HelloPM · AI Builder Series Explore builds →
Quest 7 · Your own PM AI Agent

Your own PM AI Agent

AI agentsGitHubPM toolingVideo

The assignment

Fork Hermes or OpenClaw on GitHub and ship your own Product Manager AI Agent.

What Ritu shipped

Discovery Canvas AI is a Telegram bot that guides a user through structuring a raw product idea into an eight-point Discovery Canvas covering problem, users, jobs-to-be-done, MVP scope, metrics, and validation plan. It is currently in beta, using pairing codes to manage API access during testing.

Open in Telegram ↗ Ritu's full portfolio

Our read on this build

Ritu shipped a Canva-hosted video. This read comes from the artifact and Ritu's own account of it — no scores, just what the build does and does not show.

What it demonstrates

  • It is bent to specific PM work: discovery support — a workflow, not a rename.

What is not shown

  • No fork or repository is reachable from here, so whether this stands on Hermes/OpenClaw or was rebuilt beside them is unclear.
  • It is not shown running against a real PM task, which leaves the distance between 'repo exists' and 'agent works' for the reader to cover.

Take this awayWorth a read for the architecture, then apply the real test to your own: could someone else run it tomorrow without you in the room explaining it?


Why this quest matters

Forking beats a blank page. Standing on Hermes or OpenClaw and bending it to a real PM workflow is exactly how modern builders ship a working agent in days instead of months.

What separated the strongest builds

Across the 24 builds we could open for this quest, the same three or four things kept deciding whether one landed. Useful whether you are judging this one or attempting your own.

It stands on a real codebase

A linkable fork of Hermes or OpenClaw. 'Inspired by' is how people describe a blank page they started anyway.

Bent to one PM job, properly

A PRD writer, a backlog triager, a teardown engine — a workflow the builder actually has. A renamed system prompt on a template is not customisation.

Seen doing the work

Running, answering, producing an artifact you can look at. A repo that claims to work and is never shown working asks for a lot of trust.

No numeric scores are published here. These pages are written reads of what each builder shipped — the build is the point, not a mark out of a hundred.

More from Ritu

Quest 1Quest 2Quest 3Quest 4Quest 5Quest 6Quest 7
← Back to Ritu's portfolio