PromptWork
Brainstorm and rank risks for a project plan
Feed in a project plan and get risks ranked by likelihood times impact, each with an early-warning sign and a concrete mitigation to plan around.
Last updated
Fill in the blanks
Assembled in your browser — nothing you type is stored or sent anywhere.
Your prompt
Review the project plan below for the Q1 mobile app relaunch and identify risks.
For each risk give: a one-sentence description, likelihood (low/medium/high), impact (low/medium/high), an early-warning sign someone could actually notice before the risk becomes a problem, and a specific mitigation (not "monitor closely"). Sort the list with the highest likelihood-times-impact risks first. Base every risk on something in the plan — a dependency, a deadline, a resource gap — and if you're inferring a risk that isn't directly supported by the plan, label it as speculative rather than presenting it as certain.
Project plan:
relaunching the mobile app with a new design and payment provider. design is done, engineering starts in 2 weeks with a team of 3 (one just joined). payment provider integration is new to the team and has a hard cutover date from the old provider on March 1st because the old contract ends. app store review typically takes 3-5 days but can take longer for payment-related changes. no dedicated QA, engineers test their own work.
Model-agnostic — works in Claude, ChatGPT, Gemini or any AI chat.
Why this prompt works
- →Requiring likelihood, impact and a sort order forces a ranked list instead of a flat brain-dump, so the reader's attention goes to the risk that actually matters most rather than whichever one the model wrote first.
- →Demanding an early-warning sign per risk, not just a mitigation, is what makes the assessment usable during the project instead of only useful in hindsight after the risk has already landed.
- →Rejecting "monitor closely" as a mitigation and requiring the risk to trace back to something in the plan keeps the model from padding the list with generic risk-management filler that isn't grounded in this specific project.