Agentic investigation workspace for professionals working with large document collections
Make AI decisions inspectable
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Not given
Not given
Pricing
Free with pay-as-you-go option. Pro plan: $49/month with 20 credits. Team plan: $99 per user per month with 20 credits per user. Enterprise: Custom pricing.
Community: Free (open artifacts, self-serve). Team: $2,500 per month (launch pricing). Governed Evidence Pilot: $15,000 flat for 30 days (launch pricing). Enterprise: Custom annual contract with own hardware. Per-call API: $0.02 USDC for OpenAI-compatible chat and completions, $0.05 USDC for mesh an
Key features
1 billion context window to analyze very large document sets
Complete-record analysis without retrieval blind spots
Shared data room for team collaboration and investigation
Agent-native artifacts for reports, spreadsheets, and presentations
Exact-page citations linking findings to source documents
Preserve and display conflicting information from sources
Zero document retention for temporary tasks
HIPAA-ready workflows for healthcare investigations
Policy gates before AI agent actions
Signed hash-chained receipt ledger
Offline verification capability
Evidence synthesis through Second Brain
Mapped controls for ISO/IEC 42001, EU AI Act and NIST AI RMF
Air-gap deployment on own hardware
Hardware-key signing with user's own keys
Evidence-plane sidecar for agent stacks
Auditor export bundle
Open receipt specification and format
What makes it different
Complete-record reasoning across all uploaded files rather than retrieval-based Q&A with blind spots
Professional-grade evidence standards with citations preserved through investigation
Zero document retention and no use of customer data for AI model training
Persistent Projects for recurring investigations of the same documents
Flexible investigation criteria to control what to find and how to present results
Every decision sealed into verifiable offline receipts
Eight core formulas proven in Lean 4
Explicit labeling of claims as declared, simulated or roadmap
No hidden paywall metrics—usage counted in signed receipts you verify