PROMPT STUDIO

A place for good prompts and clearer ideas.

Run a work retrospective that leads to specific actions

Work

Review a project using a timeline, evidence, and actions with owners and deadlines. Includes a complete example of a delayed handoff.

Edit prompt

When to use this prompt Use this after a delivery, experiment, or project milestone. Remove personal, customer, and confidential information before sending real work notes to an AI service. Copyable prompt Help me review the work below without turning assumptions into facts or assigning blame without evidence. 1. Restate the intended outcome, planned date, actual result, and available evidence. 2. Build a short timeline. Label missing or disputed details instead of filling them in. 3. Separate observed events from explanations. For each possible cause, state what evidence supports it and what would challenge it. 4. Identify what to keep, what to change, and what needs further checking. 5. Propose no more than three follow-up actions. Each needs a clear owner or proposed role, deadline, completion criterion, and a date to review the result. Do not invent an agreement or claim that someone has accepted an action. 6. End with the decisions a person must confirm. Goal: [intended result] Planned and actual dates: [dates] Timeline and evidence: [notes, records, or source text] Constraints: [staff, scope, time, or dependencies] Example input The following is a fictional teaching example, not a real customer project or a completed model evaluation. A team planned to hand over a draft on Wednesday and delivered it on Friday. Monday's kickoff assigned a writer and reviewer but did not define acceptance criteria. On Tuesday the writer requested those criteria. The reviewer supplied them on Wednesday afternoon. A revised draft was ready Thursday and approved Friday. The notes do not record reviewer workload or any agreement on response time. Example output Outcome: the handoff occurred two days after the planned Wednesday date. Timeline: Monday—roles assigned, acceptance criteria absent; Tuesday—writer requested criteria; Wednesday afternoon—criteria supplied; Thursday—revised draft ready; Friday—approval and handoff. Observed problem: acceptance criteria were supplied after drafting had begun. Possible explanation: the kickoff did not establish what "ready for review" meant. The record does not establish whether reviewer workload, scope changes, or other constraints also caused delay. Keep: the writer raised the missing criteria and the team recorded the handoff dates. Proposed actions, subject to team agreement: 1. Project lead: add acceptance criteria to the next kickoff brief before the next project starts. Complete when the writer and reviewer confirm the same checklist. 1. Reviewer: agree a review slot before drafting starts. Complete when a named reviewer and a feasible response window are recorded; review the next handoff to see whether that window was met. 1. Writer: flag missing criteria at the first check-in rather than waiting for a complete draft. Complete when unresolved items appear in the shared issue list with a decision owner. Review point: after the next two handoffs, compare planned and actual dates and check which assumptions held. This is a proposal, not a claim that the process already improved. Human review Confirm the timeline against source records, ask the team whether the proposed owners and dates are feasible, and check alternative explanations before concluding why the delay happened. Avoid turning a two-day delay into an unsupported judgment about a colleague's motivation. For related planning methods, read [AI Prompts for Project Management](https://yepsoso.com/blog/ai-prompts-for-project-management/).

Read prompt

Yep

Build an article outline from a reader's question

Writing

Turn a topic and source notes into a useful outline, with concrete examples, evidence gaps, and a clear next step. Includes a full worked example.

