Skip to content
How it works · always on, no exam

Set it up once. It runs on the real work.

No homework, no two-week clock, no simulation day. You connect a repo or two, and Promptster reads how your team actually works in the AI tools they already use — then turns it into team trends for managers and private, concrete coaching for each engineer.

How it works · always on, no exam

Set it up once. It runs on the real work.
No homework, no two-week clock.

01

Connect.

One CLI instruments the AI tools your engineers already use (Claude Code, Codex, Cursor, Copilot), scoped to the repos you choose.

# platform team · one-time setup
promptster connect
3 repos · open-source client · 23 engineers notified
02

Capture, continuously.

Real work sessions as they happen: no exam, no simulation day, no clock. Promptster reads where spend leaks, where context thrashes, and where the workflow could be tighter.

● live · always on
spend · context · workflow · skills
23 engineers · 3 repos · real work
03

Act.

Managers get an aggregate team dashboard: savings, fluency, skill adoption. Each engineer gets a private view with targeted, self-directed fixes.

# two surfaces, one wall
manager → team trends
engineer → private coaching
Getting started · honestly, not much to it

What setup actually involves.

If you can point us at a repository, you can run Promptster. The hard part — reading sessions, attributing spend, scoring workflow — is ours. Your part is four small decisions.

One CLI, every agent

The same client instruments Claude Code, Codex, Cursor, and Copilot. You don't pick a tool or mandate one — it reads whatever your engineers already reach for.

You choose the repos

Capture is scoped to the repositories you connect. Nothing outside them is ever read. Start with one repo and expand when you're comfortable.

Engineers are told

Onboarding notifies every engineer that capture is on and points them at their own private view. It's enablement, not a hidden monitor.

Then you leave it alone

There's no exam to schedule and no clock to start. It runs on real work as it happens; the dashboards fill in on their own.

Privacy · code never leaves your device

We read the prompt context, never your source.

It's read-only, and nothing routes through a proxy. We capture prompt context and process telemetry only — never the code — retained for no more than 90 days and deleted on request. An individual engineer's numbers stay with that engineer; managers see team-level aggregates only.

Captured
  • prompts & plans
  • tool calls
  • terminal commands
  • test runs
Never captured
  • your source code
  • keystrokes
  • screen recording
  • anything outside scoped repos

The shape of a PR description, never the code itself — captured by a client you can read line for line.

See it on your own team

Book a 15-min walkthrough.
We'll show the live dashboards.

Bring a VP Eng or platform lead, and we'll show the manager view and an engineer's private view, and you decide in 15 minutes whether to connect a repo and see your own.

or get the monthly memo
no spam · we reply personally