Bulk panel tagging

Applies the same attribute across your panel so one filter returns everyone it should.

Workflow 11 of 12Research opsSeptember 30, 2026

Get the workflow

Enter your details and the prompt appears here, ready to copy.

How do I update an attribute across my whole research panel?

Ask an AI tool connected to Great Question to find the candidates that match your criteria and are missing the attribute, and to show you the list first. Once you confirm, it sets that one attribute to the value you give and nothing else, then reports how many it changed and any it couldn't. Watch it the first time you run it.

Who runs it
Research ops, during a panel clean-up.
Where you sign off · You approve first
Yes, on the list, before anything is written. “Show me the list first” is doing real work in that prompt. Keep it.
Schedule it · By hand
No. Run it as a clean-up, and watch it the first time.

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. 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. 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.

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
  • update_candidate

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 show the list before it writes?

Because a filter that's slightly off changes the wrong people, and you only find out when a later study recruits from them. Reading the list is the cheapest check there is.

Can I undo a bulk update?

Keep the list of changed candidates from the report, and the same workflow can set the field back. There's no single undo button, which is another reason to confirm first.

How often should I clean up panel attributes?

Whenever a filter stops returning who you expect, and before any big recruitment push. The panel hygiene auditor skill finds what needs fixing first.

Related reading