Weeks end feeling busy but not productive. The diagnosis is almost always the same: the calendar got planned reactively, one accepted invite at a time, with no priorities to defend against. This walks through a 25-minute Sunday-night workflow that uses AI to score every meeting against your real goals, propose blocks for deep work, and draft the polite “I’m shifting this to async” messages — so Monday stops feeling like an ambush.
What this covers
A reproducible weekly planning ritual that consumes three inputs (next week’s outcomes, current calendar, recent inbox) and produces a defended calendar: deep-work blocks where they belong, low-impact meetings declined or shortened, recurring meetings shifted to async with the Slack message already written. Total wall time: 25 minutes.
Who this is for
ICs whose calendars get fragmented by reactive meetings and “quick syncs.” Managers spending more than half their week in meetings. Founders who suspect they’re optimizing for replies, not outcomes. Anyone returning from PTO to a week they didn’t design.
When to reach for it
When you finish multiple weeks in a row feeling busy but not productive. When Monday morning has more than 4 meetings before noon. When you can’t name your top 3 outcomes for the current week off the top of your head. Run this every Sunday evening — or shift to Friday afternoon if you’re better at planning when the week is still fresh.
Before you start
- Decide your top 3 outcomes for next week. Not 7, not “improve everything” — exactly 3. If you can’t pick 3, do that first; the workflow can’t optimize for nothing.
- Export next week’s calendar (ICS, or copy/paste the agenda view). Strip attendee names if privacy-conscious — title + duration + time is enough.
- Have the last 7 days of inbox subject lines accessible. They reveal what’s actually demanding your attention vs what you think is demanding it.
- Pick one AI: ChatGPT or Claude. Anything with long-context paste-and-respond works.
Step by step
- Dump 3 inputs to AI: this week’s top 3 outcomes, next week’s calendar export, the last 7 days of inbox subject lines. Use clear headers between each.
- Score meetings. Prompt:
Given my 3 outcomes for next week, score each meeting on
my calendar 1-5 for impact on those outcomes. For meetings
scoring 1-2, flag whether to decline outright, shorten by
half, or shift to async. Be honest — I'd rather decline 5
meetings than have an unfocused week.- Propose deep-work blocks. Prompt:
For my 3 outcomes, propose 4 deep-work blocks of 90 min
each across the week. Avoid morning meeting clusters.
Account for typical fatigue (Friday afternoon = light).
Specify which block goes to which outcome.- Identify recurring meetings worth shifting to async. Prompt:
Among recurring meetings on my calendar, which 2-3 could
be replaced by async updates? For each, draft a Slack
message I can send to the organizer proposing the shift.
Keep it polite, specific, and short.- Review the proposed week. AI proposes, you decide — accept or reject each suggestion individually. Some “low-impact” meetings have social value the AI can’t see.
- Apply changes in the calendar. Send the decline / async-shift messages today, not tomorrow.
- Sunday-night ritual: 25 minutes, every week. Save the prompts as a template you paste fresh inputs into.
First-run exercise
- Run the workflow on a real upcoming week, but only commit to the 2-3 cheapest changes (declining a clearly low-impact meeting; blocking 2 hours of deep work).
- Live with those changes for a week. Note what improved and what backfired (e.g., the meeting you declined turned out to be where the political decision happened).
- The second week, expand to 4-5 changes. By week 4, you’re using the workflow fully and you trust the AI’s scoring because you’ve calibrated it on your own outcomes.
Quality check
- Did the AI score against YOUR outcomes, or against some generic “be productive” rubric? If the scoring feels generic, your outcomes weren’t specific enough.
- Are the deep-work blocks at times you’ll actually defend, or at 6am when you’ll skip them? Be honest about when you actually focus.
- Do the async-shift messages sound like you, or like a corporate template? Rewrite voice; AI tone here is often too formal.
- Did the AI flag any high-impact meetings as low-impact? That’s a signal it doesn’t have enough context — feed it more about the outcome it scored against.
How to reuse this workflow
- Save the prompt template with placeholders for outcomes, calendar, inbox. Paste fresh inputs each Sunday.
- Track outcomes over 4 weeks. Compare planned vs actual — the gap reveals which outcomes you systematically deprioritize.
- After 8 weeks, re-read your old plans. Patterns emerge: you over-optimize for X meetings, under-defend Y outcomes.
Recommended workflow
Sunday 8pm: 3 outcomes typed in 3 minutes → calendar pasted → inbox subjects pasted → AI scores 18 meetings, flags 4 to drop/shorten → AI proposes 4 deep-work blocks → AI drafts 3 async-shift Slack messages → manual review accepts 3 of 4 drops, all 4 blocks, 2 of 3 async shifts → calendar updated, messages sent → 27 minutes total.
Common mistakes
- Skipping the 3-outcomes input — AI optimizes nothing without it; you get generic suggestions.
- Declining without an async-shift draft — colleagues feel ghosted; relationships erode.
- Doing it monthly instead of weekly — calendar drift accumulates faster than monthly cadence can repair.
- Accepting all AI recommendations blindly — some meetings have social or political value not visible in the title.
- Planning Monday morning instead of Sunday night — you start the week in reactive mode.
- Sending async-shift messages on Sunday night — wait until Monday morning; nobody wants to think about work Sunday 9pm.
FAQ
- Privacy concern with calendar export?: Strip attendee emails and confidential meeting titles before pasting. “Sync with [Internal Team]” works as well as the full title.
- Tool?: ChatGPT or Claude. Anything with paste-and-respond and long context. Specialty calendar AI tools exist but a long-context chat works for free.
- What if my outcomes change mid-week?: Re-run the workflow on Wednesday with updated outcomes. The ritual scales to mid-week recalibration.
- Does this replace deep planning?: No. It optimizes one week. Quarterly outcomes and roadmap planning are separate exercises this workflow supports, not replaces.
- What about my team’s calendar?: Run it on your own. Once you have a defended week, others will notice and ask how. Then teach.
- Can this work for non-knowledge work?: Less well. The “defend deep work” logic assumes meetings vs focused work as the primary tradeoff.
Related
- AI weekly report tutorial
- AI task breakdown tutorial
- AI SOP Drafting Workflow: Turn Tribal Knowledge into Documented Process
- Productivity AI Tools Comparison: ChatGPT vs Claude vs Gemini vs Copilot
- AI email triage tutorial
- AI OKR Quarterly Planning Tutorial That Doesn’t Drift
- AI Slack Message Tone Tutorial: Direct Without Being Curt
- AI 1-on-1 Meeting Prep Tutorial for Manager and Report