn how to apply Mom Test principles at scale using AI-moderated interviews. Includes question templates, common mistakes, and how to convert survey questions.
How to Run 50 Switch Interviews in a Week Without a Research Team
The JTBD Switch Interview captures the Forces of Progress behind every customer decision. This guide shows how AI interviewers automate the technique at 10x scale while maintaining methodological rigor.
Contextual Inquiry: The Complete Guide to Observational Research
Learn how to run contextual inquiry sessions to uncover the real workflows, workarounds, and behaviors your users can't articulate in interviews.
Customer Discovery Interviews: The Complete Guide
Learn how to conduct customer discovery interviews to validate your product ideas before building. Covers Steve Blank methodology, question frameworks, sample sizes, and common mistakes.
How to Conduct Usability Testing: The Complete Guide
A comprehensive guide to usability testing for UX researchers and product managers. Covers types of testing, participant numbers, step-by-step facilitation, and the most common mistakes to avoid.
Surveys vs. Interviews: How to Choose the Right Research Method
A comprehensive comparison of surveys and interviews as research methods. Understand when to use each, the key trade-offs, how to combine them in mixed-methods studies, and why the choice matters for research quality.
Unmoderated vs Moderated User Research: How to Choose
Understand the real differences between moderated and unmoderated user research — and how AI-moderated interviews give you depth at scale that traditional approaches never could.
Diary Studies: The Complete Guide to Longitudinal User Research
Learn how to design, run, and analyze diary studies that capture real user experiences in context. Includes how AI interviews complement diary research at scale.
How to Create Research-Backed User Personas from Customer Interviews
Learn how to build accurate user personas using qualitative interviews rather than assumptions. Includes a step-by-step process for recruiting, interviewing, clustering, and maintaining personas.
Card Sorting: The Complete Guide to Information Architecture Research
Everything you need to run effective card sorting studies — open, closed, and hybrid variants. Includes sample sizes, analysis techniques, and how to combine card sorting with qualitative interviews.
Generative vs. Evaluative Research: When to Use Each Method
Understand the difference between generative and evaluative research, when to use each, and how combining both leads to better product decisions. Includes a comparison table and decision framework.
AI Usability Testing: How AI Moderates and Analyzes Usability Studies in 2026
A practical guide to AI usability testing in 2026 — what AI can moderate and analyze, where it fits alongside click-based testing, and how to capture the "why" behind every usability result.
User Interviews vs Usability Testing: When to Use Each (and How They Work Together)
User interviews vs usability testing — the difference between generative and evaluative research, when to use each, and how one AI platform can run both.
How to Validate Product-Market Fit Through Qualitative Interviews
Learn how to design and run customer interviews specifically focused on measuring and moving your product-market fit score.
Proto-Personas: How to Build Assumption-Based Personas and Validate Them Fast
Learn how to build proto-personas from team assumptions, when to use them, and how to validate them with real customer interviews before they mislead your roadmap.
Experience Mapping: The Complete Guide to Visualizing the End-to-End Customer Experience (2026)
Learn what an experience map is, how it differs from journey maps and service blueprints, and how to build one grounded in real customer interviews rather than assumptions.
True Intent Studies: How to Find Out Why Visitors Come to Your Site (and Whether They Succeed)
A practical guide to true intent studies — the intercept method that reveals why visitors come to your website, whether they accomplish their task, and why they fail.
Semi-Structured Interviews: The Complete Guide
Learn how to design, run, and analyze semi-structured interviews — the gold standard for qualitative research that balances structure with flexibility.
Win/Loss Analysis: How to Learn Why You Win and Lose Deals
A complete guide to running win/loss analysis interviews that improve win rates, sharpen positioning, and give product teams real competitive intelligence.
Startup Idea Validation: How to Test Your Idea with Customer Interviews
A research-backed guide to validating startup ideas through customer interviews — before you write a line of code.
Employee Retention Research: Stay Interviews, Exit Interviews, and What Actually Works
How to use qualitative research — stay interviews, exit interviews, and engagement conversations — to understand why employees leave and what makes them stay.
