APIR
APIRAPIR · FOR ENGINEERING TEAMS

An agent changed production. Which one, and who allowed it?

Coding and operations agents run commands, open pull requests and touch infrastructure. Your git history shows a bot account. It does not show which agent, on whose authority, or what it was told.

A customer’s security team will ask before they let it near their environment.

WITHOUT A RECORD

The incident review starts by working out which agent it was.

WHAT YOU DO
STEP 1

Register the agent

One form, or the API. The first agent is free. It keeps running where it runs today. Paper your first agent.
STEP 2

Log each tool call

Type tool_call, a one-line summary, and the hashes of the task and the result. Code and secrets stay on your side. The API reference.
STEP 3

Write its mandate

Which repositories and environments it may touch, and until when. APIR signs it.
STEP 4

Show the record

To your own reviewers, or to a customer’s security team, who check it with no account.
ONE ENTRY IN THE LOG BOOK
type      tool_call
summary   Opened PR #812: bump the payments client to 4.2.1
input     sha256 of the task it was given
output    sha256 of the diff

An example of what one entry reads like. The summary is yours to write; the two hashes are computed on your side.

WHAT YOU GET
FREE

The export

A zip of the log book with its timestamp tokens. Anyone runs the open-source checker on their own machine: every hash, every link, and each chain head against its token. The checker.
FREE

A passport link

Once the agent has earned a passport, anyone with the link checks its signature, mandate and record, with no account. Check an agent.
PAID · AUD 499 one-time

The Evidence Pack

One agent’s record, sealed behind a public verify link, with its outside timestamp, for one security review or incident. See it on the pricing page.
WHAT IT WILL NOT DO
  • APIR does not sit in your pipeline. It cannot stop a command or revert a change.
  • It records what the agent reports. Read it beside your own CI and access logs.
  • APIR holds no SOC 2, ISO 27001 or penetration test report. The trust page says so and lists what can be checked instead.

Start with the free step.

No card and no call. Every price is on the pricing page, and what APIR holds and does not hold is on the trust page.

We are taking on the first outside teams now.

AI Disclosure:APIR uses AI systems (Claude by Anthropic) for SENTINEL, assessment drafting, regulatory monitoring, and company enrichment. AI-generated outputs are labelled as such.

Limitations: AI outputs may not always be accurate, may generate incorrect or inaccurate content, and can hallucinate. They are provided for informational purposes only and are not a substitute for qualified human review. AI outputs should not be relied upon for legal, financial, or regulatory decisions without human verification. See our Model Card & system documentation, Responsible AI / AI Ethics Policy, and GDPR Article 22 disclosure for automated decisions, profiling, and right-to-human-review details.