Write a PRD
Can the model turn a brief into a spec engineers could build from, including how an AI feature behaves when it is wrong?
The PM job
Writing the requirements document a team will build and test against.
Why it matters
A PRD is where ambiguity becomes either a decision or a bug. For AI products it must also say what happens when the model is uncertain or wrong. Most generated PRDs skip that part.
What good looks like
- States the user problem and the decision the PRD enables
- Specifies behaviour under uncertainty, failure and refusal
- Names eval criteria and a launch bar
- Separates must-haves from later ideas
Deliberately not measured
- Formatting or template conformance
- Length
- Visual polish of diagrams
Making product behaviour, uncertainty and eval requirements executable
A generic feature spec that ignores AI failure behaviour
Decision model, LLM judge and blind PM review
AI product PRD (core) · Conventional product PRD
Results
Every setup we’ve tested on this task, across all cases and repeats.
| # | Model · Harness | Task score | Decision model | LLM judge | PM review | Runs | Critical failures | Cost / run | Latency |
|---|
Case viewer
Read the brief, then put up to three outputs side by side. The outputs are the point; the scores just tell you where to look.
Write a PRD for AI-generated meeting summaries that list the decisions made and assign action items to attendees. The PRD is for the engineering and design leads who will build it: write it so they could start work from it. Aim for 1,000–1,500 words.
Specifies attribution confidence, editing, and what happens on mis-assignment; keeps a person reviewing before action items go out.
- Assigns actions to non-attendees
v1.2 · synthetic · AI product, productivity