How to Write a Research Brief: Templates, Examples, and AI-Assisted Generation
A step-by-step guide to writing an effective user research brief. Covers the 7 essential components, participant targeting, methodology selection, and how Koji's AI generates briefs automatically from a plain-language goal.
Human Evaluation of AI Outputs: The Complete Guide for Product Teams (2026)
How to design, staff, and run human evaluation of LLM and AI-agent outputs — rubric design, rater selection, sample size, inter-rater agreement targets, and bias controls — plus how AI-moderated interviews capture the "why" behind every score.
LLM-as-a-Judge vs. Human Evaluation: When to Trust Automated Scoring (2026)
Automated LLM judges agree with humans over 80% of the time on some tasks — and carry position, verbosity, and self-preference biases on others. Here is the evidence, the failure modes, and the calibration loop that lets you use both safely.
AI Red Teaming with Real Users: How to Find Harms Before Your Users Do (2026)
A practitioner guide to adversarial testing of AI products with real people — harm taxonomies, recruiting adversaries, severity scoring, red-teamer wellbeing, and the EU AI Act and NIST obligations that now make it mandatory.
Evaluation Datasets for AI Products: How to Build a Golden Set from Real User Research (2026)
How to construct and maintain the golden dataset your AI evals run against — sizing and confidence intervals, the four-bucket structure, label-error rates in published benchmarks, sourcing acceptance criteria from real users, and versioning against overfitting.
Medical Device Usability Testing: IEC 62366-1 and FDA Human Factors Requirements (2026)
Regulators do not accept "we tested it and users liked it." Here is how usability engineering actually works under IEC 62366-1 and the FDA's May 2026 human factors guidance — critical tasks, formative studies, summative validation, and the parts of the file AI-moderated research can legitimately fill.
Data Annotation Quality: Guidelines, Agreement Metrics, and Gold Tasks That Actually Work (2026)
A practical guide to running an annotation and data-labeling operation: writing guidelines that resolve edge cases, choosing between Cohen's kappa and Krippendorff's alpha, setting gold-task and honeypot rates, and adjudicating disagreement instead of averaging it away.
AI Failure Mode Analysis: An FMEA Framework for AI Products (2026)
How to run Failure Mode and Effects Analysis (FMEA) on an AI product: the failure mode taxonomy, how to score severity, occurrence and detection when failures are probabilistic, and how user research supplies the numbers.
AI Guardrail Testing: How to Measure False Refusals and Over-Blocking with Real Users (2026)
Your safety layer has a false positive rate, and it is costing you users you never hear from. How to measure false refusal rate, run an over-blocking study, and tune guardrails against real user harm instead of vibes.
Usability Issue Severity Ratings: How to Score, Prioritize, and Report UX Problems (2026)
How to rate the severity of usability problems using Nielsen's 0-4 scale, why single-evaluator ratings are unreliable, how to separate severity from priority, and how to replace guessed frequency estimates with measured data.
AI Over-Reliance and Automation Bias: How to Research Whether Users Trust Your AI Too Much (2026)
Users who accept every AI suggestion are a product risk, not a success metric. How to measure over-reliance and automation bias, why self-report fails, and the study designs that produce honest reliance data.
Acceptance Criteria for AI Features: How to Define "Good Enough to Ship" (2026)
Traditional acceptance criteria are binary and per-case; AI features fail probabilistically, so the same approach produces a checklist nobody can sign. This guide shows how to write distributional acceptance criteria, weight false positives against false negatives by user cost, and gather the user evidence that makes a ship decision defensible.
AI Explainability Testing: How to Find Out Whether Your Explanations Actually Help Users (2026)
Explanations that users rate highly often fail to improve their decisions — and in one 3,800-person experiment, the more transparent model made people worse at catching its mistakes. This guide covers the four outcome measures that separate a useful explanation from a satisfying one, and how to test yours.
Why a Vague Question Gets a Short Answer: Specificity and the Length Contract (2026)
Answer length is a property of the question, not of the participant. How the maxim of quantity sets an implied contract for how much detail is required, and how to write questions that earn it.
