LitKit · document review

Document review, end to end.

LitKit is Litco’s document review platform. Load a production, assign batches, code documents, and produce with Bates stamps and a privilege log, with the Matter Agent in the sidebar the whole time. Everything works the way reviewers expect from the review tools they use today.

The review grid on the demo matter with tags applied, and the Matter Agent summarizing the finished run in the sidebar
The review grid after a run, with tags applied and the Matter Agent summarizing the results. Captured from a live instance.

Review & Tag, the Matter Agent’s first pass.

Brief a review the way you would brief your reviewers, with criteria in plain English and tags mapped to your taxonomy. The model codes every document and records its rationale and the key quote for each call, so your team can spot-check any decision quickly.

A Review & Tag run in progress, recorded live. Each square is one document, and the squares turn green when tagged or amber when a finding needs a check. Recorded from a live instance.

Criteria in your words.

Each criterion is a short instruction, written the way you would write it for a person, and the run’s tags map to the taxonomy your reviewers already use.

The criteria step of the review wizard, with a criterion named Responsive and its instructions written in plain English
The wizard’s criteria step. Captured from a live instance.

Recall and precision.

When the run finishes, Litco draws a blind sample for your reviewers to code and reports recall and precision with confidence intervals—the same statistics courts have accepted for technology-assisted review since 2012. A deterministic sampling engine computes the numbers outside the model, and the record shows who decided every contested call.

The review run’s results panel: recall and precision with confidence intervals, and the blind sample your reviewers coded
The run’s results panel, with the blind sample your reviewers coded. Captured from a live instance.

Ask about the document you are reading.

Open a document and ask about the document: what the thread was about, who else received the attachment, whether anything else in the record contradicts what the witness wrote. The Matter Agent works from the record, pulls the related documents, and cites each one by Bates number.

The viewer and coding panel, with the Matter Agent citing related documents by Bates number. Captured from a live instance.

Code by voice.

Reviewers can code documents by voice—say “responsive,” “privileged,” or “next document” while reading, and the tags apply. The audio is transcribed on Litco’s own hardware and never stored.

The foot of the document viewer: the coding panel's tag buttons, with the voice review indicator listening
The foot of the viewer during voice review: the coding panel’s tag buttons, with the listening indicator active. Captured from a live instance.

Productions go out with Bates volumes, redactions, and load files, and Litco drafts the privilege log itself—an entry for every withheld document, with the privilege ground and a description written from the document and its metadata, ready for counsel to review before service.