Transcript to markdown
Turns a session transcript into clean markdown you can drop into a repo, a wiki or your notes, without paraphrasing a word.
Get the workflow
Enter your details and the prompt appears here, ready to copy.
How do I convert an interview transcript to markdown?
Ask an AI tool connected to Great Question to export the session transcript as markdown: a heading with the study and date, speaker-attributed dialogue, and timestamps every few turns. Tell it to strip filler words but never paraphrase. The result drops straight into a repo, a wiki or Obsidian with the participant's exact wording intact.
- Who runs it
- Anyone who writes somewhere other than a document editor.
- Where you sign off · Read only
- Nothing. Read only.
- Schedule it · By hand
- No. Run it when you need it.
How to run it in Claude, ChatGPT, Cursor or Copilot
The prompt is the same in every tool. What changes is where you connect Great Question and where you paste it.
Run it in Claude
- 1
Connect Great Question to Claude
In Claude Desktop, open Settings → Connectors → Add custom connector. Name it Great Question, paste https://greatquestion.co/api/mcp/v1, then Save and Connect and sign in with your Great Question account. Restart Claude so the tools load.
- 2
Paste the prompt
Start a new chat and paste the prompt. Claude asks before it uses each Great Question tool; allow the read tools, and read anything it proposes to write before you allow it.
Run it in ChatGPT
- 1
Connect Great Question to ChatGPT
In the ChatGPT or Codex desktop app, go to Settings → Plugins → MCPs → Add server. Name it Great Question, choose Streamable HTTP, paste https://greatquestion.co/api/mcp/v1, save, then authenticate.
- 2
Paste the prompt
Open a new chat with the Great Question server switched on and paste the prompt. If ChatGPT answers without calling a tool, say “use the Great Question tools” and it will.
Run it in Cursor
- 1
Connect Great Question to Cursor
Open Cursor Settings (Cmd/Ctrl + Shift + J) → MCP → New MCP Server, and add a server named great-question with the url https://greatquestion.co/api/mcp/v1 to mcp.json. Save, click Connect, and sign in.
- 2
Paste the prompt
Paste the prompt into the chat in Agent mode, which is the mode that can call MCP tools. Cursor asks before it runs each tool unless you have switched on auto-run.
Run it in Copilot
- 1
Connect Great Question to Copilot
In Copilot Studio, open your agent's Tools page → Add a tool → New tool → Model Context Protocol. Server name Great Question, server URL https://greatquestion.co/api/mcp/v1, OAuth for authentication, then add it to the agent.
- 2
Paste the prompt
Paste the prompt into the agent's chat. To run it the same way every time, put the prompt in the agent's instructions instead and share the agent with your team.
Your admin has to switch the MCP on in Great Question first. The MCP guide covers every tool, the security model and a team rollout.
The tools it calls
Named so you can see exactly what the agent touches before you let it near anything.
- get_transcript
What we never automate
Four rules sit under every workflow here, and they matter more than the workflows.
Nothing reaches a participant without a person
No workflow sends an invitation, an email or a reminder. The MCP can do those things. They are left out on purpose, because a scheduled job that contacts your customers is a different category of risk from one that reads a transcript.
Nothing launches a study without a person
An agent can build the screener and draft the messages. Someone still presses go.
Nothing reaches a stakeholder unchecked
The synthesis workflows hand you quotes with links attached so you can check them in one click. Use the click. A misattributed quote in a board deck costs more than the hour it saved.
Nothing sees more than the person who connected it
Permissions follow the individual, so an agent connected by a PM reaches exactly what that PM reaches. Your admin decides whether it is available at all.
Questions
Will the AI change what participants said?
Not if you tell it not to. The prompt says to keep the exact wording and only remove filler words. Spot-check a few lines against the session the first time you run it.
Why markdown rather than a document?
Markdown works where technical teams already write: git repos, wikis, Obsidian, Notion imports. It also keeps a transcript small enough to hand to another AI tool as context later.
Can I convert a whole study at once?
Yes. Ask for every session in the study, one markdown block per session. For more than a handful, the transcript vault workflow is the better fit.
Related reading
- How to transcribe an interview
The step before this one, if your sessions aren't transcribed yet.
- Interviews in Great Question
Where sessions are recorded and transcribed before the agent exports them.
More workflows
See all 12- 04
Attach the evidence to the ticket
Pulls the transcript and the participant's company onto the matching task in your planning tool, so whoever picks up the work can read the source.
Writes outside GQ - 05
The response rate tracker
Counts how many people you invited against how many submitted a screener, for any date range, without building a report.
Read onlySchedule monthly - 06
Screener cloning
Lifts screener questions you already trust from a past study into a new one, then reads the result back before anything goes out.
You approve first
