Amplitude + Koji: Closing the Loop Between Quant and Qual

Answer first: Amplitude tells you what happened in your product. Koji's AI-moderated interviews tell you why. The native integration pattern between the two is bidirectional: (1) export an Amplitude behavioral cohort and trigger a Koji interview link to every user in it, and (2) pipe each completed Koji interview's themes, sentiment, and quality score back into Amplitude as a custom event (koji.interview_completed) and user properties. End-to-end this takes about 30 minutes to wire up via webhooks + the Amplitude HTTP API, or under an hour with no code via Zapier. With tools like Koji, the gap between "users dropped off at step 4" and "here are the seven sentences they said about it" closes in the same dashboard.

If you've ever wanted to click on an Amplitude funnel drop-off and read the actual transcripts of users who fell out, this is that integration.

Why combine Amplitude and Koji

Amplitude is excellent at quantitative behavior. It cannot tell you why a user did what they did — only what they did. Most product teams patch that gap by:

• Running quarterly NPS surveys (low resolution, low candor).
• DMing power users on LinkedIn (low scale, biased sample).
• Booking five user interviews per quarter (too slow to keep up with sprint cadence).

Koji solves the scale problem — AI-moderated interviews mean you can run dozens per week without scheduling — but the bigger unlock is targeting. You don't want to interview "users." You want to interview "users who completed onboarding, used the app for three sessions, then never came back" — a behavioral cohort Amplitude already knows how to define.

With the integration, that cohort becomes an interview audience automatically.

What flows in each direction

Amplitude → Koji (trigger interviews from behavior)

• A user enters an Amplitude cohort (defined by any combination of events and properties).
• A scheduled cohort export or a real-time webhook fires their email to your forwarder.
• The forwarder calls Koji's headless API to start an interview for that respondent (starting interviews via API).
• Koji sends the personalized interview link to the user via your email tool (or via Koji's built-in delivery).

Koji → Amplitude (pipe insights back as events + user properties)

When each Koji interview reaches analysis_ready, the webhook payload includes themes, sentiment, quality score, and a transcript URL. Your forwarder PATCHes Amplitude:

• As a custom event — koji.interview_completed with properties: theme_top_1, theme_top_2, sentiment, quality_score, transcript_url.
• As user properties — last_interview_at, last_interview_sentiment, last_interview_themes, last_interview_quality.

Once that's in place, you can build Amplitude charts that segment any metric by interview theme — e.g., "Day-30 retention for users whose last interview surfaced 'pricing confusion' is 14 points lower than the cohort average." This is the kind of join survey tools cannot enable because surveys don't produce themes natively.

Step 1 — Decide the cohorts you'll interview

The most productive Amplitude → Koji pairings are behavioral cohorts where the why is most valuable:

• Onboarding drop-off — Users who hit step N then went silent for 7 days.
• Aha-moment skippers — Users who never reached the activation event.
• Power-user expansion candidates — Users who hit the top decile of usage but stayed on the free tier.
• Reactivated churners — Users who churned and came back; what changed?
• Feature-adoption laggards — Users who used a feature once and never again.

Define each one in Amplitude as a saved cohort. The feature adoption research and customer retention research docs cover the methodology side.

Step 2 — Trigger Koji interviews from Amplitude

There are three integration paths, in order of operational maturity:

Path A: Zapier or Make (no code, ~30 min)

1. Trigger: Amplitude cohort entry (via Amplitude Cohort Sync to a destination tool, or via a scheduled cohort export to webhook).
2. Action: Koji → Start Interview, passing the respondent's email.
3. Action (optional): Email tool → Send personalized interview link.

Path B: Amplitude Cohort Sync + Koji headless API (~1 hour)

If you're on Amplitude Audiences (or any cohort sync feature), pipe the cohort to a webhook destination. A small serverless function receives the cohort payload, iterates the user list, and calls Koji's start interview API for each respondent. Koji handles deduplication via stable respondent_email — re-running the same cohort doesn't double-interview anyone.

