| What it does | Independent verification for AI agent outcomes
| Engineering firm that tests AI agents before customers use them
|
|---|
| Stage | Startup
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| TH
|
|---|
| Pricing model | Freemium
| Paid
|
|---|
| Pricing | Hobbyist: free forever with 250 checks/month; Pro: $9/month with 2,500 checks/month, $0.01 per extra check
| Production readiness review: USD 10,000 (ten working days, up to 10 tools and MCP servers, one re-run within 30 days). Founding-client price for first three: USD 6,000 for published summary. Forward deployed engineers: USD 12,000 per engineer per month (minimum one month, invoiced monthly in advance
|
|---|
| Key features | - Independent outcome verification with VERIFIED, FAILED, or UNKNOWN status
- First-party adapters for Stripe, GitHub, Linear, Sentry, Resend, and HTTP endpoints
- MCP integration with Claude Code, Cursor, and any MCP host
- GitHub Actions required check that fails on unverified claims
- Audit trail storing claims, evidence, and verdicts separately
- Capability inspection before agents call tools
- Read-only credential access with AES-256-GCM encryption
- Continuous monitoring with watches every 5-10 minutes on Pro plan
- Evidence retention for 7 days on Hobbyist, 1 year on Pro
| - Automated tests built from real production failures
- Security review of tools and MCP servers
- Signed go/no-go verdict from founder
- One re-run within 30 days
- Up to 10 tools and MCP servers per review
- Forward deployed engineers for go-lives
- Round-the-clock engineer support
- Monthly regression testing after model changes
- Up to 100 production traces per agent per month
|
|---|
| What makes it different | - Refuses to guess: returns UNKNOWN rather than false positives when evidence is unreachable
- Neutral gate between agent execution and success verification
- Runs the same way in production as in development
- Never needs write access, only reads authoritative state
- Structured audit trail for debugging and agent evaluation
| - Founder personally leads and signs every verdict
- Same price for go and no-go verdicts
- All code built stays in customer's repository
- 24/7 engineer shifts to match customer time zones
- Founding-client price of USD 6,000 for first three reviews
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 2 ● no change since last check | 4 ● no change since last check |
|---|
| Trust Flow (Majestic) | 1 | 0 |
|---|
| Citation Flow (Majestic) | 23 | 16 |
|---|
| Referring domains (Majestic) | 14 | 5 |
|---|
DidWork
Volans Aquilae