What this covers
The pain: you have a goal like “launch v1 in 8 weeks” or “learn enough ML to ship a side project”, and every time you sit down to plan, the goal feels too big and you do something easier instead. This workflow uses AI to decompose ambitious goals into milestone → week → day, with measurable outcomes at each level, so on Monday morning you know exactly what to do for two hours. The trick is decomposing one level at a time — not the whole quarter — because anything past week 2 will change.
Who this is for
Founders shipping a v1, students preparing for a thesis or exam, side-hustlers stealing 5 hours a week from real life, and individual contributors with a quarterly OKR they cannot start. Also useful for tech leads scoping a feature: the same milestone-week-day decomposition produces a Linear epic with sensible weekly tickets.
When to reach for it
Start of a quarter, project kickoff, sprint planning where a story is still vague, or anytime you find yourself staring at a goal and reaching for email instead. Also when you have been working for two weeks but cannot describe what you actually shipped — that is a sign the goal was never broken down to a measurable outcome.
Before you start
- Write the goal in one sentence with a deadline. “Launch v1 in 8 weeks” works. “Get serious about ML” does not.
- Name the definition of done. If the goal is “launch v1”, does that mean signups open, first paying customer, or App Store live?
- Block 30 to 45 minutes of uninterrupted time for the planning session. Decomposition is not a 5-minute task.
- Know your real weekly capacity in hours. If you have 6 hours a week, AI will happily plan 20 — that is a fantasy plan.
- Have your tracker open (Linear, Notion, Things, Todoist). Each day-level task goes in immediately.
Step by step
- State the goal and time horizon in one sentence. Example:
Launch v1 of my note-taking app in 8 weeks with 50 beta users. - Ask AI to decompose into 4 milestones, each with a measurable outcome. Reject any milestone whose success criterion is a verb like “improve” or “build”.
- Pick milestone 1 only. Ask AI to break it into weekly outcomes — a sentence per week ending with what is shippable on Friday.
- Pick week 1 only. Ask AI to break it into daily tasks of 2 hours or less, marking dependencies between days. Reject tasks larger than 2 hours.
- Capture each daily task in your tracker with the milestone tag and the week tag. Tag dependencies so blocked tasks do not stare at you.
- Execute week 1. Re-decompose milestone 1 week 2 only after week 1 is done — what you learned in week 1 will invalidate week 3’s plan anyway.
- After milestone 1 ships, re-decompose milestone 2 from scratch. Do not trust the plan AI made for milestone 2 eight weeks ago.
First-run exercise
Pick a small goal first — one you can finish in 2 weeks, like “ship a personal site”. Decompose into 2 milestones, 2 weeks, daily tasks. Run the decomposition end to end, but do not start executing for 24 hours. Sleep on it. The next morning, look at day 1’s tasks: can you start the first task in 90 seconds without any further thinking? If yes, the decomposition is good. If you have to think about “where do I begin”, a day-level task is still too abstract — push it one level smaller.
Quality check
- Every milestone has a measurable outcome. “Improve UX” is not measurable. “First-time user can sign up and create a note in under 60 seconds” is.
- Every weekly outcome ends with something shippable, demoable, or measurable on Friday. Otherwise the week disappears into busywork.
- Every daily task is 2 hours or less. AI consistently over-estimates how much fits in a day; cut every task by 30%.
- No task references a tool you have not installed or an API you have not signed up for. Add a “setup” task as day 0.
- Dependencies are explicit. If “deploy to prod” depends on “buy domain”, the dependency must be visible.
How to reuse this workflow
- Save the milestone prompt, weekly prompt, and daily prompt as three separate snippets. Each is one-line tweak per goal.
- Keep a
goals/folder with one file per quarterly goal. After 4 quarters, you have a corpus of how long real things took versus AI’s estimates. - Track an “AI estimate vs actual” ratio per category. For coding tasks the ratio is often 2 to 3x; for writing it is closer to 1.2x. Apply the ratio to future AI estimates.
- Re-run the milestone decomposition every 2 weeks even when nothing has slipped. New information should change the plan.
- After a goal ships, write a one-paragraph retro and paste it into the next quarter’s planning prompt. AI gets better with examples of your real velocity.
Recommended workflow
Goal in one sentence with deadline → AI proposes 4 milestones with measurable outcomes → pick milestone 1, AI breaks into weekly outcomes → pick week 1, AI breaks into daily tasks under 2 hours with dependencies → capture in tracker → execute week 1 → re-decompose week 2 → ship milestone → re-decompose milestone 2.
Common mistakes
- Decomposing all 4 milestones into daily tasks at once. By week 2, half the day-level tasks are obsolete and you stop trusting the plan.
- Tasks larger than 2 hours. They sit in the tracker for days because starting feels too expensive.
- Milestones with no measurable outcome. “Improve onboarding” expands forever; “reduce signup-to-first-action time to under 60 seconds” finishes.
- Trusting AI’s time estimates without applying your personal velocity ratio.
- Skipping the day 0 setup tasks. The first real task often blocks on installing a dependency, signing up for a service, or finding a credential.
- Replanning instead of executing. If you have decomposed the same week three times, the problem is not the plan.
FAQ
- My goal keeps changing. Is this workflow still useful?: Yes — re-decompose more often. Treat the milestone level as stable for the quarter and re-decompose weeks every Friday.
- What if AI suggests a milestone I cannot do?: Push back in the conversation: “I do not have backend skills. Re-decompose with that constraint.” The plan gets dramatically more useful.
- Should daily tasks be 1 hour or 2 hours?: Two hours for focused work, 1 hour if the task is research-heavy or requires switching contexts. Smaller is always safer.
- How do I handle goals that depend on other people?: Mark those tasks
waiting on Xand have a separate sub-plan for the dependency. Do not let waiting tasks block your own work. - Can I use this for personal goals like fitness?: Yes. The milestone-week-day structure works for any goal with a deadline. Replace “shippable” with “measurable” — pounds, miles, minutes.
- What if I miss week 1’s outcome?: Do not catch up; re-decompose. Ask AI to compress milestone 1 into 3 weeks instead of 4, accepting that something has to drop.