Hi Product Hunt, Galang here. I built Thinkr because of one pattern that kept burning me: every PRD I shipped went out a little foggy, and my team caught the real gaps in review a sprint too late. AI writing tools didn't help. Helpful defaults to agreeable, so you get twenty suggestions of equal weight, none of them willing to tell you which one sinks the launch. They polish what's already on the page instead of hunting for what's missing, the edge case nobody mapped, the acceptance criterion nobody wrote. And reviewing a spec is a skill almost no PM is taught. We learn to write PRDs, we never learn to red-team one. So Thinkr is a reviewer first. Try the thing in the title: open a PRD you already shipped and were proud of, and run the critique. It does 11 named passes, the rubric is published so you can see exactly what's checked, and findings land on the line they concern with a rewrite you can accept. It ends on a 0–100 score that's computed from those findings, so it reproduces. One honest note: if you mainly want an all-in-one generator, ChatPRD is cheaper and does that well. Thinkr's bet is the review step. Free plan plus no-card trial. I'm here all day, tell me what it catches in your spec.

Forum Threads

p/thinkr

•

24h ago

PMs, how do you actually review a PRD before it ships?

Writing a PRD is taught. Reviewing one isn't.

Most of us learned to write specs from templates and examples, but I've never seen anyone taught how to red-team one: to hunt for the missing edge case, the metric with no baseline, the acceptance criteria that aren't testable. Those gaps usually surface in eng review, a sprint too late.

View all

Thinkr

Run 11 named passes on the PRD you thought was done

Run 11 named passes on the PRD you thought was done

Forum Threads

PMs, how do you actually review a PRD before it ships?

Forum Threads

PMs, how do you actually review a PRD before it ships?