Instrumentation audit
Every event the code emits, cross-checked against what the warehouse has actually received.
For the team
When a metric moves, ask the code what shipped.
A number moved on Tuesday. Half the answer is in the warehouse and half is in the diff, and today those are two investigations run by two different people. Here they can be one question, asked in a thread.
For data and analytics
The wait today
Every interesting question here spans two systems that do not talk. The warehouse knows the number changed and cannot say why; the repository holds the reason and has never heard of the number. Most of the investigation is the handoff between them, run twice because the first pass asked the wrong half.
They ask
Ask in your own words. The answer names its commit.
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.
- @PRCHD signups dropped 12% on Tuesday — did anything ship that touches the signup path?
- @PRCHD which events does the checkout flow emit, and are any of them dead?
- @PRCHD where is the trial-conversion event fired, and what does it send?
They run
The jobs that keep coming back, written down once.
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 data and analytics, not a catalog to install — PRCHD supplies the engine, and each team writes its own.
Funnel change correlation
The deploys and diffs that line up with a metric movement, with the code behind each plausible cause.
Tracking-plan implementer
A requested event added at every call site, left as a branch to review.
Scheduled and triggered
Some of the work is done before anyone asks.
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.
- A scheduled metric-to-deploy correlation report.
- An anomaly webhook from the analytics platform, firing an investigation recipe against the code that produced the number.
What changes
Analytics questions and code questions become one investigation.
Where it stops. The warehouse half of an answer reaches the agent through the agent’s own tool configuration — PRCHD has no MCP client of its own — so what is attached, and what it may read, stays the operator’s decision.
Other roles
The same host answers the rest of the team.
Product managers
@PRCHD is the export limit still 500 rows, and where is it enforced?
Product questions get answered from the code, without booking an engineer.
Engineering managers
@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.
Founders and CTOs
@PRCHD how hard would it be to support a second currency?
Leadership gets ground truth directly, at 22:00, without pulling anyone off anything.
Where your code lives
The computer you own is the computer that runs.
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
Send this to whoever runs the shared computer.
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.