New

Now in Claude, ChatGPT, Cursor & more with our MCP server

Back to docs
Claude & MCP Integration

MCP Workflow Guide for Product Managers

End-to-end guide for product managers using Koji MCP with Claude to automate customer discovery, validate hypotheses, and generate stakeholder-ready research reports — all from a single conversation.

The Product Manager Research Workflow

Product managers spend hours context-switching between research tools, spreadsheets, and slide decks. With Koji MCP and Claude, you can run your entire research workflow in one conversation — from hypothesis to stakeholder-ready report.

This guide walks through a real-world scenario: validating whether enterprise users need SSO before you build it.


Step 1: Define Your Research Question

Start a new Claude conversation and describe your research goal:

"I am a product manager at a B2B SaaS company. We keep getting SSO requests from enterprise prospects but I am not sure if it is actually blocking deals or just a nice-to-have. Create a customer discovery study to figure this out."

Claude will use koji_create_study with the Customer Discovery methodology to create a study with:

  • A focused problem statement about SSO as a deal-blocker
  • Key interview questions that avoid leading the witness
  • Guardrails based on methodology best practices (e.g., asking about past behavior, not hypotheticals)
  • An interview plan with probe points for deeper exploration

Pro tip: Mention your methodology preference if you have one. "Use the Mom Test approach" or "I want a Jobs-to-be-Done framework" will shape the entire interview structure.


Step 2: Review and Refine the Brief

After creation, ask Claude to show you the full brief:

"Show me the research brief and interview plan"

Review the key questions. You might refine them:

"The questions look good but add one about what they are currently doing instead of SSO — like password managers or shared credentials"

Claude will update the study with your refinements.


Step 3: Publish and Distribute

When you are happy with the brief:

"Publish the study and enable voice interviews"

Claude publishes the study and returns your interview link. Then:

"Set the interview URL to 'sso-enterprise-research' and customize the headline to 'Help Us Build Better Enterprise Security'"

Now share the link with prospects and customers. For a targeted outreach:

"Import these contacts for the study: Sarah Chen (VP Engineering, Acme Corp), James Park (CTO, Betaworks), Maria Rodriguez (IT Director, CloudFirst)"

Each person gets a personalized interview link you can include in email outreach.


Step 4: Monitor Progress

Check in on interview completion:

"How are my SSO interviews going? Show me the completed ones."

Claude shows you interview summaries with sentiment and themes — no need to read every transcript. For deeper exploration:

"The interview with Sarah Chen sounds interesting. Show me her full transcript."


Step 5: Analyze Patterns

Once you have 5 or more completed interviews, ask for structured analysis:

"Get the study data and tell me what patterns you see. Is SSO actually blocking deals?"

Claude pulls the aggregated data — themes, sentiment distribution, top topics — and synthesizes findings across all interviews. It can identify:

  • Common pain points and workarounds
  • How many respondents mentioned SSO as a deal-blocker vs. nice-to-have
  • Unexpected insights you had not considered

Step 6: Generate the Report

"Generate a research report and publish it so I can share with stakeholders"

Claude generates a comprehensive report with:

  • Executive summary
  • Key takeaways ranked by importance
  • Theme analysis with supporting quotes
  • Recommendations tied to evidence
  • Sentiment breakdown

Then publishes it with a shareable link you can drop into Slack, email, or your product brief.


Step 7: Export for Deeper Analysis

If you need to bring data into another tool:

"Export the full study data including transcripts and respondent info"

You get structured JSON you can import into Notion, Airtable, or your product analytics stack.


The Full Conversation Flow

Here is how the entire workflow looks in a single Claude conversation:

You: Create a customer discovery study about whether SSO is blocking enterprise deals
You: Review the brief and add a question about current workarounds
You: Publish it with voice enabled and set a custom URL slug
You: Import my list of 15 enterprise contacts
[Wait for interviews to complete]
You: Show me the interview summaries and key themes
You: Generate a report and publish it for the team
You: Export everything to JSON for our product brief

Seven messages. One conversation. A complete research cycle that would traditionally take days of tool-switching.


PM-Specific Tips

Choosing the Right Methodology

Research GoalMethodologyWhy
Validate a feature ideaMom TestPrevents confirmation bias by focusing on past behavior
Understand user motivationsJTBDReveals the "job" users hire your product to do
Explore a new marketDiscoveryOpen-ended exploration before narrowing scope
Gather general feedbackExploratoryBroad themes without a specific hypothesis
Qualify leads through researchLead MagnetCombines research value with sales engagement

Handling Stakeholder Questions

When your VP asks "do users actually want this?", you can respond in real-time:

"Pull up the sentiment breakdown and top themes from my onboarding study"

No scrambling for slides. Claude gives you data-backed answers instantly.

Weekly Research Cadence

Set up a recurring workflow:

  1. Monday: Check interview progress across active studies
  2. Wednesday: Review new completed interviews and emerging themes
  3. Friday: Generate updated reports if you have new interviews

Next Steps

Related Articles

Continuous Discovery with Koji MCP — Always-On Research Pipeline

Build an always-on customer research pipeline using Koji MCP and Claude. Automate continuous discovery habits for product teams — from setting up recurring studies to synthesizing insights across weeks of interviews.

Choosing a Methodology

An overview of every research methodology Koji supports and when to use each one.

Koji MCP Integration Overview

Connect Koji to Claude, Cursor, and other AI assistants using the Model Context Protocol (MCP). Manage your entire research workflow conversationally — create studies, run interviews, analyze data, and generate reports without leaving your AI assistant.

MCP Tool Reference — All 17 Tools

Complete reference for all 17 Koji MCP tools. Includes parameters, return data, plan requirements, and example prompts for each tool across read, create, analyze, customize, and distribute categories.

MCP Workflow Guide for UX Researchers

How UX researchers use Koji MCP with Claude to scale qualitative research. Manage multiple studies, analyze transcripts across projects, generate themed reports, and maintain a living research repository.

MCP Workflow Guide for Founders & GTM Teams

How founders and go-to-market teams use Koji MCP with Claude to validate markets, qualify leads through research conversations, and build evidence-based positioning — all without hiring a dedicated researcher.

MCP Best Practices — Getting the Most from Koji + Claude

Tips, patterns, and anti-patterns for using Koji MCP effectively. Learn how to write better prompts, choose methodologies, manage token budgets, and build efficient research workflows with AI.