Realtime AI News
Legora launches Skills, letting legal teams teach its AI agent how they work
Legal-AI company Legora has launched Skills, a feature that gives its AI agent pre-built and custom instructions. Skills lets legal teams encode their own standards, processes and preferences into the Legora agent so it works the way the team already does.
Legal-AI company Legora is turning "make the AI work your way" into a product feature. As reported by Law.com, Legora has launched Skills, which gives its AI agent pre-built and custom instructions.
Legora's own product update frames it plainly: "Teach the Agent how you work." Skills, it says, let legal teams encode their standards, processes and preferences inside the Legora aOS — the company's "agentic operating system for legal work."
The Legora agent is designed to take on end-to-end execution of complex legal work: it plans, executes, reviews and delivers, leaving the decisions that require judgment to the lawyer. Skills gives that execution a basis, determining which of a firm's or legal department's established practices the agent should follow.
Pre-built skills let a team adopt a ready-made set of practices out of the box, while custom instructions let it write in its own templates, phrasing and review standards. That addresses a familiar complaint about general-purpose AI tools in law: they can be impressive yet still "don't know us," producing output that needs heavy rework.
The move fits the direction of the legal-AI market, where the competitive question has shifted from "can the model get the answer right?" to "can the workflow be trusted and customized?" For law firms and in-house teams, being able to bake internal standards into a tool often matters more than any single impressive answer.
Legora is also hosting an "Introducing Skills" webinar on Oct. 14, focused on how law firms and in-house legal teams can teach the Legora Agent their standards, processes and preferences — a sign that Skills is not just a routine feature update but a headline pitch to customers.
More broadly, writing instructions for AI agents is becoming a common pattern across enterprise software. It lowers the barrier to wiring AI into real work, and it makes "who owns the team's best practices" a new kind of product moat. What to watch next is how stable Skills proves on real legal documents and cross-border matters, and whether the same approach spreads to other regulated industries.
Why it matters
By letting legal teams encode their standards and processes into the agent, Legora makes AI more usable in a field where trust and confidentiality are paramount. If customizable instructions become standard, competition in legal AI will shift from raw model quality to workflow and trust.
Nearby Updates
All10/07, 04:35
Musubi launches PolicyLM-1.7B, an open-weights model built for real-time content moderation
On Tuesday, AI company Musubi released PolicyLM-1.7B, a lightweight decision model designed for real-time content moderation and shipped with open weights. It applies a plain-English content policy to messages in under 50 milliseconds and, crucially, does not need retraining when the policy changes.
10/07, 04:03
OpenAI and Anthropic face rising price pressure from big AI users
OpenAI and Anthropic are facing rising price pressure from their large AI customers, according to a Bloomberg report. The story points to shifting bargaining power at the top of the model market.
10/07, 04:02
Meta and partners launch an open standard for AI agent authentication
Meta is launching an open standard for AI agent authentication together with a group of partners, according to a report by Quartz. The effort targets the identity and permission layer that autonomous agents rely on, rather than a single product release.
10/07, 04:00
Lambda to raise up to $4B ahead of planned 2027 IPO
AI computing startup Lambda is preparing to raise up to $4 billion at a $14.5 billion pre-money valuation, according to TechCrunch. The Nvidia-backed company is doing so ahead of a planned 2027 IPO, with Coatue and Blackstone leading the round.