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.

Workflow 4 of 12Research opsSeptember 30, 2026

Get the workflow

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

How do I attach user research evidence to a Jira or Linear ticket?

Connect your AI tool to Great Question and to your planning tool, then ask it to fetch the session transcript and the participant's role and company, attach the transcript to the task you name, and add a two-line comment on who the participant is. Tell it not to change the status or assignee, so the only thing that moves is the evidence.

Who runs it
Whoever runs the study, usually the day after a session.
Where you sign off · Writes outside GQ
The agent writes into your planning tool. The instruction not to touch status or assignee is deliberate. Keep it.
Schedule it · By hand
No. This one is event-driven, and the judgment about which ticket is yours.

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

    Connect the other end

    This workflow also needs your planning tool (Jira, Linear or Asana) connected in Claude, through that tool's own connector.

  3. 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.

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
  • get_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 attach the transcript instead of a summary?

So whoever picks up the ticket can check the source themselves. A summary tells them what someone concluded; the transcript lets them read what the customer said.

Which planning tools does this work with?

Any your AI tool can reach through a connector, such as Jira, Linear or Asana. The Great Question side is the same in each.

Can it pick the right ticket on its own?

It can search for one, but name the task yourself. Deciding which piece of work a session is evidence for is a judgment call, which is why this workflow isn't scheduled.

Related reading

More workflows

See all 12