Time-savers

Turn meeting recordings into a to-do list

After each meeting, you get the decisions, who owes what, and open questions, ready to paste into your task list or chat.

Last updated October 16, 2026.

Costs here use the prices AI companies charge software developers, so they show relative cost, not your monthly bill. See what ChatGPT, Claude and Gemini charge you.

Starter recipe, not yet tested end to end.

What it does for you

Reads the transcript of a meeting and lists the decisions made, the action items with owners and dates (only when they were actually said), and the questions still open.

Time saved

Replaces re-listening or rewriting notes by hand. We have not measured the time saved yet, and the first few results should be spot-checked for wrong names.

What it costs to run

Model to start with	Cost for 100 meetings
Claude Sonnet 5.5	$3.20
GPT-6.1 Sol	$3.20

Transcripts are long and getting names right matters, so a mid-priced model is worth it. Estimate assumes about 12,000 tokens in and 800 tokens out per item (a token is about three-quarters of a word), at list prices. Real usage will differ.

How to build it

You will need: A meeting-notes app such as Granola or Fireflies; Zapier or Make (automation apps); Slack, Notion or your task app

Start the automation when a transcript is ready.
Send the transcript to the AI model with the instructions below.
Post the summary to your chat or task app.
Check the first 10 results for wrong names or dates.

Instructions to give the AI

From this meeting transcript, list: 1) decisions made, 2) action items as 'who - what - due date (or none)', 3) open questions. Only include names and dates that appear in the transcript. Transcript:
{{transcript}}