Staged Rollout for AI Features: Shadow Mode, Canary, and Kill Switches (2026)
A research-first guide to staging an AI feature launch. What shadow mode can and cannot measure, what to ask users at each canary ring, how to pre-register rollback thresholds, and why the EU AI Act made the kill switch a legal requirement.
AI-to-Human Handoff: How to Design and Research the Escalation Moment (2026)
The handoff from AI to a human is where most AI products actually fail. A practical guide to escalation triggers, why accuracy metrics mis-measure handoff timing, what to research at the transfer point, and how to test it with real users.
Algorithm Aversion and Trust Repair: What Happens After Your AI Gets It Wrong (2026)
Users abandon an AI faster than they abandon a human who makes the identical mistake. The research on why, the single design change that raised algorithm adoption from 32% to 76%, and how to research trust repair after an AI failure.
Graceful Degradation for AI Features: Researching What Users Experience When the Model Cannot Deliver (2026)
AI features fail in four distinct ways: unavailable, too slow, too unsure, and out of scope. Learn how to design a degradation ladder for each, what the EU AI Act and NIST AI RMF require, and how to research the degraded state with real users.
Thumbs Up, Thumbs Down: What In-Product AI Feedback Signals Actually Tell You (2026)
Thumbs and report buttons measure who felt strongly enough to click, not what your users think. Learn the self-selection biases that distort every voluntary feedback channel, the implicit signals that are more honest, and how to convert both into research you can act on.
Contestability and Redress: How to Design and Research the Appeal Flow for AI Decisions (2026)
EU AI Act Article 86 became applicable on 2 August 2026. Learn what GDPR Article 22 and the CJEU already require of an appeal flow, why appeal rates are a misleading metric, and how to research whether users can actually contest a decision.
Conversation Memory and Long-Session Degradation: Why AI Interviews Get Worse After Turn 20 (2026)
AI moderators lose the thread in long conversations. The evidence, the four degradation symptoms, the session budget framework, and how to test your own moderator before it costs you a study.
Green Claims Research: How to Substantiate a Sustainability Claim With Consumer Perception Evidence
Every environmental claim carries two substantiation burdens: the science burden and the perception burden. Lab data answers the first. Only research answers the second, and it is the one companies fail. Here is how to design a green claim perception study.
Model Version Drift: What Happens to Your Research When the AI Changes Mid-Study (2026)
When the model behind your AI moderator or analyst is upgraded, your measuring instrument changed. The evidence, the three layers of drift, the bridge sample method, and how to make model version part of your method section.
Reference Prices and Drip Pricing: How to Test a Price Display Without Making a Deceptive Claim
Willingness-to-pay research tells you what people will pay. It says nothing about whether your was-now price or your checkout fees are lawful. Here is the price-display law that changed in 2025 and the comprehension study that produces evidence for it.
Regression to the Mean: Why Your Fix Looks Like It Worked (2026)
Regression to the mean makes ordinary noise look like a successful intervention. Learn the formula that predicts how much of your improvement is arithmetic, the five product-research traps it hides in, and the designs that separate a real win from a bounce-back.
AI Claims Substantiation: How to Prove an AI-Powered Claim Before You Advertise It
Every "AI-powered" claim carries two burdens of proof: an engineering burden (does the system do it?) and a perception burden (what do customers hear?). Learn how to build both evidence files with consumer research before you ship the copy.
Auto-Renewal and Cancellation Research: Testing Whether Subscribers Actually Understood
ROSCA requires clear disclosure, express informed consent, and a simple cancellation mechanism - and defines none of those terms. Learn how to test subscription sign-up and cancel flows for comprehension, and why the vacated Click-to-Cancel rule is still the best research brief available.
Made in USA and Country-of-Origin Claims: Testing What Consumers Actually Infer
The Made in USA Labeling Rule sets a strict three-part standard and carries civil penalties per violation. But the rule governs the claim you make - not the claim customers hear. Learn how to test origin inference from flags, brand names, and qualified claims.
