Selected work · Product case study

Squirrel Board

A shared ideas backlog for the awkward space between we should remember this and we have decided to do it. AI collaborators help capture, retrieve, and develop ideas. Decisions about what becomes work remain mine, including what I explicitly delegate.

My role: Product owner and workflow designer
Status: Private system in use; public hackathon demo frozen at submission.

Open the historical hackathon demo (external)See the product decisions

The problem

Good ideas were becoming accidental commitments

My AI collaborators and I do not have an idea shortage. The harder problem is keeping a promising thought without immediately promoting it into a project, forgetting where it came from, or letting momentum make the decision by default.

A normal task list starts too late. Squirrel Board was designed for the earlier, messier stage between this may matter and we have decided to do it.

The product rule

Capture first.

Triage later.

Do not turn every squirrel into a project.

Capturing an idea preserves it. It does not change its priority, activate work, or authorize anyone to act on it.

The design

Authority is part of the product, not a disclaimer

Capture is not commitment

An idea can be saved with its reason and provenance and still remain inactive. Remembering something does not make it urgent.

Agents propose. People decide.

AI collaborators can capture and retrieve ideas or suggest an update. They cannot quietly turn a suggestion into the authoritative record.

Make the history visible

Proposals and decisions stay in the record. A user can see what changed, who contributed, and who made the final call.

Do not build ahead of the evidence

A feature earns its way onto the roadmap by solving a problem that has actually shown up. “That sounds useful” is not enough.

My role

The rules came from using the thing

Squirrel Board grew out of a problem in my own working process: I wanted room to explore ideas without turning every interesting thought into another commitment. I also wanted to stop adding sticky notes to the edge of my monitor, the whiteboard, and the side of my desk, then hoping I’d remember to look for them before they fell off and got tossed.

I defined the workflow and the boundaries around it: what collaborators could capture, what required a proposal, and who could authorize a change. I tested those choices through regular use, reviewed how they appeared in the product, and refined them when the workflow exposed an ambiguity.

AI collaborators contributed design exploration, implementation, testing, and documentation. I retained responsibility for product direction, delegated authority, and acceptance. The aim was to make collaboration useful while keeping decisions and their ownership visible.

What it demonstrates

What the work demonstrates

Separating idea capture from commitment, so saving a thought does not automatically start work.
Defining what agents can do independently, what requires a proposal, and where explicit authorization is needed.
Preserving the context behind an idea and the history of proposals and decisions.
Refining the workflow through regular use, including situations where authority needed clarification.
Keeping the public demonstration separate from the private working system.

A lesson from use

Make delegated authority explicit

Regular use exposed a distinction worth making explicit: a collaborator can carry a decision on my behalf when I have delegated that authority. The workflow needs to preserve that authorization rather than assume it from who delivered the message.

Explore

See the workflow in the public demo

The public version is the original hackathon demo, frozen where it was submitted. The private successor is the one we actually use.

Open the historical hackathon demo