Feasibility sketch
A scoped estimate with the files it would touch, the risky parts, and what it cannot tell from the code alone.
For the team
Half your questions are ones you’ve asked an engineer before. The other half are “is this already built?”, which only the code can answer. Now you ask the code yourself, in a channel you’re already in.
For product managers
The wait today
Product decisions get made against a mental model of the code, and that model is always a little out of date. The gap is filled by interrupting somebody — which is expensive enough that most questions never get asked, and the ones that do arrive as a meeting.
They ask
Mention @PRCHD with the question you’d have saved for a colleague, and it reaches the agent exactly as typed. The agent reads the project’s checkout in Act mode, which changes nothing on disk, and the answer lands in the thread footed with the commit it was read from.
They run
Each is a prompt plus a posture that someone on the team writes once. After that, anyone in a private channel the operator enabled for runs starts it with one slash command, and the result comes back in the thread. These are examples for product managers, not a catalog to install — PRCHD supplies the engine, and each team writes its own.
A scoped estimate with the files it would touch, the risky parts, and what it cannot tell from the code alone.
Where the implementation has drifted from a spec document, point by point.
A scoped story, filed in your tracker through the agent’s own configuration, with acceptance criteria taken from how the code behaves today.
What your equivalent screen does today, after the agent opens theirs with the browser tool.
Scheduled and triggered
Put the same recipe on a cron line or behind a webhook URL and it starts on its own, so work that used to wait for someone to wake up or find time is already done when people arrive.
What changes
Product questions get answered from the code, without booking an engineer.
Where it stops. Questions run in Act mode, so the agent reads the checkout and changes nothing on disk. Starting a recipe from Slack happens in a private channel the operator enabled for runs.
Other roles
@PRCHD what’s changed on main since Friday, and what’s risky in it?
The status an engineering manager currently assembles by asking five people assembles itself.
@PRCHD how hard would it be to support a second currency?
Leadership gets ground truth directly, at 22:00, without pulling anyone off anything.
@PRCHD a customer says CSV export drops the last row — is that possible in the current code?
The first-line answer comes from the code, names its commit, and takes a minute.
Where your code lives
Repositories, worktrees, prompts, transcripts, diffs, command output, attachments, environment values, and the event log stay on the computer you installed PRCHD on — the one that already has your code and your tools. The agent works there, so there is nothing to copy into a hosted environment and nothing uploaded to be indexed.
One small public service handles what a computer with no open port can’t do on its own: it enrolls your computer’s identity, forwards short push notifications, and holds webhook deliveries until your computer collects them. Each delivery is sealed to your computer’s public key the moment it arrives, so the service only ever holds ciphertext, and it is never in the path of your work.
Standing watch
One person installs it — an afternoon, not a migration. Everyone else asks from a Slack channel they’re already in, and nobody creates an account, installs an app, or pairs a phone.