{"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":"2026-06-03T08:19:49.613Z"},"content":[{"type":"documentation","id":"ec5f1af9-a404-4d54-ba4e-7b109c048471","slug":"figma-research-integration","title":"How to Connect Koji User Research to Figma & FigJam","url":"https://www.koji.so/docs/figma-research-integration","summary":"Koji insights can flow into Figma and FigJam four ways: export the auto-generated report and paste themes/quotes onto a FigJam affinity board; pull data via Koji''s REST API; use Claude through Koji''s MCP server to generate FigJam-ready sticky text and problem statements; or automate with Zapier/n8n on study-completed triggers. Because Koji auto-codes open-ended answers into themes during analysis, you import organized insight, not raw transcript. Koji''s six structured question types (open_ended, scale, single_choice, multiple_choice, ranking, yes_no) give designs quantitative backbone — rankings inform layout priority, scales set baselines — while themed quotes supply empathy you pin beside mockups. The recommended loop: define the design question, interview in Koji, auto-analyze, bring themes to FigJam, affinity map, design in Figma with each decision tied to a real quote, then re-interview to validate.","content":"## The Short Answer\n\nKoji does not lock your research in a separate silo. You can bring AI interview insights — **themes, verbatim quotes, and structured-question results** — into **Figma and FigJam** four ways: **export** the report and drop quotes onto a FigJam board, pull data through the **REST API**, generate design-ready artifacts with **Claude via Koji's MCP server**, or wire an automation with **Zapier/n8n**. The result is a design surface where every screen is backed by a real customer quote instead of a guess.\n\nThe fastest path for most teams: run the study in Koji, let it auto-generate the [research report](/docs/generating-research-reports), then export themes and quotes into a FigJam affinity board your whole team can design against.\n\n---\n\n## Why Connect Research to Figma at All\n\nDesign decisions made without evidence are expensive to unwind. When the insight lives in a separate research tool, designers rarely open it — so it never shapes the work. Pulling Koji's output into the canvas where design actually happens closes that gap:\n\n- **Quote-backed designs** — pin a real customer sentence next to the screen it justifies\n- **Affinity mapping in FigJam** — cluster Koji's auto-extracted [themes](/docs/understanding-themes-patterns) into opportunity areas\n- **Evidence in design reviews** — stakeholders see the *why* beside the *what*\n- **Faster discovery-to-design handoff** — no re-typing findings from a PDF\n\n---\n\n## Method 1 — Export → FigJam (no setup)\n\nThe simplest workflow, and the one most teams start with:\n\n1. Run your study in Koji and open the auto-generated report\n2. **Export** the report and structured-question data ([export options](/docs/exporting-research-data))\n3. In FigJam, create sticky notes from Koji's coded themes and verbatim quotes\n4. Group stickies into clusters — this is classic [affinity mapping](/docs/affinity-mapping), now grounded in real interviews\n\nBecause Koji already codes open-ended answers into themes during analysis, you are pasting *organized* insight, not raw transcript. A study that produced 40 interviews lands as a tidy set of theme clusters with supporting quotes — minutes of work instead of hours of manual tagging.\n\n---\n\n## Method 2 — REST API (live data)\n\nIf you want a repeatable pipeline, Koji's [REST API](/docs/api-authentication) exposes study data, transcripts, and report content programmatically. A small script can:\n\n- Fetch the latest report for a study\n- Pull the top themes and their supporting quotes\n- Format them as text your team imports into FigJam, or push them to a design-ops dashboard\n\nThis is ideal for teams running [continuous discovery](/docs/continuous-discovery-user-research) who want the current \"voice of the customer\" always reflected in their design system documentation.\n\n---\n\n## Method 3 — Claude MCP (AI-assisted)\n\nKoji ships a [Model Context Protocol (MCP) server](/docs/mcp-overview) so AI clients like Claude can read your studies directly. With MCP connected, you can ask Claude to:\n\n- \"Summarize the top 5 themes from my onboarding study as FigJam-ready sticky text\"\n- \"List the three strongest quotes about pricing confusion\"\n- \"Draft a problem statement for the checkout redesign based on this study\"\n\nClaude reads the live Koji data through MCP tools and hands you structured text you paste straight onto the canvas. It is the closest thing to a research analyst sitting next to your designer.