Sample report with made-up data. Yours is built from your own app. Start your free report →

30-day report — Acme Billing (sample data)

Observe mode: nothing was blocked. The figures show what the rules would have done in protect mode.
22 Oct 2026 – 21 Nov 2026
generated 21 Nov 2026
from the OneHuman portal

AI agents were inside 77 of your customers' sessions (5.2% of 1,481).

4 agent products: Claude in Chrome, Claude app browser, Codex (Chrome extension), Browser side-panel agent. They asked for 270 protected actions; your rules would have hidden private data 144 times, sent 65 to the account owner for approval and kept 34 closed.

1,481sessions on protected endpoints
5.2%had an AI agent in them (77)
243agent requests would have been refused, hidden or sent to a passkey
0requests by people would have been refused

What we noticed

Sessions per day

22 Oct 202620 Nov 2026

all sessions sessions with an AI agent

Which AI agents

AI agentSessionsRequests
Claude in Chrome41140
Claude app browser1350
Codex (Chrome extension)1238
Browser side-panel agent1142

Which endpoints they touched, and what the rules would have done

EndpointAll requestsBy an agentWould refuseWould hideWould ask passkey
invoices.read1,211730730
customers.read625710710
settings.api_keys34343400
payments.create33330033
customers.export32320032
reports.read57727000
profile.read5720000

Effect on real people

1,404sessions by people only
0times a person would have been asked for a passkey
0requests by a person would have been refused

Evidence

3,084 of 3,084 decisions carry a signed proof (Ed25519), made on your server. An auditor checks them without trusting OneHuman: export the proofs, then run npx onehumanai verify-proof proofs.json --keys https://<your-site>/onehuman/proof-keys.

Want help going live? Book 15 min: cal.com/onehumanai