πŸ“‹ Product Manager Β· PRDs / competitive analysis / requirements

The PRD you spent half a day on β€” a peer ships in an hour using Claude, with data to back it

It's not AI β€” you're treating AI like a 'draft generator' instead of a collaborator.

Your current approach vs. what peers achieve

It's not the tool β€” it's how you use it.

Before

How you probably write PRDs today

  • 1 Open Lark / Notion, stare at a blank template
  • 2 Write the "user persona" section from memory
  • 3 Get stuck, ask ChatGPT: "Write me a PRD for feature X"
  • 4 Get generic copy β€” 80% needs rewriting, data backing from your own BI digging
Half a day - 1 day / weak data backing
After

SOTA workflow β€” no extra spend required

  • 1 Use a spec template (What / Why / Users / Constraints / Metrics)
  • 2 Claude reads spec + your company's PRD history + related data
  • 3 Subagent A scans competitors; Subagent B summarizes user interviews
  • 4 Claude produces a sourced draft; you focus on value judgment
1 hour / with data backing

Going from 'let AI write a PRD' to 'let AI read your company's PRD history first' β€” that's the gap between a real assistant and a boilerplate generator.

3 key actions that get you to SOTA β€” for free

1

Write a structured spec first

Don't put AI in front of a blank doc. Use a What / Why / Users / Constraints / Metrics frame, then let AI fill it in.

2

Feed historical PRDs as context

Drop in 3-5 strong PRDs from your company alongside the prompt. Output picks up your company's voice and structure.

3

Parallel research + counter-arguments

Have AI run competitive analysis + user-needs comparison + counter-arguments in parallel. Single-threaded thinking becomes multi-threaded validation.

Want to know your current AI-efficiency score?

Diagnosis tailored to Product Manager scenarios β€” benchmark report + concrete next steps in 5 minutes

Powered by the LoreJump benchmark system, referencing Anthropic / Thoughtworks / OSSF / DX Core 4 and other authoritative sources

Doesn't cover your scenario?

Tell us your specific scenario β€” we'll notify you first when the matching diagnosis opens

Tell us your scenario

Outside the 5 core groups β€” leave your email and a description, and we'll prioritize you when the matching diagnosis opens