{"site":{"name":"Koji","description":"AI-native customer research platform that helps teams conduct, analyze, and synthesize customer interviews at scale.","url":"https://www.koji.so","contentTypes":["blog","documentation"],"lastUpdated":"2026-06-10T00:51:36.297Z"},"content":[{"type":"documentation","id":"cc8fbf8e-e2e5-4acf-a6ea-e8e089c699ee","slug":"mcp-workflow-product-managers","title":"MCP Workflow Guide for Product Managers","url":"https://www.koji.so/docs/mcp-workflow-product-managers","summary":"End-to-end workflow guide for product managers using Koji MCP with Claude. Covers the complete research cycle including structured question configuration (NPS scales, feature ranking, choice segmentation), quantitative analysis with per-question aggregations, brief refinement, publishing, respondent import, interview monitoring, report generation, and data export — all from a single Claude conversation.","content":"## The Product Manager Research Workflow\n\nProduct 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.\n\nThis guide walks through a real-world scenario: **validating whether enterprise users need SSO before you build it**.\n\n---\n\n## Step 1: Define Your Research Question\n\nStart a new Claude conversation and describe your research goal:\n\n> \"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.\"\n\nClaude will use `koji_create_study` with the **Customer Discovery** methodology to create a study with:\n- A focused problem statement about SSO as a deal-blocker\n- Key interview questions that avoid leading the witness\n- Guardrails based on methodology best practices (e.g., asking about past behavior, not hypotheticals)\n- An interview plan with probe points for deeper exploration\n\n**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.\n\n---\n\n## Step 2: Add Structured Questions for Quantitative Data\n\nThis is where MCP gets powerful for PMs. You can mix qualitative depth with quantitative metrics:\n\n> \"Add these structured questions to my study: an NPS question on a 0-10 scale with anchor probing, a single-choice question asking how they currently handle SSO (options: shared passwords, password manager, manual provisioning, existing SSO, other), and a ranking question asking them to prioritize security, ease of onboarding, compliance, and cost.\"\n\nClaude uses `koji_update_brief` to add structured questions with:\n- **Scale questions** — NPS or satisfaction ratings with configurable ranges and labeled endpoints\n- **Choice questions** — Segment respondents by their current behavior or preferences\n- **Ranking questions** — Understand relative priority of features or pain points\n- **Anchor probing** — After a rating, the AI asks \"You said X — what would need to change for that to be higher?\"\n\nThese questions appear as interactive widgets during the interview while the AI interviewer still conducts a natural conversation around them.\n\n---\n\n## Step 3: Review and Refine the Brief\n\nAfter creation, ask Claude to show you the full brief:\n\n> \"Show me the research brief, interview plan, and all structured questions\"\n\nReview the questions. You might refine them:\n\n> \"The questions look good but add one about what they are currently doing instead of SSO — like password managers or shared credentials. Also increase the probing depth to 2 follow-ups for the NPS question.\"\n\nClaude will update the study with your refinements using `koji_update_brief`.\n\n---\n\n## Step 4: Publish and Distribute\n\nWhen you are happy with the brief:\n\n> \"Publish the study and configure it with voice enabled as default, set the URL slug to 'sso-enterprise-research', and set the headline to 'Help Us Build Better Enterprise Security'\"\n\nClaude publishes the study with `koji_publish_study` and configures branding with `koji_configure_study` — all in one conversation turn.\n\nFor targeted outreach:\n\n> \"Import these contacts for the study: Sarah Chen (VP Engineering, Acme Corp), James Park (CTO, Betaworks), Maria Rodriguez (IT Director, CloudFirst)\"\n\nEach person gets a personalized interview link you can include in email outreach.\n\n---\n\n## Step 5: Monitor Progress\n\nCheck in on interview completion:\n\n> \"How are my SSO interviews going? Show me the completed ones.\"\n\nClaude shows you interview summaries with sentiment and themes — no need to read every transcript. For deeper exploration:\n\n> \"The interview with Sarah Chen sounds interesting. Show me her full transcript and structured answers.\"\n\nClaude shows the transcript along with her NPS score, choice selections, and ranking — all with qualitative context from the conversation.\n\n---\n\n## Step 6: Analyze Patterns with Quantitative Data\n\nOnce you have 5 or more completed interviews, ask for structured analysis:\n\n> \"Get the study data and tell me what patterns you see. What is the average NPS score? How do respondents rank the security priorities? Is SSO actually blocking deals?\"\n\nClaude pulls the aggregated data — per-question statistics, themes, sentiment distribution — and synthesizes findings across all interviews. For structured questions, you get:\n- **NPS averages and distributions** — \"Average NPS is 6.2, with 40% detractors\"\n- **Choice frequency counts** — \"8 of 12 respondents use shared passwords as their current workaround\"\n- **Ranking positions** — \"Compliance ranked #1 on average, followed by ease of onboarding\"\n- **Cross-referencing** — \"Respondents who gave NPS below 5 all ranked compliance as their top priority\"\n\n---\n\n## Step 7: Generate the Report\n\n> \"Generate a research report and publish it so I can share with stakeholders\"\n\nClaude generates a comprehensive report with:\n- Executive summary\n- Key takeaways ranked by importance\n- Theme analysis with supporting quotes\n- Charts showing NPS distribution, choice breakdowns, and ranking results\n- Recommendations tied to evidence\n- Sentiment breakdown\n\nThen publishes it with a shareable link you can drop into Slack, email, or your product brief.