\n\n---\n\n## Method 4 — Zapier / n8n (automation)\n\nFor hands-off workflows, connect Koji to [Zapier](/docs/zapier-research-automation) or [n8n](/docs/n8n-research-automation). Trigger on \"study completed\" or \"report generated,\" then route the output wherever your design team works — a Slack channel, a Notion research database your FigJam links to, or a Google Doc the team pulls from. You set it once and new insights flow automatically.\n\n---\n\n## Pairing Structured Questions with Design Decisions\n\nKoji's six [structured question types](/docs/structured-questions-guide) — open_ended, scale, single_choice, multiple_choice, ranking, and yes_no — give your Figma work quantitative backbone, not just quotes:\n\n- A **ranking** question (\"order these features by importance\") tells you what to put first in the layout\n- A **scale** question (satisfaction or NPS) gives you a baseline to redesign against\n- A **single_choice** question (\"which entry point did you expect?\") settles navigation debates with data\n- **open_ended** answers, auto-themed, supply the verbatim quotes you pin beside mockups\n\nSo a single Koji study feeds both the *direction* (structured results) and the *empathy* (quotes) of your design — no separate survey tool required.\n\n---\n\n## A Practical Discovery-to-Design Loop\n\n1. **Define** the design question (e.g., \"why do users drop at step 3?\")\n2. **Interview** in Koji — voice or text, with AI follow-up probing\n3. **Auto-analyze** — Koji codes themes and aggregates structured answers\n4. **Bring to FigJam** — export or MCP the themes and quotes onto a board\n5. **Affinity map** — cluster into opportunities\n6. **Design** in Figma with each decision tied to a quote\n7. **Validate** the new design, then **re-interview** to confirm it worked\n\nThis keeps the canvas honest: every pixel traces back to something a real customer said.\n\n---\n\n## Tips for a Clean Workflow\n\n- Keep one FigJam board per study so evidence stays traceable\n- Color-code stickies by theme to make clusters obvious\n- Always carry the **verbatim quote** next to your paraphrase — it is what convinces stakeholders\n- For recurring research, use the API or Zapier route so the board updates itself\n\n---\n\n## Related Resources\n\n- [Structured Questions Guide](/docs/structured-questions-guide) — the 6 question types that give your designs quantitative backbone\n- [Generating Research Reports](/docs/generating-research-reports) — the report you export into FigJam\n- [Affinity Mapping](/docs/affinity-mapping) — cluster Koji themes into opportunity areas\n- [Understanding Themes & Patterns](/docs/understanding-themes-patterns) — how Koji codes open-ended answers\n- [MCP Overview](/docs/mcp-overview) — connect Claude to your Koji studies\n- [User Interview Guide](/docs/user-interview-guide) — run the interviews that feed your design","category":"Research Operations","lastModified":"2026-06-03T03:18:57.097564+00:00","metaTitle":"Connect Koji User Research to Figma & FigJam (2026 Guide)","metaDescription":"Bring Koji AI interview insights into Figma and FigJam — themes, verbatim quotes, and structured-question charts. Four workflows: export, REST API, Claude MCP, and Zapier/n8n. Design with evidence, not guesses.","keywords":["figma research integration","figjam user research","koji figma","user research in figma","design research workflow","affinity mapping figjam","research to design handoff"],"aiSummary":"Koji insights can flow into Figma and FigJam four ways: export the auto-generated report and paste themes/quotes onto a FigJam affinity board; pull data via Koji''s REST API; use Claude through Koji''s MCP server to generate FigJam-ready sticky text and problem statements; or automate with Zapier/n8n on study-completed triggers. Because Koji auto-codes open-ended answers into themes during analysis, you import organized insight, not raw transcript. Koji''s six structured question types (open_ended, scale, single_choice, multiple_choice, ranking, yes_no) give designs quantitative backbone — rankings inform layout priority, scales set baselines — while themed quotes supply empathy you pin beside mockups. The recommended loop: define the design question, interview in Koji, auto-analyze, bring themes to FigJam, affinity map, design in Figma with each decision tied to a real quote, then re-interview to validate.","aiPrerequisites":["A Koji study with completed interviews and a generated report","Basic familiarity with Figma and FigJam","Optional: API keys or a Zapier/n8n account for automated workflows"],"aiLearningOutcomes":["Move Koji insights into Figma and FigJam four different ways","Build a quote-backed affinity board in FigJam from Koji themes","Use the REST API or Claude MCP to pull live research data","Pair structured-question results with design decisions","Run a repeatable discovery-to-design loop"],"aiDifficulty":"intermediate","aiEstimatedTime":"9 minutes"}],"pagination":{"total":1,"returned":1,"offset":0}}