Quasi-Experimental Design: How to Measure Impact When You Cannot Run an A/B Test (2026)
Most product decisions cannot be randomised. Quasi-experimental designs give you a defensible causal answer anyway. Learn which of the three designs your situation calls for, how to write the impact model before the data arrives, and why interviews are the cheapest confounder detector you have.
The Multiple Comparisons Problem: Why Slicing Data Into Segments Manufactures Findings (2026)
Test 20 segments at the 5 percent threshold and you have a 64 percent chance of finding at least one difference that is not there. Learn how to count the tests you actually ran, when to control the family-wise error rate versus the false discovery rate, and why a correction cannot rescue a bad prior.
Health and Nutrition Claims: What Consumer Research Can and Cannot Substantiate
The FTC says consumer surveys are never sufficient to substantiate a health benefit claim - and in the same document says consumer surveys are valuable for determining what claim you made. Both are true. Learn where the line sits and how to build the perception evidence file.
P-Hacking and Researcher Degrees of Freedom: How Analytic Flexibility Manufactures Findings (2026)
Four ordinary analytic choices raise the false-positive rate from 5 percent to 61 percent. Learn what researcher degrees of freedom are, why the garden of forking paths catches honest researchers, and how a one-page pre-committed analysis plan fixes it without banning exploration.
Warranty Comprehension Research: Testing Whether Buyers Understand What Your Warranty Covers
The Magnuson-Moss Warranty Act requires warranty terms in simple and readily understood language, but never defines the test. Here is how to measure what buyers actually understand about coverage, remedy, and process.
Ceiling and Floor Effects: When Your Scale Cannot Measure the Change You Care About (2026)
If more than 15 percent of respondents score the maximum, your metric has gone blind - and it goes blind first on your best customers. Learn how to run a headroom audit, why ceilings manufacture false segment differences, and which question types have no ceiling at all.
Money-Back and Satisfaction Guarantees: Testing What Your Promise Actually Promises
The FTC Guides say you should use Satisfaction Guarantee or Money Back Guarantee only if you refund the full purchase price on request. Here is how to test what buyers believe your guarantee covers, and whether claimants got it.
Chargeback Research: Why Customers Dispute Instead of Contacting You
Card network rules require a cardholder to certify they tried to resolve with the merchant first. That makes every consumer dispute an attested support failure. Here is how to research the cause instead of only fighting the outcome.
Product Recall Notice Research: Testing Whether Safety Notices Reach, Convince, and Move Owners
Recall correction rates sit in the single digits while awareness can be above 80 percent. Those are different variables. Here is how to find which stage of the recall funnel is leaking, using the CPSC evidence base.
Publication Bias and the File-Drawer Problem in Product Research: Why Your Evidence Base Only Remembers the Studies That Worked (2026)
Publication bias is not an academic curiosity. In product research it is worse, because nobody rejects your null study - you simply never write it up. Learn how big the file drawer is, what it does to your confidence, and how to build a study register that closes it.
Lemon Law Research: Measuring When a Buyer Decides a Product Is Beyond Repair
Federal law promises a refund or replacement after a reasonable number of repair attempts, then never defines the number. Here is how to measure the attempt at which your customers actually give up, and why it arrives before the statute does.
Extended Warranty and Service Contract Research: Testing What Buyers Think They Bought
A service contract and a warranty can promise identical coverage and still be different legal instruments. Here is how to measure what buyers believe they purchased at checkout, and why the overlap they paid for twice is the fastest thing to find.
How to Prove There Is No Difference: Equivalence Testing for Product Research (2026)
A non-significant result does not mean there is no difference - it usually means your study could not tell. Equivalence testing is the method that lets you actually claim two things are the same, and product teams make expensive no-difference decisions without it every quarter.
Right to Repair Research: Measuring Whether Owners Can Actually Fix What They Own
Publishing a repair manual satisfies a statute. It does not tell you whether anyone could follow it. Here is how to measure the repair abandonment funnel, and why compliance measures the one stage least likely to be broken.
