Meeting notes to issues

Turns meeting notes into draft issues and specs so follow ups do not get lost. You review the list before anything is filed.

EngineeringWorks with Claude Desktop with MCP · Claude Code+2Community exampleAdded Oct 13, 2026, 9:38 AM EDT

Build your prompt See requirements

What it does

Reads notes from the meeting
Pulls out decisions, requests and follow ups
Drafts issues with context and an owner
Skips anything already tracked

Your approval boundaries

Approval required

These actions always wait for your yes:

Filing the issues
Assigning work to people

You decide what happens next.

More about this workflow

This setup is for developers and small engineering teams who want fewer chores. It takes a repeat chore off your plate and hands back something you can check quickly.

First, it reads notes from the meeting. Next, it pulls out decisions, requests and follow ups. Then it drafts issues with context and an owner. Finally, it skips anything already tracked. It works with your call recorder and issue tracker, each on its own login with limited access.

You get the prep work done and waiting for you. The agent stops and asks for your yes before filing the issues and assigning work to people, and says plainly if a step cannot be undone.

“turn meeting notes into project specs”

Linear @linear · Apr 25, 2026

Before you startCall recorder · Issue tracker accessScoped permissionsClaude Desktop with MCP or Claude Code

Explore required tools and model recommendations

Tools and access

Call recorder
Handles the call recorder part of this job. Grant read access to transcripts you choose.
API required: Optional. Most meeting tools can export transcripts. An API is only needed to pull them automatically.
No sign-up needed
Linear
Handles the issue tracker part of this job. Grant read plus create in one triage team.
API required: Yes. Needs a personal API key or an OAuth app.
Sign up: Linear

Official links only. Not sponsored, no affiliate links.

Model recommendations

Best pick

Claude Opus 5.5

Its maker points to it for long running coding work.

$4 per million input tokens, $20 per million output tokens.

Anthropic docs as of October 11, 2026

Cheaper backup

Claude Sonnet 5.5

Half the price per token and still strong for reviews and docs.

$2 per million input tokens, $10 per million output tokens.

Anthropic docs as of October 11, 2026

Our own picks. Not sponsored, no affiliate links.

Build your prompt

Add your details, then copy the prompt into your tool.

2Your prompt

3 of 3 still empty

Fill these in before you run it: [WHERE MEETING NOTES LIVE] [YOUR ISSUE TRACKER AND TEAM] [WHICH MEETINGS TO INCLUDE] You are the Meeting notes to issues agent. Turns meeting notes into draft issues and specs so follow ups do not get lost. You review the list before anything is filed. Use only the details filled in above. If any [BRACKETED] item is still blank or unclear, stop and ask for it first. Do not guess. What you do on your own: - Reads notes from the meeting - Pulls out decisions, requests and follow ups - Drafts issues with context and an owner - Skips anything already tracked What you must never do without a yes from a person: - Filing the issues - Assigning work to people Rules: - Before any step on the list above, stop and ask. Say in plain words what you want to do, who it affects, and whether it can be undone. - If something cannot be undone, say so first, in one short line. - Write drafts, not final actions. A person sends, pays, posts, or deletes. - Keep a short log of every action you took and every source you read. - If you are unsure, ask instead of guessing.

View run instructionsPaste into: Claude Desktop with MCP, Claude Code, Zapier Agents, n8n

Your answers stay in this browser only.

Run your workflow

Connect your tools with only the access this setup needs, then follow these steps.

Do these in order. Test on old data before it touches live work.

1Set up Call recorder. Keep it to read access to transcripts you choose.
2Connect Linear with its own login, not yours. Grant read plus create in one triage team.
3Paste the prompt where your harness takes instructions. See the note under the Copy button.
4Do a dry run on old or test data first. Check every draft and every stop point by hand before you let it near live work.
5Read its log after the first real run. Only widen access once a week of runs looks clean.

Safeguards and trust score

The score describes this example setup’s access, approval boundaries, ability to undo changes, and scope.

Access18 / 30

Can draft things that send or spend, so it sits close to risky actions.

Human approval30 / 30

Waits for a yes on: filing the issues, assigning work to people.

Undo and logs14 / 20

Proposes changes to live records, so the setup needs a change log and a way back.

Scope18 / 20

Runs on its own login across 2 tools. Fewer connections means a smaller blast radius.

How to raise it

Access: Take away its ability to send, post or spend. Let it only write drafts, and have a person press send or pay from their own account +6
Undo and logs: Stop it from editing live records. Have it write the change as a proposal you apply, and keep a log of every change with a way to roll it back +3
Scope: Run it on one tool only, with its own login that can see just what this job needs +2

Do all of these to reach 91, up from 80.

Want help getting there? Get an AI Trust Audit from Pixeldesigns

Reviewed by Trustcase (example setup). How scoring works

Embed badge

Show this trust score on your site or README. It links back here.

Markdown

[![Trustcase trust score for Meeting notes to issues](https://trustcase.dev/badge/meeting-notes-to-issues.svg)](https://trustcase.dev/use-cases/meeting-notes-to-issues)

HTML

<a href="https://trustcase.dev/use-cases/meeting-notes-to-issues"><img src="https://trustcase.dev/badge/meeting-notes-to-issues.svg" alt="Trustcase trust score for Meeting notes to issues" height="20"></a>

Broken link sweep
Checks every link on your docs or site each week and proposes fixes for the dead ones. A person confirms each fix before it goes live.
Weekly codebase review report
Once a week it reviews the whole repo, focusing on what changed since last time. It tracks each finding as new, still open or fixed, and nothing blocks on it.
Small fix pull requests
Runs on a schedule and opens one small pull request per fix, each proven by a test that failed before and passes after. Changes collect on a dev branch and you decide when they ship.
New issue intake sorter
Reads each new issue on your repo and sorts it as ready to work, needs more info, or too big. You get a clean queue and reporters get asked for missing details.