Velaris GroupStrix

Approve what AI does for you.
Stop what you didn't agree to.
Take the proof with you.

Strix is an execution control layer for AI agents and autonomous software. Every governed action is evaluated before it runs — and every decision produces a signed record anyone can verify, with or without us.

Book a demoSee it happen ↓

The gap every AI deployment has.

Logins prove who you are.

Permissions say what you may do.

Logs say what already happened.

Nothing decides whether it happens. That is what Strix does.

Model-level guardrails filter what an AI says. Observability tools record what it did. Strix sits at the only point where either can still be prevented: the moment an action is about to execute.

Every action gets one of three outcomes.

✓ Allow

The action runs — and a signed record of the decision is written before the side effect.

✗ Deny

The action never runs. The record shows what was refused, and why.

⏸ Intercept

A human decides first. The approval is single-use and bound to the exact action that was approved.

For engineers: what the integration looks like
Before — no governance
adminProcedure
  .input(z.object({...}))
  .mutation(handler)

// Executes immediately
// No evidence
// No control
After — governed
governedProcedure("admin.programs.delete")
  .input(z.object({...}))
  .mutation(handler)

// Intercepted → Evaluated → Decided
// Evidence recorded every time

Any async function or HTTP call can be wrapped the same way with governedAction() from the MIT-licensed @strixgov/governed-action package. Underneath, five rules hold: nothing executes without evaluation; authority does not carry over between actions; admissibility is judged at execution time; enforcement happens before the side effect, not in a log after it; and execution grants are single-use, expiring, and revocable. Full architecture in the docs.

The refund bot, governed.

A demonstration you can walk yourself — every record signed and re-checked on the page, nothing asserted.

  1. 1 · Denied. An AI agent, refund_bot_v3, asks to delete every customer record. The capability was never granted to it — the request is refused and nothing runs. The refusal itself becomes a signed record.

  2. 2 · Held for a human. It then asks to issue a $4,200 refund. That exceeds its autonomy, so the action waits for a human approver — and the approver cannot be the one who asked.

  3. 3 · Executed, once. After approval, the refund runs exactly once — and the whole exchange is a chain of signed evidence you can re-verify, including the four honest verification states (verified, invalid, legacy-unsigned, unverifiable).

Walk the full demo →
Check a real production record from your own terminal
npx @strixgov/verifier@latest 5686

This re-derives the record's hash, chain, and Ed25519 signature against the public key at /.well-known/strix-jwks.json — no Strix account, no SDK. If we disappeared tomorrow, every record we ever produced would still verify against the key you already archived. That is the difference between an audit trail and an audit story.

Three rules that do the work.

1

Agents cannot issue their own permission slips.

Execution tokens are minted only by the decision kernel, are single-use, and expire. An agent cannot grant itself the authority it was refused.

2

The one asking cannot be the one approving.

For high-risk actions, the actor requesting an action cannot be the actor who approves it — enforced in policy evaluation, not in the UI.

3

The record outlives the thing it recorded.

Deleting a governed object does not delete the signed evidence of what happened to it. The trail stays verifiable after the data is gone.

EU AI Act flags (Articles 12, 14, 28) are derived from cryptographic verification of each record — never asserted. The NIST AI RMF and SOC 2 crosswalk is published at /compliance-map.

For federal and self-hosted buyers: each deployment holds its own signing keys — Strix does not hold customer signing keys. Strix is not currently FedRAMP authorized; authorization is in evaluation.

See it on your own workflow.

Thirty minutes: wrap one action, watch it get allowed, denied, or held — and verify the record yourself before we hang up.

Not ready to book? Write to admin@strixgov.com or call (505) 305-7900. More ways in — including a written-question form — at /contact.

Strix is a product of Velaris Group.