Implied Warranty Research: Testing What Ordinary Purpose and As Is Actually Mean to Buyers
You are liable for goods being fit for their ordinary purpose, and the ordinary purpose is defined by what your customers actually do. Here is how to measure a warranty you never wrote, and the notice rule that quietly kills most claims before you hear them.
Clickwrap vs Browsewrap: How to Research Whether Users Actually Agreed to Your Terms
Courts decide whether your terms are enforceable by asking what a reasonably prudent Internet user would have seen and understood. That is an empirical question. Here is how to answer it with evidence instead of opinion.
Cronbach's Alpha and Internal Consistency: Does Your Multi-Question Score Actually Measure One Thing? (2026)
A practical guide to Cronbach's alpha for product and UX teams: what it really measures, why the 0.70 threshold is a misquote, why a high alpha does not prove your score is one thing, and what to report instead.
Measurement Invariance: Why You Cannot Compare Scores Across Segments, Languages, or Time (Until You Test This) (2026)
Every segment leaderboard, country comparison and quarterly trend line assumes your questions mean the same thing to everyone. Measurement invariance is the test of that assumption - and it usually fails. Here is what breaks, and what to do about it.
Dark Patterns: How to Test a Flow for Deceptive Design Before a Regulator Does
Dark pattern rules judge effect, not intent. That makes deceptive design a measurement problem, and the measurement is the one thing conversion testing never captures: what the user actually believed.
Construct Validity: How to Tell Whether You Are Measuring the Thing You Named (2026)
Construct validity is the question of whether your engagement score measures engagement. A guide to operationalization, convergent and discriminant evidence, jingle-jangle fallacies, and the discriminant test that kills most product metrics.
Age Assurance and Age Gates: Testing Accuracy, Friction, and Abandonment
Age assurance is the rare feature where friction is the legal deliverable. That inverts the usual research question, and it creates a blind spot analytics physically cannot see: the adult who was wrongly blocked and left.
Secondary Meaning Surveys: How to Prove a Descriptive Name Points to One Source (2026)
A practical guide to secondary meaning and acquired distinctiveness surveys: the legal target, the numbers courts have accepted, why the control term decides everything, and how to run the same study on your own brand in days instead of months.
Likelihood of Confusion Surveys: The Eveready and Squirt Formats Explained (2026)
The two survey formats courts recognise for trademark confusion, the numbers that have persuaded judges, the attacks each format invites, and how to run the same design on your own sub-brand or packaging change.
Blind Analysis: How to Analyze Research Before You Know the Answer
Blind analysis hides which group is which until your analysis is locked. Borrowed from particle physics, it is the cheapest way to stop your expectations from steering your findings.
Genericness Surveys: The Teflon and Thermos Formats, and How a Brand Loses Its Name (2026)
How genericness is measured: the Teflon classification format, the Thermos imaginary-situation format, the exact results from DuPont, American Thermos, Elliott v. Google and Booking.com, and why the question format decides the answer.
Analysis of Competing Hypotheses: How to Test What Your Research Actually Supports
Most evidence that supports your favorite explanation also supports the ones you never wrote down. ACH is the matrix method that finds the evidence which actually discriminates.
Same Data, Different Answers: The Many-Analysts Problem in Product Research
When 73 teams analyzed identical data to test one hypothesis, over 95 percent of the variance in their results was unexplained. Your analysis is one draw from a distribution you never see.
Survey Universe: How to Define Who Counts Before You Collect a Single Answer (2026)
The universe is the population whose opinion is actually relevant to your claim. Get it wrong and no sample size, weighting or analysis can rescue the study. A protocol, four documented failures, and how to enforce it at the door.
Interim Analysis and Sequential Testing: How to Check a Running Study Without Inflating False Positives (2026)
Every modern research tool shows you results while the study is still collecting them. Repeatedly testing accumulating data inflates the false-positive rate from 5% to 25% and beyond. Here is the clinical-trials method for looking as often as you like and still trusting the answer.
Interim Analysis and Stopping Rules: How to Stop a Study Early Without Faking the Result (2026)
Clinical trials solved the problem of looking at data before a study ends. Group sequential designs, alpha spending, and futility boundaries let you stop early without inflating false positives - and the evidence shows what happens when you stop early without them.
