Legal
Legal AI agent
Privilege protection, consent-bound access, dual sign-off on high-risk outputs.
What this package does
Guardrails for AI agents operating inside law firms and legal departments. Binds every AI action to a declared matter purpose, redacts PII before it enters logs or downstream tools, requires a senior reviewer to countersign high-risk outputs, and retains a tamper-proof log for the professional responsibility record.
Designed for
- Law firm AI research agents
- In-house legal operations tools
- Contract analysis and drafting platforms
What's included
- Consent-purpose binding: legal matter + client service
- PII masking before logs and downstream sinks
- Dual approval: senior partner countersign
- Immutable 7-year professional responsibility log
- HITL escalation on sensitive outputs
Controls in this bundle
Profile tiers
Switch profiles in Studio to retune default thresholds across the whole bundle without rewriting any control by hand. This package ships at strict — anything you've already tightened by hand is preserved on switch.
Every control in this package uses identical parameters across all four profiles. Switching profile in Studio has no effect here.
Attestation
The canonical hash of these bundle bytes is sha256:6b46aa00909d6441a0cc2e28382fc8873778bae081b3ef11dac4da170747b478. The same hash is computed at lock time, at Stripe checkout, and again on the runtime side before any byte is honored.
Want to customize first? Opening this package in Studio prefills the canvas with the 8 controls above. You can add, remove, or retune any of them before you lock the hash and pay.