| What it does | Self-Improving Defense platform that protects from AI attacks
| Catch where AI agents get stuck on your API or MCP server, rank problems by impact, and draft fixes as pull requests
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | 2022
| Not given
|
|---|
| Based in | US
| US
|
|---|
| Pricing model | Contact for pricing
| Freemium
|
|---|
| Pricing | Not given
| Open source: free. Team: $199/month with 14-day free trial (1 API or MCP service, 25,000 reports/month, 15 coding-agent runs/month). Business: $799/month (up to 3 services, 250,000 reports/month, 60 coding-agent runs/month). Extra coding-agent runs: $6 each.
|
|---|
| Key features | - Acts directly in EDR, cloud, Active Directory, and SIEM
- Investigates every alert to a verdict with reasoning, not playbooks
- AI SOC Agent for automated alert triage and response
- AI Threat Hunt Agent for hypothesis-driven threat detection
- AI Pentest Agent for continuous, on-demand offensive testing
- AI NetSecOps Agent for firewall and network operations
- Context Lake for organization-wide persistent memory of assets and verdicts
- Multi-tenant isolation with per-tenant reasoning for MSSPs
- Hardened against prompt injection and data poisoning
| - Session replay for MCP servers to identify failed agent sessions
- Clustering reports by agent goals and workflows
- Priority ranking weighted by frequency, failed workflows, and affected accounts
- Claude Code generates pull requests with tests
- Review queue with diff, tests, agent reports, and evidence
- Isolated git worktree prevents unauthorized code push
- Schema validation and rate limiting for feedback
- Open Agent Feedback Protocol with TypeScript and Python SDKs
- GitHub integration for draft PR creation
|
|---|
| What makes it different | - Responds to every alert in under 4 minutes on average
- 95% of proposed actions approved by your own analysts
- Self-improves by learning from analyst corrections
- Onboards tenants in hours, not months
| - Only AI agent failures on successful HTTP responses get detected and ranked
- Automated pull request drafts with your approval required before shipping
- Session replay captures failures even when agents don't report them
- Pay only for coding-agent runs, not feedback submission
- Open protocol and SDKs can be self-hosted at no cost
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 44 ● no change since last check | 1 ● no change since last check |
|---|
| Trust Flow (Majestic) | 17 | 1 |
|---|
| Citation Flow (Majestic) | 36 | 14 |
|---|
| Referring domains (Majestic) | 356 | 4 |
|---|
Simbian®
Backloop