Case-Control Research: How to Study Churn and Lost Deals Without Fooling Yourself (2026)
Every churn interview and win-loss study is a case-control design, whether or not anyone says so. Epidemiology has spent seventy-five years learning how these studies go wrong - control selection, admission bias, recall bias, and base rates.
Futility Analysis: How to Decide a Running Study Will Never Answer Your Question
Most teams only ever ask whether a study can be stopped early because it worked. The more valuable question is whether it can be stopped because it never will. Futility rules, stop-for-harm, and who is allowed to make the call.
Calibration Scoring for Research Teams: How to Find Out If Your Insights Were Actually Right (2026)
Research is graded on process and almost never on outcome. Forecasting tournaments solved this with proper scoring rules. Here is how to score a research team on whether its claims came true.
Intention to Treat vs Per Protocol: Which Responses Belong in Your Analysis
Almost every research tool reports on completed responses only. That is a per-protocol analysis, it is the optimistic one, and nobody decided to run it. Here is how to choose an analysis population on purpose.
Levels of Assurance in Research: How Much Confidence a Study Can Honestly Support
Auditing defines three levels of assurance - reasonable, limited, and none. Research reports use one voice for all three. Here is how to pick and state the level before you field a study.
Immortal Time Bias: Why Feature Adopters Always Look More Loyal Than They Are (2026)
Immortal time bias makes every feature-adoption retention chart overstate the feature. Learn how the bias works, why product data is the worst case, and the three fixes.
Corroboration in Research: Why Three Sources Saying the Same Thing Can Be One Source
Evidence from multiple sources only multiplies confidence when the sources are independent. Four ways research sources secretly share an origin, and a ten-minute test for catching it.
Surveillance Bias: Why the Team That Measures Best Looks Worst (2026)
The harder you look, the more you find. Surveillance and lead time bias make well-instrumented teams look worse and useless interventions look effective. Here is how to tell the difference.
The Bradford Hill Criteria: Making Causal Claims When You Cannot Run the Experiment (2026)
Most of what matters in product research cannot be randomised. Bradford Hill nine viewpoints are the framework for building a defensible causal case without an A/B test.
The Healthy Adherer Effect: Why Users Who Finish Onboarding Always Retain Better (2026)
Users who complete your onboarding checklist retain better. So do users who adhere to a placebo. The healthy adherer effect explains why adoption metrics overstate feature impact, why adjusting for covariates does not fix it, and what to do instead.
The Churn Hazard Curve: Why One Churn Rate Hides Three Different Problems (2026)
Your monthly churn rate averages three unrelated problems into one number. Learn to plot the churn hazard by tenure, read the three regimes, and avoid the sorting trap that makes a flattening curve look like product-market fit.
Collider Bias: When Adding a Control Variable Creates the Correlation (2026)
Most research advice tells you to control for more variables. Collider bias is the case where controlling, filtering or segmenting manufactures an association that does not exist. Here is how to recognise it before it reaches a roadmap.
Professional Skepticism in Research: The Duty to Doubt an Answer That Sounds Right
Auditing made skepticism a written requirement with named trigger conditions. Learn the four conditions that oblige further work, why a trusted source never lowers the evidence bar, and how to stop scrutiny being applied only to findings you dislike.
The Stepped Wedge: How to Randomise a Rollout You Cannot Randomise (2026)
You cannot randomise who gets the feature, because everyone is getting it. You can randomise when. The stepped wedge turns a phased rollout into a randomised trial at almost no extra cost, and it is the design B2B teams are already accidentally halfway to running.
Synthetic Control: How to Build a Comparison Group That Does Not Exist (2026)
When you roll out to one market, segment, or account and have no valid holdout, synthetic control builds a weighted blend of untreated units that matched your treated unit before the change. Here is how it works, what it requires, and where it breaks.
Propensity Score Matching and the Pruning Paradox: When Better Balance Makes Your Estimate Worse (2026)
Propensity score matching is the default way teams build a comparable control group from observational data. King and Nielsen showed it often does the opposite of what it promises. Here is the failure mode, how to detect it, and what to use instead.
