The agent accountability layer.
An independent check on what your AI agents decide.
Every decision scored against six criteria, kept in a tamper-evident record, and written up in an Audit Report your reviewers can follow.
Free self-serve sign-up. No sales call. See a sample report.
See it in action
Jiminy, in motion.
Built in, not bolted on
How Jiminy stays trustworthy.
Independence, integrity and reliability are properties of how the audit works, not settings you switch on.
Independence
On independent accounts, the organisation that runs the agent cannot be the one that signs off its audit. This is a rule in the data model, not a setting.
Integrity
Each step of a trace is hashed into a chain, so any later change is detectable.
Reliability
Up to five independent judge passes per trace. When they disagree, the more cautious verdict wins.
Live audit
Every trace runs through six criteria
AUDIT
Every trace checked against
six criteria in seconds
six criteria in seconds
RECORD
Tamper-evident, kept for
your retention period
your retention period
REPORT
Audit Report as PDF,
on demand
on demand
The problem
You're deploying AI that makes consequential decisions. Can you explain every one of them?
The EU AI Act, FCA Consumer Duty, and ICO guidance all assume you can. Most teams today cannot. Jiminy closes that gap, without changing how your agents work.
SDK-based integration
Build a hash-chained trace of your agent's decision with the Jiminy Python SDK and submit it for audit. No changes to your agent architecture required.
Criteria-based audit
Every trace is scored against a structured six-criterion rubric: scope adherence, tool authorisation, escalation judgement, output traceability, data boundary, and differential treatment.
Hash chain
Step hashes link every tool call into a tamper-evident chain, so a later change is detectable.
Multi-run reliability
Opt in to up to 5 independent judge passes on a single trace. Jiminy returns the majority verdict, with ties always resolved toward the more cautious outcome, by design.
In action
The audit report your compliance team has been asking for
Full dashboard: audit report, verdict banner, attestation chain, criteria breakdown
Works with your stack
Go deeper
Read more before you decide.
How it works
The actual architecture: agent decides, trace submitted, audit runs, report issued. Under 60 seconds.
EU PLD
The new Product Liability Directive applies from 9 December 2026. What it means for your records, and why a dashboard alone may not be enough.
Independence
Why an evaluator inside your own environment can't claim independence, and what Jiminy does differently.
Get started
Built for the people who hold AI decisions accountable.
Compliance leads, internal audit, finance and risk teams, and the developers who ship the agents.