Skip to content
Scheduling

Scheduling

Run a 15-minute AI weekly review

ResearchedWhat this sticker meansBeginnerWork

Last updated:

Quick answer

Close each week by talking through wins, drains, and open loops with voice mode while the AI takes notes, then get a drafted plan for next week instead of a blank Monday.

At a glance

All outcome figures are estimates from cited sources, not independent verification by us.

What it is allowed to do
Drafts for you

Writes drafts (emails, posts, plans, replies). You review and send. Nothing goes out without you.

Reviewed Oct 19, 2026

Time saved (estimate)
Roughly 30–45 minutes per review
Difficulty
Beginner
Tools needed
ChatGPT, Google Calendar, Notion
Typical cost
ChatGPT: free tier includes voice mode; calendar and notes apps you already use.

Basis (estimate): Estimate only: one practitioner reports the voice-driven review taking ~15 minutes versus a manual typed pass; no timed study exists.

What does this setup do?

Close each week by talking through wins, drains, and open loops with voice mode while the AI takes notes, then get a drafted plan for next week instead of a blank Monday.

Who is it for?

Anyone whose to-do list grows until it is paralyzing, and who skips weekly reviews because sitting down to type one feels like homework.

How do you set it up?

Tools

  • ChatGPT mobile app with voice mode
  • Your calendar (Google, Apple, or Outlook)
  • A notes app to paste the summary (Notion, Google Docs, Apple Notes)

Steps

  1. Pick a fixed slot. Friday afternoon or Sunday evening, and protect it.
  2. Open voice mode and ask it to act as your review coach, one question at a time.
  3. Talk through the week: what got done, what slipped, what is still open, what drained you.
  4. Have it summarize into three buckets: wins, open loops, and next week’s top three priorities.
  5. Paste the summary into your notes app; put the top three priorities on the calendar.
  6. Skim last week’s summary before the next review so patterns surface.
  7. Pick 1 to 3 objectives for the quarter and write each as an outcome, not a task. For each, add 2 to 3 key results: measurable targets with a number and a date, one owner per objective, and a starting confidence level. Keep goals small enough that every key result can be checked objectively at quarter end.
  8. Ask the AI to build the quarter as a simple rhythm: plan in week one, a 15-minute weekly check-in answering 'what did I finish, what is stuck, what is next,' and an end-of-quarter review where you score each key result and carry forward, adjust, or drop it.

Example output

Illustrative. Your results will differ.

  • 5 new reviews found: 4 positive, 1 needs a reply
  • Reply draft ready for the unhappy one
  • You approve every reply before it posts.

Where to paste this prompt

ChatGPT: ChatGPT → Project instructions, or ChatGPT Tasks for scheduled reminders (once a day on Free)

Copy-paste prompt

Adapt bracketed fields to your situation.

Act as my weekly review coach. Ask me one question at a time and wait for my answer before moving on.

Questions:
1. What are the 3 most important things you finished this week?
2. What slipped, and why. In one sentence each?
3. What loose ends are still floating in your head? List them all.
4. What drained your energy for little payoff?
5. What are your top 3 priorities for next week?

When I am done, summarize as: WINS / OPEN LOOPS / NEXT WEEK'S THREE. Keep it short enough to read in 60 seconds. Do not add tasks I did not mention.

Newsletter

Get the free starter pack

Free starter pack with five beginner copy-paste prompts after you confirm, plus three sourced setups in your inbox each week. Unsubscribe anytime.

What usually goes wrong?

Where agents tend to stall on this job. More patterns in Where AI gets stuck.

  • Voice mode rambles. Interrupt it and say "summarize what you have so far" when it drifts.
  • The AI will happily invent priorities you never mentioned; the "do not add tasks" line matters.
  • Skipping two weeks in a row kills the habit; the value compounds from the archive, not one session.
  • Too many objectives and vague key results are the two classic failures. If a key result cannot be checked objectively at quarter end, rewrite it before the quarter starts.

Common questions

What does this setup do?
Close each week by talking through wins, drains, and open loops with voice mode while the AI takes notes, then get a drafted plan for next week instead of a blank Monday.
Who is it for?
Anyone whose to-do list grows until it is paralyzing, and who skips weekly reviews because sitting down to type one feels like homework.
What does it cost to run?
ChatGPT: free tier includes voice mode; calendar and notes apps you already use.
What usually goes wrong?
Voice mode rambles. Interrupt it and say "summarize what you have so far" when it drifts. The AI will happily invent priorities you never mentioned; the "do not add tasks" line matters.
How much time might it save?
Roughly 30–45 minutes per review Estimate only: one practitioner reports the voice-driven review taking ~15 minutes versus a manual typed pass; no timed study exists.

What tips make it smoother?

  • Do it walking. The review feels less like admin when your body is moving.
  • Keep a running "next week" note during the week so Friday is assembly, not archaeology.
  • Score each week 1–10 on focus; after a month you will see what actually moves the number.
  • Write key results as outcomes you can measure at quarter end, not activity lists - 'reach [X] repeat customers by [date]' beats 'work on retention'.

Where do the claims come from?

Summaries use public sources linked below, not independent verification. How setups are picked.

Related setups

Best AI setups for solo operators (2026) →

Ready for the next one?

Next up: a Scheduling setup on the Work path.

Meeting notes to action items and follow-up email

Paste messy meeting notes or a transcript and get decisions, owners, due dates, and a follow-up email draft you send yourself, without the model inventing commitments that were not in the notes.

Estimate only: recap and action-item drafting time varies by meeting length; no timed study cited.