Path C: Reverse ETL (Hightouch, Census) (production-grade)

For a high-volume program, use a reverse-ETL tool to mirror an Amplitude cohort into Koji on a schedule. This is the cleanest pattern for orgs that already run reverse ETL for other destinations.

For any path, the user research API guide, API authentication doc, and managing API keys doc cover the credential basics.

Step 3 — Pipe Koji results back into Amplitude

Subscribe to Koji's interview.analysis_ready event (full reference in webhook setup). Your forwarder:

1. Verifies the Koji HMAC signature.
2. Posts to Amplitude HTTP API v2 with two payloads:
   • An event: event_type = "koji.interview_completed" plus event properties.
   • An identify call: setting last_interview_sentiment, last_interview_themes, last_interview_quality, and last_interview_at as user properties.
3. Handles anonymous interviews — when respondent_email is null, skip the Amplitude write (there's no user_id to attach to).

The write completes in <100ms p95 and shows up in Amplitude within ~2 minutes (subject to Amplitude's standard ingestion latency).

What you can build in Amplitude once the data lands

• Funnel × theme segmentation — Take an onboarding funnel and segment by last_interview_themes. The drop-off step where the "pricing confusion" theme is 3x represented is the actual problem.
• Retention curves by sentiment — Are users whose last Koji interview was negative more likely to churn? You no longer have to guess.
• Cohort triggers from sentiment — Build a workflow where any user whose last_interview_sentiment = negative enters a save-the-account cohort that triggers CSM outreach.
• A/B test annotation — When you ship a change, drop a Koji interview link to the control + treatment cohorts and pipe the qualitative read back into Amplitude alongside the quant lift. You stop relying on instinct to explain "why did treatment win?"

Comparison: Koji + Amplitude vs survey-tool + Amplitude

Amplitude integrates with most survey tools (SurveyMonkey, Typeform, Qualtrics). Why is the Koji integration meaningfully different?

• Themes are first-class. Surveys deposit a numeric score and a raw text blob. Koji deposits themes — Amplitude can group on them directly. With surveys, you'd have to run an analysis pipeline to extract themes before you could segment on them. (Understanding themes and patterns.)
• Probing closes the "I don't know" answers. When a Typeform open-text says "it's fine," that's the end of the data. When a Koji interview gets "it's fine," the AI follows up and frequently extracts the real reason. The Amplitude property ends up populated with substance.
• Quality gating. Koji scores each conversation 1–5 and only writes back quality 3+ to keep your Amplitude properties clean. Surveys cannot filter this way — every junk response lands as a "user property" and contaminates your cohorts.

If you're evaluating the broader category, the Koji vs Amplitude comparison covers when each tool is the primary system — they're complementary, not competitive.

Plan requirements and cost

Webhooks and the headless API are on the Interviews plan (€79/month, 79 credits) and Enterprise. The Insights plan (€29/month) doesn't include webhooks — for that tier, the Zapier path works on any plan. Text interviews cost 1 credit, voice 3, and only interviews scoring 3+ on Koji's quality gate consume credits. See the plan comparison guide.

A typical "Amplitude-triggered" research program — three weekly studies of 10 respondents each — uses around 30 credits/week if running text and ~90/week if running voice, well within the Interviews plan or a small overage budget (€1/credit flat).

Anonymous mode, consent, and compliance

For regulated industries (fintech, health), see GDPR-compliant AI user research and anonymizing customer interview data. When Koji runs in anonymous mode, no email is collected and your Amplitude write should be skipped — there's no user to attach properties to. This is enforced by your forwarder, not by Koji.

Related Resources

• Structured Questions Guide — the six structured question types that power the events.
• Webhook Setup — full reference for Koji webhook events and signatures.
• Research Automation Webhooks — idempotency, retries, replay patterns.
• User Research API Guide — programmatic access to studies and interviews.
• HubSpot Research Integration — the same pattern, mapped to HubSpot CRM.
• Salesforce Research Integration — the same pattern, mapped to Salesforce.
• Zapier Research Automation — no-code path for any of these tools.
• Feature Adoption Research — the methodology side of the cohorts you'll target.