ThinkWithPrompt by SynotticThinkWithPrompt

Estimate task durations with three-point (PERT) estimates

Converts optimistic, likely, and pessimistic guesses into expected durations, ranges, and a total you can defend.

Projects & OperationsRTFStandardFill-in Template

The prompt

Help me estimate task durations using three-point (PERT) estimating. Tasks: [LIST each task with optimistic / most likely / pessimistic duration - e.g. "Data migration: 5 / 8 / 15 days"] Which tasks are sequential vs. parallel: [DEPENDENCIES, if known] Who gave the estimates: [the people doing the work / me / a vendor] Units: [working days / hours] For each task: - Calculate the PERT expected duration: (O + 4M + P) / 6. - Calculate the standard deviation: (P - O) / 6. - Flag tasks where the spread is very wide (pessimistic more than 2x most likely) - these are where the real uncertainty lives. For the sequence of dependent tasks, sum the expected durations and combine the variances (square root of the sum of squared standard deviations) to give a total with roughly 68% and 95% ranges. State that this assumes tasks are independent, which often understates risk. Also check the estimates for common problems: estimates that look like padded round numbers, missing tasks (testing, reviews, approvals, handoffs, deployment), and optimistic figures that assume no interruptions. Return: 1. A table: task | O | M | P | expected | std dev | risk flag. 2. Total duration with 68% and 95% ranges. 3. The 3 tasks driving most of the uncertainty and a question to ask the estimator for each. 4. A one-sentence way to communicate the estimate to stakeholders as a range, not a single date.

Highlighted [brackets] are blanks to replace with your own details.

Fill in the blanks and use this promptMore Projects & Operations prompts

What to fill in

  • DEPENDENCIES, if known
  • the people doing the work / me / a vendor
  • working days / hours

How this prompt is built

This prompt follows the RTF structure (Role, Task, Format). RTF tells the model who to be, what to do and what shape the answer should take. It is the quickest structure that still gives noticeably better results than a bare request.

Related prompts

Find more prompts like this