The control plane for AI actions

The safety checkpoint every AI action passes through — before it happens.

Your agent can send the email, issue the refund, update the record. SafeAct makes sure it does that safely, once, and on the record — so your risk team says yes instead of no.

$ pip install safeact $ npm i safeact
The problem nobody wants to admit

The agent isn't too dumb to deploy. It's too untrusted to let act.

Almost every company launched an AI agent this year. Almost none put one into production — not for lack of intelligence, but because no one could trust it to touch real money and real customers.

97%
of companies launched an AI agent this year
12%
reached production at scale
4 / 5
of SafeAct's guarantees are already running in production code
What SafeAct does

Four things, every single time your agent acts.

Enforced in code — underneath any agent framework. The model proposes; SafeAct decides whether the action is allowed to happen.

Checked

Every action is checked against your rules — in code, not a prompt the model can talk its way around.

Held when unsure

Low-confidence actions are routed to a human to approve or reject — not fired off blindly. The confidence signal comes from real checks (our companion library wobbly), not the model grading its own homework.

Exactly once

Crash, restart, retry — the refund still goes out once. And if it's genuinely unknowable, SafeAct says so instead of guessing.

Provable

A tamper-evident receipt for every action: what happened, why, which rule was in force, and who approved it.

See it in 90 seconds

One refund agent. Five moments. The whole thesis.

Nothing staged — this is the product doing its job, start to finish.

01

Agent issues a routine $50 refund.

✓ CLEARED
02

Agent tries a $50,000 refund.

✋ HELD
03

A human clicks approve. It runs.

✓ RAN
04

Server dies mid-payment, restarts.

① NO DOUBLE
05

One button: "Prove it."

🔒 RECEIPT
How it's built to spread

Free core. Paid control.

Two free libraries get developers in the door — the action spine and the verifier. The control plane is what their risk and compliance leads pay to keep.

SafeAct Core + wobbly
Free · two open-source libraries
  • Exactly-once, crash-safe execution
  • Honest "in-doubt" state — never a blind retry
  • Saga rollback for multi-step actions
  • Python & TypeScript, ten lines to adopt
  • Runs local — one file, no server
  • Ships with wobbly — label-free checks that flag unstable AI outputs before you act on them
Install the library
SafeAct Control
Talk to us · for teams that answer to someone
  • Human-approval inbox for held actions
  • Rules-as-code policy engine, versioned
  • Tamper-evident audit of every action
  • One-click "prove it" regulator export
  • Roles, multi-team, SSO
Book a demo
Built by people who've shipped this

Let your AI act. Keep the proof.

SafeAct comes out of running real, action-taking agents in production — where we learned exactly how they break. That knowledge is the product.

Get started free