Meetings that write their own follow-ups
Every meeting ends with a summary, decisions, and a drafted follow-up email waiting for your review.
The problem
After every call you lose 20 minutes writing notes and the follow-up email, or worse, you skip it and drop threads.
What you get
A working system with the steps, tools, checkpoints, and expected return made explicit.
- Setup
- 45 minutes
- Back each week
- 3 hours
- Difficulty
- assisted
Expected return
The working case
A planning estimate, not a guaranteed result. Measure the first four weeks against your own baseline.
144
hours returned per year
At 3 hours/week across 48 working weeks.
1
week to earn back setup
Compare the setup estimate with the weekly time returned.
Operating contract
Input
The source material, constraints, and examples a human would need to do this work well.
Checkpoint
A person reviews judgment calls, sensitive content, unfamiliar tools, and irreversible actions.
Success signal
Track time returned, corrections required, and exceptions. Keep it only if the measured result compounds.
Before you start
- ·Your meetings happen on a platform the notetaker supports
The steps
- 01
Turn on an AI notetaker for your calls (Granola for in-person-feel notes, or your meeting app’s built-in one).
- 02
After each call, run the transcript through a fixed prompt you keep saved.
Copy this prompt
From this meeting transcript, produce: 1) five-bullet summary, 2) decisions made, 3) action items as "who / what / by when", 4) a short follow-up email to the other attendees confirming the actions. Transcript: [paste]
- 03
Paste the follow-up into email, adjust names and nuance, send within ten minutes of the call while context is fresh.
What it runs on
Where this goes wrong
- Notetakers mishear names, numbers, and dates; check those in the summary before you send anything on.
- Do not send AI summaries of sensitive conversations (HR, health, conflict) to a group without a careful read.
Definition of done
Run it for four weeks. Then make it earn its place.
- □ Baseline the manual time before launch.
- □ Keep a human approval step for consequential output.
- □ Record corrections and exceptions, not just successes.
- □ Expand, revise, or retire it after the first review.
Build the system around it
Related workflows
If this one stops working, tell us. Three reports in a month and it leaves the library until a person has looked at it again.