Rank work with transparent evidence, dependencies, deadlines, and uncertainty instead of a false universal score
5 min setupTested with:ChatGPTReviewed: 2026-08-28
1
Add your context
Your text stays in this browser. AILesson Prompts does not send it to a model or server.
2
Your prompt
Unfilled fields remain visible as placeholders, so you can still copy and edit the prompt
Prioritize the task list using impact, urgency, effort, and the supplied rules.
Tasks, outcomes, stakeholders, deadline sources, consequences, dependencies, estimates, and confidence:
[tasks]
Available people/time, fixed work, skills, energy, and horizon:
[capacity]
Impact, urgency, effort, risk, obligation, weighting, and tie-break rules:
[criteria]
Normalize task descriptions before ranking. Distinguish true deadlines and obligations from requested or self-imposed dates. Score only dimensions supported by the inputs; label unknowns and show rationale rather than inventing precision. Account for dependencies, cost of delay, risk reduction, opportunity enablement, and task size. Return a comparison table, priority tiers, recommended sequence within actual capacity, quick wins that do not displace higher-consequence work, tasks to clarify/defer/decline, sensitivity to uncertain estimates, and the first physical action for the top three. Do not let a short low-value task outrank necessary enabling work merely because it is easy.
Private by defaultPrompt assembly happens locally in your browser. Avoid placing confidential information into any AI service unless your organization allows it.
From input to outcome
A worked example
See how concrete context turns this recipe into a usable result
Actual input
Tasks and evidence
A Submit statutory filing, hard deadline Fri 17:00, penalty if late, 90 min, data ready. B Fix broken checkout for 6% of mobile sessions, live now, estimate 2–5 h, engineer needed. C Make board slides prettier, requested Thursday, no decision impact stated, 3 h. D Approve supplier renewal by Wednesday to avoid service lapse Friday, 30 min after Legal review. E Ask Legal to finish renewal review, no due date from Legal, 10-min request; D depends on it. F Clear 20 low-priority emails, 45 min. G Analyze cancellation spike, potential revenue impact unknown, 4 h, data extraction first 30 min.
Capacity and planning horizon
One manager has 5 hours today and 4 tomorrow. Engineer has 3 hours today. Legal capacity unknown. Horizon through Friday. Manager cannot fix checkout but can prepare reproduction evidence.
Priority rules
Regulatory or service-continuity obligations outrank convenience. Then active customer harm and material decisions. Use qualitative High/Medium/Low for impact and urgency; effort ranges stay ranges. Tie-break by dependency enablement and earliest cost of delay.
Example output
Tier 1: E then D—service continuity. E is a 10-minute enabling request; its urgency is high despite low effort because D cannot proceed without Legal. Confirm Legal's completion date and escalate through the stated process if one exists. B—active harm to 6% of mobile sessions; impact/urgency high, engineering estimate uncertain. Engineer spends the available three hours on reproduction and fix; manager supplies evidence and defines rollback, but completion may require more capacity. A—regulatory, hard Friday deadline, high impact but data-ready and 90 minutes; protect a Wednesday block rather than letting it drift.
Tier 2: G—potentially material but impact unknown; spend only 30 minutes extracting data first, then reprioritize based on magnitude. Tier 3: C—requested date but no decision consequence; clarify minimum useful slide changes or defer. F—low impact; batch only in leftover shallow time.
Today's sequence: send E; manager creates checkout reproduction evidence while engineer starts B; reserve 90 minutes for A; extract G data; use remaining manager capacity for D if Legal returns or for checkout coordination. Sensitivity: if B exceeds three hours, customer-harm mitigation/rollback decision becomes the priority rather than pretending the fix will finish. First actions: E—send a request naming service-lapse date; B—capture affected device/session reproduction; A—open filing checklist and verify submission credentials.
Why this works
1
Deadline-source and evidence fields prevent loud requests from masquerading as objective urgency.
2
Dependency-aware sequencing recognizes enabling work that simple score sorting misses.
Check the result
Are impact, urgency, and effort rationales tied to supplied evidence?
Were real deadlines, requested dates, dependencies, and unknowns distinguished?
Does the proposed sequence fit actual capacity and honor enabling work?
ChatGPT