CRM to panel matching
Checks in bulk whether the people in your CRM are already research participants, so you stop inviting the same person through two doors.
Get the workflow
Enter your details and the prompt appears here, ready to copy.
How do I check which customers are already in my research panel?
Paste a list of email addresses from your CRM into an AI tool connected to Great Question and ask it to check each one against your candidates. It returns three lists: in the panel and recently studied, in the panel but not recently, and not in the panel at all. It stays read only, so adding new people remains a separate decision you make.
- Who runs it
- Research ops, or whoever is about to send a recruitment list to sales for approval.
- Where you sign off · Read only
- Nothing. Read only, deliberately. Adding people is a separate decision and it belongs to you.
- Schedule it · By hand
- No.
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
Connect the other end
This workflow also needs your CRM, optionally (otherwise paste the list) connected in Claude, through that tool's own connector.
- 3
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
Connect the other end
This workflow also needs your CRM, optionally (otherwise paste the list) connected in ChatGPT, through that tool's own connector.
- 3
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
Connect the other end
This workflow also needs your CRM, optionally (otherwise paste the list) connected in Cursor, through that tool's own connector.
- 3
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
Connect the other end
This workflow also needs your CRM, optionally (otherwise paste the list) connected in Copilot, through that tool's own connector.
- 3
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.
- search_candidates
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
Why match a CRM list before recruiting?
So you don't invite the same person through two doors, once from sales and once from research, and so you can see who was studied last month before you ask them again.
Does it add missing people to the panel?
No, deliberately. Adding people is a consent and governance decision. Once you've reviewed the not-in-panel list, add them yourself.
Can it read the CRM directly?
If your AI tool has a connector for your CRM, yes. Otherwise paste the export. The panel side lives in Great Question's research CRM.
Related reading
- Research CRM
Where your panel and its study history live.
- What is a user research CRM?
Why research keeps its own record of customers alongside sales.
More workflows
See all 12- 11
Bulk panel tagging
Applies the same attribute across your panel so one filter returns everyone it should.
You approve first - 12
Study email localisation
Translates your study email templates for a second region without rewriting each one by hand, and replaces nothing until you approve.
You approve first - 01
The daily interview digest
Finds every session that completed today across your active studies and posts a short summary where the team already looks.
Read onlySchedule daily
