| What it does | Checkpoint and attack test for AI agents
| AI Behavior You Can Prove
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | SI
| Not given
|
|---|
| Pricing model | Open source
| Paid
|
|---|
| Pricing | Not given
| Platform: $12,000 USD per year (initial pricing, being validated with design partners). Enterprise plan includes additional capabilities such as AI Governance Score, Policy Wizard, Calibration Advisor, and Portfolio Management. Failed and flagged certifications can be sent to Splunk, Sentinel, QRada
|
|---|
| Key features | - Holds risky actions for human approval
- Plain code with fixed rules
- Works with any model
- Attack test reports success rates
- Logs all actions asked, answered and executed
- Open source rules readable by anyone
- Approval expires after one action
- Some actions permanently locked
- Installed via pip
| - Six behavioral dimensions: Factual Grounding, Boundary Compliance, Information Safety, Topical Adherence, Semantic Fidelity, Response Stability
- Cryptographic certification with Ed25519 signatures and SHA-256 hash chains
- Three deployment modes: Shadow (observe), Inline (verdict before delivery), Async (post-hoc)
- Agent chain records for multi-step workflows with signed certified steps
- One-click audit evidence packages for all 19 frameworks and SOC 2 compliance
- Integration with Splunk, Sentinel, QRadar, Slack, Teams, ServiceNow
- Streaming certification with partial and final verdicts
- Clinical-context certification with context-aware scoring for healthcare settings
- Model identity attestation and drift detection with behavioral fingerprinting
|
|---|
| What makes it different | - Plain code rules cannot be argued with by persuasive text
- Model cannot edit the rules it runs under
- Free and open source under Apache 2.0 licence
- Publishes all test results including failures
- Independent lab with nothing for sale
| - Machine-verifiable and auditable proofs instead of dashboards or PDFs
- Per-interaction automatic certification replacing manual compliance assessments
- Cryptographically signed evidence that is verifiable by auditors without an account
- Detects AI behavioral deviations before they become incidents
- Independent verification of AI behavior separate from platform that built the agent
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | Not checked yet ● no change since last check | Not checked yet |
| Trust Flow (Majestic) | 0 | 0 |
| Citation Flow (Majestic) | 0 | 11 |
| Referring domains (Majestic) | 0 | 1 |