Instrumental Variables and Encouragement Designs: Measuring an Effect You Cannot Assign (2026)
You cannot force a user to adopt a feature, but you can randomise the invitation. Encouragement designs recover a real causal effect from that nudge, at a price most teams never state: the estimate describes a subpopulation you cannot list.
Total Survey Error: The Seven Ways a Study Is Wrong (and How to Spend a Fixed Budget Across Them)
Sample size buys down exactly one of seven error components. Learn the total survey error framework, why federal agencies report only the computable one, and how to write a one-page error budget before you field.
Mode Effects: When Letting People Choose Voice or Text Changes the Answer
Pew randomly assigned 3,003 people to phone or web and got answers that differed by up to 18 points on identical questions. Here is what that means when your respondents pick their own mode.
Split-Ballot Experiments: How Much of Your Number Is the Question?
Write two versions of the item, randomly assign half your sample to each, and the gap is the wording effect. The technique that tells you whether your metric is a fact about customers or about your questionnaire.
The AI Interviewer House Effect: When One Interviewer Turns Variance Into Bias
An AI interviewer removes interviewer variance and converts what remains into bias. How to measure your house effect with an interviewer A/B.
Measurement System Analysis: How Much of Your Segment Difference Is the Instrument? (2026)
How to separate real variation between customers from variation created by measuring them. The intraclass correlation, the four classes of monitor, probable error, and how to run an honest R&R study on a research metric.
Nothing Was Measured Twice: Why the Only Error Bar You Can Compute Is the Smallest One
Your margin of error covers sampling and nothing else, because sampling is the only step of a typical study that gets repeated. The Type A and Type B distinction, the definitional floor, and the cheapest ways to buy back replication.
Customer Insights: The Complete Guide to Definition, Types, Examples, and How to Generate Them
Learn what customer insights actually are, how they differ from data and observations, the seven main types with examples, and a modern AI-powered framework for generating insights that drive growth.
Opportunity Solution Tree: The Complete Guide to Continuous Product Discovery
Learn how to build and use the Opportunity Solution Tree (OST) framework — Teresa Torres' visual map for connecting business outcomes to validated customer solutions through continuous discovery. Includes step-by-step instructions, templates, and how Koji automates the evidence-collection process.
Quantitative User Research: Methods, Examples, and When to Use Them
A complete pillar guide to quantitative user research — the 9 core methods (surveys, A/B testing, analytics, tree testing, SUS, and more), when to use each, sample size rules, and how AI is bridging quant and qual.
Guerrilla User Research: The Complete Guide to Fast, Low-Cost Feedback
Learn how to run guerrilla user research — the informal, rapid method for collecting user feedback in coffee shops, online communities, and in-app intercepts. Includes step-by-step instructions, 5-user rule explained, and how AI-moderated interviews make guerrilla research faster and more precise.
Behavioral Segmentation: Definition, 8 Types, Examples, and How to Build Segments
A complete guide to behavioral segmentation — what it is, how it differs from demographic segmentation, the 8 main types with examples, the data and research methods that power it, and how AI-native interviews unlock the 'why' behind every segment.
How to Get Customer Feedback: 10 Methods That Actually Work
A complete guide to collecting high-quality customer feedback. Covers the 10 best methods — from interviews and NPS to in-app microsurveys and review mining — with response rate benchmarks, timing guidance, and a practical feedback cadence.
Intercept Research: How to Capture Feedback at the Moment of Truth
A practical guide to intercept research — surveys and prompts that capture feedback during or immediately after user interactions. Covers exit-intent, in-app microsurveys, post-action triggers, and the timing rules that determine whether users respond or dismiss.
Design Sprint: The 5-Day Guide to Validating Ideas Before You Build
A complete guide to the design sprint — the five-day process from Google Ventures for designing, prototyping, and testing an idea with real customers before you build. Covers each day, Design Sprint 2.0, when to use it, and how to scale Friday testing with AI.
