Skip to content
EdgeLex

Lex AI & Agents

A legal AI that works inside your firm's data — and only acts when you say so.

The problem

Cloud legal AI answers from a model you can't see, trained on data you can't audit, with no proof of where an answer came from. For work that is malpractice-adjacent, that's not good enough.

Capabilities

What it does

Grounded conversational AI

Multi-turn chat that answers from your matters, documents, emails, and court rules, with streaming responses and cited sources. Answers that can't be grounded are blocked rather than guessed.

Matter-aware

Scope a conversation to a matter and Lex pulls that matter's documents, tasks, deadlines, notes, and communications into context.

Governed AI agents

Configurable agent profiles with explicit, whitelisted actions. Agents can be triggered by schedule, incoming email, overdue tasks, or approaching deadlines.

Approval-gated actions

High-impact actions — send email, save a document, complete a court-mandated task — require explicit human approval. The AI proposes; you approve.

Action toolset

Across email, tasks, calendar, and documents: search a mailbox, reconstruct a thread, draft a reply, create or update tasks, extract a deadline from an email, propose a document save. Read actions run freely; write actions are governed.

Model choice & routing

The firm picks local or frontier models. An internal router scores models per task and refuses to let underpowered models perform destructive actions.

Governed memory

Lex can remember a user's preferences and facts under a scope-safe contract. Memory is context, never used as legal authority.

In your control

Three-layer model governance (platform / firm / user) with default-deny, full token-and-cost attribution per user, matter, and model, and tool allowlists per agent.

See EdgeLex on your own terms.

We'll walk through self-hosting, model control, and your firm's workflows.