| What it does | Human-in-the-loop approval for AI agents
| The credential layer for AI agents
|
|---|
| Stage | Not given
| Startup
|
|---|
| Founded | Not given
| 2026
|
|---|
| Based in | Not given
| ES
|
|---|
| Pricing model | Free
| Freemium
|
|---|
| Pricing | Free forever with all features included
| Free: 1 agent, 30 runs/month, public scoring only. Pro: unlimited agents, 1,000 runs/month, private runs, $120/year or $12/month. Team: unlimited agents, 5,000 runs/month, 5 seats, $261/year or $29/month. Enterprise: 25,000 pooled runs/month, SSO, SCIM, from $499/month billed annually.
|
|---|
| Key features | - Alerts on iPhone and Android with answer buttons
- Phone call escalation for high and critical alerts
- Breaks through silent mode and Do Not Disturb
- Attachments and notes on every alert
- Broadcast to a channel with one person taking ownership
- See who acted and who ignored alerts
- Answer buttons set by you or your AI
- Callback webhooks to return answers to your code
- Setup via pasted prompt or API key-free send link
- Integration with AI frameworks, automation platforms and HTTP API
| - Standardised work sample testing with composite scoring (40% success, 30% latency, 30% cost)
- Five-axis diagnostic radar (correctness, latency, cost, tool efficiency, robustness)
- Ed25519-signed certificates with public key verification
- Hiring Frontier cost-per-task analysis across model candidates
- Embedded badge rendering for README files
- Private screening (Pro plan and above)
- Team workspaces with up to 5 seats
- CSV and PDF export
- API access with rate limits
|
|---|
| What makes it different | - Full-volume alerts that interrupt even when phone is silenced
- No SDK, API key or card required to start
- Free forever with every feature for every team member
- Escalates to phone calls for critical alerts that go unanswered
- Works with existing AI agents, workflows and monitoring tools
| - Standardised testing ensures scores are comparable, not self-reported
- Free forever for public scoring with no credit card required
- Model-agnostic testing works with any LLM provider
- Screening completes in under 5 minutes
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 73 ● no change since last check | 1 ● no change since last check |
|---|
| Trust Flow (Majestic) | 1 | 0 |
|---|
| Citation Flow (Majestic) | 1 | 19 |
|---|
| Referring domains (Majestic) | 0 | 10 |
|---|
M91
badgeIA