Proof of what an AI agent was allowed to do, and what it then did
Stage
Not given
Startup
Founded
2022
2026
Based in
US
Not given
Pricing model
Paid
Open source
Pricing
Annual subscription starting at $36,000/year per AI SOC Analyst, which includes up to 4,000 investigations per year, unlimited users, 80+ integrations, and threat intelligence. Enterprise and MSSP custom pricing available.
Not given
Key features
Alert investigation across SIEM, EDR, cloud, and identity tools
Autonomous threat hunting with hypothesis-driven searches
Integration with 90+ security tools via API
24/7 continuous security operations
Threat intelligence feeds and enrichment
Decision-ready investigation reports with evidence
Custom workflow configuration for enterprise organizations
Multiple hunt types including emerging threats and ATT&CK techniques
EU data residency option
Signed permissions with passkey authentication
Receipts for each agent action with signatures
Free checker tool to verify compliance
Quantum-safe signatures (Ed25519 and ML-DSA-87)
Permission narrowing for helper agents
Permission cancellation with signed acknowledgement
JavaScript and Python libraries
LangChain and Pydantic AI middleware
What makes it different
5x faster mean time to response (MTTR)
85% reduction in manual alert investigation effort
Maintains continuous 24/7 SOC coverage without team scaling
Transparent, auditable AI investigations with glass-box reasoning
Operates in closed loop with multiple AI agents without human prompting
Only open-source project combining machine-checkable limits, permission narrowing for helpers, and signed permission cancellation
Built entirely from published standards with no hand-made components
Free and no dependencies, sends nothing anywhere or holds money
Distinguishes between record integrity and whether agent stayed within permission
All published versions stay available for backward compatibility
Dropzone AI
Provared