The system of record for what your agents do.
Hound gates consequential agent actions behind policy and human approval, then writes every request, decision, and outcome to an append-only, hash-chained log. Built for AI vendors proving trust, and the enterprises verifying it.
Approve. Replay. Investigate.
The log you keep for compliance is the log you run on every day. Not a gate bolted onto your agent — the record it operates through.
Approve
request_approval before anything consequential. Policy auto-approves within limits; everything else routes to a human as an interactive card inside Claude, ChatGPT, or VS Code. No approval dashboard to check, no context switch.Replay
Investigate
One log. Both sides can trust it.
Ship agents with evidence attached.
Answer the vendor-risk questionnaire with an export instead of an essay. The Agent Trust Report turns your log into the answers their review is asking for.
Verify without trusting anyone.
The standalone verifier checks the hash chain from an export alone. No account with the vendor, no account with us, no taking anyone's word for it.
When the review asks what your agent did, show them.
Every enterprise security review asks the same eight questions. If you sell agents into banks, health systems, or anyone with a vendor-risk team, you've seen them. Hound answers each one with evidence, not paragraphs.
Authorization proof
Human oversight
What, and which rule
Segregation of duties
Log integrity
Replay
Outcome
Data handling
Tamper-evident, never "tamper-proof." Edits and deletions are detectable by anyone holding an export. Identity hardening (OIDC) and external anchoring are on the public roadmap. Vendors who claim more than their architecture supports are the ones your reviewer distrusts — so we don't.