Descrybe changelog

Descrybe released its Legal Engine plugin for ChatGPT Enterprise. The company says it gives ChatGPT users structured, verifiable US primary law and legal intelligence built for AI.

Buyer relevance. OpenAI launched its own legal search index the same day, so Descrybe is now selling primary law into an assistant that has one built in. The comparison worth running is coverage and citation accuracy on the buyer's own research questions, not the claims in either release.

Descrybe published a security page stating its data handling position: customer prompts, files and conversational history are not used to train Descrybe owned models; the primary model provider is OpenAI's API, with Descrybe opted out of training and OpenAI abuse monitoring logs retained up to 30 days; uploaded files are discarded once text is extracted; research history can be deleted by the user at any time, with no zero retention mode offered; data is stored on DigitalOcean in the New York region on multi tenant infrastructure, encrypted in transit and at rest; the product runs on individual user accounts with no shared or matter based workspaces; and Descrybe holds no SOC 2 or ISO 27001 certification of its own, with SOC 2 work begun. Subprocessors are listed with links to each provider's attestation.

Buyer relevance. For a solo or small firm buyer this page answers the four questions a client's outside counsel guidelines will ask before the tool touches a matter: who processes the data, where it sits, whether it trains anything, and how it is deleted. It also says plainly what it lacks, no SOC 2 yet and no matter level walls, which is more useful than a badge, because a firm can plan around a stated limit and cannot plan around silence.

Descrybe published a coverage page enumerating its primary law corpus court by court: 492 courts and tribunals and 10,969,112 opinions as of 18 July 2026, across federal, state, bankruptcy, specialized and agency, and tribal courts, plus statutes, regulations, constitutions, session laws and court rules, with an opinion count and a first to most recent date range for every court. The vendor's earlier public figure was 3.6 million opinions across state supreme and appellate courts.

Buyer relevance. A per court date range is the thing a researcher checks before trusting a search for last month's appellate decision, and almost no vendor in this category publishes one. It also shows where coverage stops, which is worth more to a buyer than a headline total: a trial court whose opinions end in 2014 is a limit to plan around rather than one to discover in a brief.