| What it does | Human evaluation for text-to-speech with blinded listening studies
| Independent verification for AI agent outcomes
|
|---|
| Stage | Not given
| Startup
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | US
| Not given
|
|---|
| Pricing model | Paid
| Freemium
|
|---|
| Pricing | $18.00 per hour of audio heard by listeners; $0.30 per judgement on a pair of two 30-second clips; $300.00 for 200 pairs × 5 ratings with 30-second clips (1,000 judgements)
| Hobbyist: free forever with 250 checks/month; Pro: $9/month with 2,500 checks/month, $0.01 per extra check
|
|---|
| Key features | - Blinded paired-preference studies with no system names visible
- API for creating studies and retrieving results
- Exact price quote before study starts
- Per-judgement data export as CSV
- Paid US-based listener panel
- Attention signals recorded with every judgement
- Live results streaming as listeners answer
- Detection template for AI vs human narration
- Published methodology and platform transparency
| - 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
|
|---|
| What makes it different | - Publishes its own listening studies on the same platform with the same methodology as customer studies
- Forced-choice preference testing answers which system people prefer, not rating scales
- Fast turnaround with live result streaming and no minimum study size
- Transparent pricing with no setup fees or minimums, quoted before starting
- Customer audio stored securely and used only for that study
| - 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
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 8 ● no change since last check | 2 ● no change since last check |
|---|
| Trust Flow (Majestic) | 9 | 1 |
|---|
| Citation Flow (Majestic) | 24 | 23 |
|---|
| Referring domains (Majestic) | 69 | 14 |
|---|
Woodstitch
DidWork