The systems inside Litco.
Litco built the platform around per-matter memory, citation verification, a sealed drafting sandbox, an architecture for long autonomous work, per-firm deployment with per-matter keys, and public measurement of the models behind the platform.
Matter memory
The Matter Agent keeps a durable memory per matter. It records observations as it works, consolidates them overnight, and starts the next session already knowing the case. It learns the firm’s drafting voice from attorney edits. Litco never uses documents or data from your matter to train a model.
How Litco verifies citations
Litco runs software checks on the Matter Agent’s output, from byte-level quote comparison to independent confirmation of negative treatment. Details →
The drafting sandbox
When the Matter Agent writes a document, Litco runs the drafting code in a sandbox with no network access. Nothing leaves the sandbox until the document’s quotations pass verification.
Reliable without babysitting
The Matter Agent works toward the goal you set, one step at a time. After each step, Litco checks whether the Matter Agent should continue, finish, or pass the work to a person for review. The Matter Agent survives restarts, waits for your approvals, and delivers whatever work it has completed.
Deployment
Each firm runs on its own instance, and each matter carries its own encryption key. Firms choose, per matter, whether the Matter Agent operates on cloud models under zero-retention terms or on Litco’s own hardware.
Measurement
Litco benchmarks every model the system uses across the production pipeline, publishes every result, and routes work to the model that scored highest. LitigationBench →