Most prioritisation collapses into “what feels urgent”. A good prompt forces impact × effort × decay × dependency, and names what gets dropped.
Who this is for
ICs drowning in tasks, managers balancing IC + manager work, founders deciding what NOT to do this quarter.
When not to use these prompts
Don’t use these on tasks you haven’t fully captured — prioritisation on partial lists is wishful thinking.
Prompt anatomy / structure formula
Every prompt should carry six elements:
- Role: who AI plays — chief of staff / manager / analyst.
- Context: team / org / scope / data.
- Goal: one deliverable — plan, memo, talking points, doc.
- Constraints: word count, must-include fields, audience seniority.
- Tone: confident, neutral, factual.
- Examples: 1-2 prior samples to anchor format.
Best for
- Weekly task triage
- Quarterly project prioritisation
- Eisenhower matrix replacement
- Drop / delegate / defer decisions
- Energy-budget allocation
12 copy-ready prompt templates
1. Impact × effort matrix
Tasks: {tasks}. Score each on IMPACT (1-5) and EFFORT (S / M / L). Output a 2x2: high impact / low effort (do first), high / high (plan), low / low (drop), low / high (don't do). Add 1-sentence rationale per item.Variables to swap: tasks
2. Decay-aware priority
For each task, classify decay: (a) Compounds if delayed, (b) Stable, (c) Decays (less valuable later). Output: do-soon = Compounding; defer = Stable; drop or do-now = Decaying. Re-rank.3. Dependency graph
Tasks: {tasks}. Map dependencies: which tasks unblock others? Output: (a) Critical path, (b) Tasks that block 2+ others (do these first), (c) Leaf tasks (last).Variables to swap: tasks
4. Drop / delegate / defer
For each task, decide: DO (this week), DELEGATE (and to whom + with what brief), DEFER (with calendar date), DROP (and how to communicate to requester). Don't leave anything in limbo.5. Energy / cognitive load
My energy pattern: {pattern}. Group tasks: (a) Deep-work (mornings), (b) Admin (post-lunch slump), (c) Social / meetings (late afternoon). Re-allocate to match energy.Variables to swap: pattern
6. Quarterly priorities (3 things)
For this quarter, identify the 3 priorities that move the most. For each: outcome, success metric, what we won't do in service of this. If you can't name 3, you have too many priorities.7. Weekly priority memo
Write a 5-bullet "this week's priorities" memo: (1) Top priority + why, (2) 2 secondary, (3) What I'm saying no to (and to whom), (4) Decisions needed from others. ≤ 150 words.8. Saying-no template
I need to say no to `{request}` from `{requester}`. Write 3 options: (a) hard no with alternative, (b) defer with date, (c) yes-if (negotiate scope). Each ≤ 50 words.Variables to swap: request, requester
9. Backlog grooming
My backlog has {n} items. Sort: (a) actionable in 1 week, (b) actionable in 1 month, (c) > 1 month or unclear (move to "someday"), (d) drop entirely (no longer relevant). Output by bucket.Variables to swap: n
10. Maker vs manager day plan
Today is a maker day (deep work). Or a manager day (meetings). Reflow my task list accordingly: which tasks fit which day? Don't schedule deep work between two meetings.11. “What’s the smallest win” filter
For each big project on my list, identify the smallest visible win this week. Outcome: a tangible artifact (memo, prototype, ticket) that proves momentum. Don't propose hidden work.12. Weekly retro
Last week: planned `{planned}`, completed `{done}`. Audit: (1) Why did I miss what I missed? (2) What surprised me (urgent things), (3) One adjustment for this week.Variables to swap: planned, done
Common mistakes
- No specific context — output is generic.
- Skipping fact-check — AI invents numbers.
- Vague audience — over/undershoots seniority.
- No word limit — readers won’t finish.
- Same template every situation — readers tune out.
- No “decision needed” framing.
- Forgetting to attach source data.
How to push results further
- Specify audience level.
- Cap length: 1-page tactical, 3-bullet executive.
- Lead with the ask / decision needed.
- Attach source data link.
- Read aloud before sending.
- AI drafts; humans review.
- Save best examples; reuse format, refresh content.
Practical depth notes
Use these prompts as starting points, not final answers. For Workload Prioritization Prompts: 12 Templates to Decide What Not to Do, the useful extra work is to replace every generic placeholder with a real constraint: audience, channel, length, brand voice, examples to imitate, and examples to avoid. Run at least two versions with different constraints, then compare the outputs side by side instead of accepting the first polished response.
A good result should pass three checks: it is specific enough that another person could reuse it, it avoids vague praise or filler, and it gives you an editable artifact rather than a broad suggestion. If the output feels generic, add one concrete reference, one forbidden pattern, and one measurable success criterion before rerunning the prompt. Before saving a prompt as reusable, test it on one realistic input and one edge case. The realistic input proves the template can produce the normal deliverable; the edge case shows whether it handles messy constraints, missing context, or an unusual audience. Keep the better output, but also keep the failed version with a note on what was missing. That small failure log is what turns a prompt collection from a list of nice sentences into a practical working library. One final check: compare the finished result against the original goal in a single sentence. If that sentence is hard to write, the output is probably polished but unfocused. Tighten the goal, remove decorative language, and rerun only the weak section instead of regenerating the entire piece.
FAQ
- How long should this doc be?: Tactical: 1 page. Executive: 3 bullets + link.
- Can AI replace the analyst / manager?: Drafts and templates yes; judgment no.
- How often refresh?: Cadence-driven; adjust when audience signals fatigue.
- Should risks be included?: Always. Pretending no risk exists erodes trust.
- How to fact-check?: Attach sources; peer review numbers.
- Can AI generate data?: No — AI invents plausible numbers. Connect real data.