Trellis, a legal research company specialising in U.S. state trial court data, has significantly expanded its artificial intelligence capabilities across multiple platforms.
The company has launched a new plugin for OpenAI’s ChatGPT and a native assistant called Trellis Chat, building on its existing connector for Anthropic’s Claude.
Trellis launched its Model Context Protocol connector for Claude in May, making the latest ChatGPT and Trellis Chat additions a rapid extension of its agentic AI strategy.
The company claims to hold the largest set of U.S. state trial court data available, with more than 2.5 billion records spanning more than 3,500 courts across 2,500 counties in 45 states.
The integrations are designed to let litigators query that vast dataset directly from inside the AI tools they already use on a daily basis.
Attorneys can pose research questions in Claude or ChatGPT, with the connectors pulling in relevant filings, rulings, verdicts, and judicial data rather than relying on a model’s general training knowledge.
Rather than returning a single answer, the connectors allow users to describe a research goal and have the system plan a strategy, search records, cross-reference results, and verify citations before responding.
Trellis describes one use case involving an Am Law 100 partner asking Claude to find factually similar California premises-liability cases involving large retailers and alleged notice of a spill hazard, with the system producing a memorandum including charts, factual analogues, comparable verdicts, and citations to underlying dockets.
Nicole Clark, a former litigator and the company’s cofounder and CEO, explained the core distinction the platform is trying to draw between conventional AI responses and grounded legal research.
“There is a real difference between a model that guesses at an answer from general memory and a system that does the research,” Clark said, adding that “combining agentic research with the nation’s largest state trial court dataset gives litigators a new superpower.”
Among the research tasks the connectors are built to handle, Trellis highlights pulling a judge’s ruling rates on summary judgment motions and comparing them against the county average.
Additional capabilities include checking an opposing attorney’s win rate and preferred motions in a particular county, as well as mapping a company’s full litigation history as a defendant.
Users can also profile expert witnesses and their testimony records, or compare summary judgment outcomes across venues to assess which county favours a given side.
Trellis now offers customers four distinct routes to access its data, beginning with its core platform housing judge analytics, attorney analysis, case-strategy reports, and alerts.
The other access points include Trellis Chat for fast answers to complex research questions, the AI connectors for ChatGPT, Claude, and other tools, and a direct API for pulling records into a firm’s own systems.
The company says the Claude and ChatGPT connectors are the first in a planned series of integrations that will extend agentic access to its trial court data across the tools attorneys already rely on professionally.