Edit prompt

When to use this prompt Use this when you have a reader's question and some notes but need a clear structure before drafting. Copyable prompt Create an article outline for the reader described below. 1. State the reader's concrete question and give a one-sentence answer using only the supplied information. 2. Propose a working title and 4–6 sections. For each section, specify the question it answers, the key point, a concrete example, and the evidence needed. 3. Distinguish supplied facts from proposed examples. Label invented examples as hypothetical. Do not fabricate statistics, interviews, citations, or personal experience. 4. Identify missing information and unclear assumptions. Keep uncertain claims out of the proposed opening. 5. Finish with a practical action the reader can take and a short list of topics to leave out. Topic: [topic] Reader and situation: [who needs this and why] Source notes: [notes and verified sources] Desired action: [what the reader should be able to do] Example input This is a fictional teaching example and a sample answer written to illustrate the method, not a completed model evaluation. Topic: How to think about the opportunity cost of a free Saturday afternoon. Reader: someone choosing between a paid shift, a course, and rest. Notes: opportunity cost concerns the best feasible alternative forgone; time, energy, and money do not always share a useful unit. Desired action: compare three real options without treating every free hour as lost wages. Example output Working title: "What are you giving up this Saturday? A practical opportunity-cost comparison." Opening answer: Compare your chosen plan with the best realistic alternative you would otherwise take, using the same time period and making non-money benefits explicit. 1. Define the decision. Question: what is actually available? List the three options, the shared four-hour window, and constraints such as travel or a fixed course time. Evidence needed: the person's real schedule and available shift. 1. Compare benefits and costs. Show a hypothetical worksheet with after-expense shift income, the course's learning value, and the value of recovery. Keep learning and rest as described benefits unless the reader supplies a defensible monetary estimate. 1. Select the best alternative. Explain why the opportunity cost of rest might be the paid shift or the course, depending on that person's goals. It is not the sum of both rejected options. 1. Test assumptions. Ask whether the shift is genuinely available, whether fatigue changes the decision, and whether the course can be taken later. Do not equate an advertised hourly rate with a guaranteed alternative. 1. Make and review a decision. Choose one plan, record the main trade-off, and review afterward whether the assumptions were reasonable. A different choice next week is not proof that this week's decision was wrong. Leave out investment-return promises, productivity guilt, and unsourced claims about how successful people spend weekends. Human review Verify the definition against a reliable economics source before drafting, check that all numbers are labelled hypothetical, and ensure each section answers a distinct reader question. The outline identifies evidence to collect; it does not pretend the research is already complete. Read [Opportunity Cost](https://yepsoso.com/blog/opportunity-cost/) for the underlying concept.

Read prompt

Yep

Fact-check a claim: separate evidence, interpretation, and unknowns

Learning

Check the claims in an article or report, verify numbers and sources, and identify what still needs human review. Includes a complete worked example.

Edit prompt

When to use this prompt Use this before publishing an article, report, or research note. It helps organize evidence; you still need to open and read the original sources. Copyable prompt Review the material below. 1. Extract specific, verifiable claims and preserve their context. Separate observed facts, interpretations, and predictions. 2. If you can browse, prioritize original studies, official documents, or first-hand records. Provide the source title, full URL, publication date, and relevant evidence. 3. If you cannot browse, evaluate only the sources I supply. Do not invent links, papers, quotations, or research findings. A link you have not opened is not verified evidence. 4. Label each claim: supported by the supplied evidence, insufficient evidence, conflicts with the source, or currently unverifiable. Explain why. Check dates, denominators, units, and the population studied. 5. Return: original claim; assessment; evidence; unresolved question. Finish with three specific checks a person should perform before publication. Material: [paste the text] Sources: [paste source text or complete URLs] Relevant time period: [enter dates] Example input The following material and sample answer are fictional teaching examples, not an actual tool trial or a completed model evaluation. A draft says: "This tool saves everyone 30% of their writing time." The attached record describes 16 volunteers completing similar tasks. Average time was 8 minutes before and 6 minutes after. There was no randomized assignment or control group. Individual timings and writing-quality scores were not supplied. Check the claim using only these details. Example output 1. "Saves 30%": conflicts with the supplied numbers. The relative reduction is (8 − 6) ÷ 8 = 25%, or 2 minutes from the original 8-minute baseline. 1. "Everyone": insufficient evidence. A volunteer sample of 16 cannot establish a result for all users. An improved average does not show that every individual improved. 1. "The tool caused the reduction": currently unverifiable. Practice, differences between tasks, or participant selection may explain part of the change. 1. "The writing is equally good": currently unverifiable. No quality measure was supplied. A defensible rewrite is: "In this uncontrolled record of 16 volunteers, average time fell from 8 to 6 minutes, a 25% reduction. The record does not establish what caused the change or whether it applies to other users." Human review Check the complete individual timing records, whether the tasks and timing rules were comparable, and whether quality, outliers, and a suitable comparison group were assessed. Do not add an imaginary study to make the answer sound authoritative. For a framework for evaluating reasons and evidence, read [Critical Thinking](https://yepsoso.com/blog/critical-thinking/).

Read prompt

Yep