\n\n---\n\n## Step 8: Export for Deeper Analysis\n\nIf you need to bring data into another tool:\n\n> \"Export the full study data including transcripts and respondent info\"\n\nYou get structured JSON you can import into Notion, Airtable, or your product analytics stack.\n\n---\n\n## The Full Conversation Flow\n\nHere is how the entire workflow looks in a single Claude conversation:\n\n```\nYou: Create a customer discovery study about whether SSO is blocking enterprise deals\nYou: Add an NPS question (0-10), a choice question about current auth methods, and a ranking of security priorities\nYou: Review the brief and adjust probing depth\nYou: Publish it with voice enabled, custom URL, and branded headline\nYou: Import my list of 15 enterprise contacts\n[Wait for interviews to complete]\nYou: Show me the NPS average and feature ranking results\nYou: Generate a report and publish it for the team\nYou: Export everything to JSON for our product brief\n```\n\nEight messages. One conversation. A complete research cycle with both qualitative and quantitative data.\n\n---\n\n## PM-Specific Tips\n\n### Using Structured Questions for Feature Prioritization\n\nCreate a study specifically for feature prioritization:\n\n> \"Create a study with a ranking question asking users to prioritize these features: SSO, audit logs, role-based access, API access, and custom integrations. Add a scale question for each asking how critical it is (1-5). Use the discovery methodology.\"\n\nThis gives you both relative rankings and absolute importance scores — perfect for roadmap decisions.\n\n### Choosing the Right Methodology\n\n| Research Goal | Methodology | Why |\n|---------------|-------------|-----|\n| Validate a feature idea | Mom Test | Prevents confirmation bias by focusing on past behavior |\n| Understand user motivations | JTBD | Reveals the \"job\" users hire your product to do |\n| Explore a new market | Discovery | Open-ended exploration before narrowing scope |\n| Gather general feedback | Exploratory | Broad themes without a specific hypothesis |\n| Qualify leads through research | Lead Magnet | Combines research value with sales engagement |\n\n### Handling Stakeholder Questions\n\nWhen your VP asks \"do users actually want this?\", you can respond in real-time:\n\n> \"What is the average NPS score and top themes from my onboarding study?\"\n\nNo scrambling for slides. Claude gives you data-backed answers instantly with both quantitative metrics and qualitative context.\n\n### Weekly Research Cadence\n\nSet up a recurring workflow:\n1. **Monday**: Check interview progress across active studies\n2. **Wednesday**: Review new completed interviews and structured question results\n3. **Friday**: Generate updated reports if you have new interviews\n\n---\n\n## Next Steps\n\n- **[Tool Reference](/docs/mcp-tool-reference)** — Deep dive into each tool\n- **[Structured Questions Guide](/docs/structured-questions-guide)** — Configure question types, scales, and probing\n- **[Best Practices](/docs/mcp-best-practices)** — Tips for better research through MCP\n- **[MCP Overview](/docs/mcp-overview)** — Full integration overview\n\n## Further reading on the blog\n\n- [B2B Customer Research: The Complete Guide for Product Teams (2026)](/blog/b2b-customer-research-guide-2026) — B2B customer research is harder than B2C — you are navigating buying groups of 10+ stakeholders, gatekeepers, and enterprise procurement cyc\n- [Best Product Discovery Tools in 2026: The Complete Buyer's Guide](/blog/best-product-discovery-tools-2026) — Product discovery is no longer a one-off pre-launch phase — it is a continuous loop. The best teams in 2026 are running weekly customer inte\n- [Concept Testing: The Complete Guide for Product Teams (2026)](/blog/concept-testing-guide-2026) — Concept testing validates whether your idea is worth building before you build it. This guide covers methods, question templates, analysis a\n\n<!-- further-reading:blog -->\n","category":"Claude & MCP Integration","lastModified":"2026-05-15T03:23:48.575624+00:00","metaTitle":"MCP Workflow Guide for Product Managers — Automate Research with Claude | Koji","metaDescription":"End-to-end guide for product managers automating customer discovery with Koji MCP and Claude. Create studies, validate hypotheses, analyze interviews, and generate stakeholder-ready reports in one conversation.","keywords":["product manager research workflow","PM AI research tools","automate customer discovery","validate feature ideas AI","stakeholder research reports","Claude AI product management","MCP workflow guide","AI interview automation PM","product discovery AI","customer validation AI tool"],"aiSummary":"End-to-end workflow guide for product managers using Koji MCP with Claude. Covers the complete research cycle including structured question configuration (NPS scales, feature ranking, choice segmentation), quantitative analysis with per-question aggregations, brief refinement, publishing, respondent import, interview monitoring, report generation, and data export — all from a single Claude conversation.","aiPrerequisites":["Koji MCP connected to Claude","Basic understanding of research methodologies"],"aiLearningOutcomes":["Run a complete PM research workflow via Claude","Choose the right methodology for your research goal","Import contacts and distribute personalized interview links","Generate and share stakeholder-ready reports","Set up a recurring research cadence"],"aiDifficulty":"intermediate","aiEstimatedTime":"12 minutes"}],"pagination":{"total":1,"returned":1,"offset":0}}