UX Audit: A Step-by-Step Guide to Finding What Is Hurting Your Product
A practical guide to running a UX audit — the structured evaluation that finds the usability problems quietly costing you conversions and retention. Covers heuristic evaluation, behavioral data, severity rating, the audit process, and how to add real user voice with AI.
Observational Research: How to Learn From What Users Do, Not What They Say
A complete guide to observational research — the family of methods that studies users by watching real behavior instead of asking. Covers the say-do gap, the main observational methods, how to run a study, and how to pair observation with AI interviews to capture the why.
Primary Research: The Complete Guide to Collecting Your Own Customer Data
A complete guide to primary research — what it is, the main methods (interviews, surveys, observation, experiments), how it differs from secondary research, a 6-step process to run a study, common pitfalls, and how AI-moderated platforms like Koji collect primary data in days instead of weeks.
Research Design: Types, Examples, and How to Choose the Right One
A practical guide to research design — the three classic types (exploratory, descriptive, causal), the qualitative vs quantitative and fixed vs flexible dimensions, a decision framework for choosing the right design, validity considerations, and how Koji helps you execute any design faster.
How to Write Unbiased Survey Questions: Avoiding Leading, Loaded & Double-Barreled Questions
A practical guide to question wording — the biggest hidden source of bad data. Learn to spot and fix leading, loaded, double-barreled, and assumptive questions, with real research examples and a pre-launch checklist.
AI vs Human Moderators in User Research: The 2026 Decision Framework
When to use AI-moderated interviews, when to use human moderators, and how to combine both. A practical decision framework backed by NN/g, Maze, and field cost data.
Monadic vs Sequential Monadic Testing: The Complete Concept Testing Guide
A practical guide to monadic and sequential monadic testing — the two core concept-testing designs. Learn how each works, the sample-size trade-off, when to use which, and how to run clean concept tests faster with AI.
Survey vs Questionnaire: What's the Difference (and Why It Matters)
Survey and questionnaire are not synonyms. A questionnaire is the instrument — the set of questions. A survey is the whole process of collecting and analyzing data. This guide clears up the confusion and shows the modern, conversational alternative to both.
Probability vs Non-Probability Sampling: Methods, Examples & When to Use Each
A clear guide to probability and non-probability sampling — the two families of sampling methods. Learn the types (random, stratified, convenience, purposive, quota, snowball), the trade-off between generalizability and speed, and how to recruit the right participants.
Survey vs Poll: What's the Difference and When to Use Each (2026)
A poll is a single quick question; a survey is a structured set of questions. Learn the real differences, when to use each, their limits, and why AI interviews now offer a deeper third option.
Emoji and Star Rating Scales: When Visual Ratings Beat Numbers (2026)
A practical guide to emoji, smiley, and star rating scales — when visual ratings outperform numeric scales, how to design them, and how to capture the reasoning behind every rating.
Positioning Research: How to Validate Your Product Positioning with Customer Interviews
A practitioner's guide to validating product positioning with customer research. Covers April Dunford's 5-component framework, 23 interview questions by component, the 8 most damaging positioning research mistakes, and a 3-week AI-moderated research sprint. Includes data from CB Insights, HBR, Gartner, Forrester, and First Round Review.
Audience Research: The Complete Guide for Marketing & Product Teams
A practitioner's guide to audience research in 2026. Learn the four research types — demographic, psychographic, behavioral, and attitudinal — plus a six-step methodology and how AI-native platforms like Koji turn weeks of audience work into hours.
Trauma-Informed User Research: How to Interview on Sensitive Topics Safely and Ethically
A practical guide to trauma-informed UX research grounded in SAMHSA's six principles. Covers screener design, dynamic consent, person-first language, in-session grounding, debrief and resource handoff, and researcher self-care — plus how AI-moderated interviewing operationalizes safety at scale.
How to Write a Research Hypothesis: A Step-by-Step Guide for Product & UX Teams
Master the art of writing testable research hypotheses. Learn the if-then-because format, null vs alternative hypotheses, common pitfalls, and how AI-native research turns hypotheses into validated learnings in days, not months.