From 12 Plugins to 90+ Claude Legal AI Agents
Claude legal AI agents are named, task-focused AI workflows that run end-to-end legal tasks like contract review, due diligence, and litigation support, and they can be tuned in plain language to match a firm’s specific practices and tools. When the Claude for Legal platform formally launched, attention centered on its 12 main plugins and MCP connectors into existing legal tech tools. Since then, the ecosystem has expanded dramatically: there are now more than 90 agents available on Anthropic’s GitHub. Anthropic describes these as job-style agents such as Vendor Agreement Reviewer, DSAR Responder, Termination Reviewer, and Claim Chart Builder, each triggered with a single command. This shift from a handful of generic capabilities to dozens of granular agents marks a move toward legal workflow automation that mirrors how lawyers actually work, with targeted helpers for narrow tasks instead of one broad, catch-all feature.
Enterprise Law Firm AI Adoption: Hanson Bridgett Goes Firm-Wide
Law firm AI adoption is moving from pilots to institutional deployment, with Hanson Bridgett’s move a notable example. The approximately 200-lawyer firm has gone “all-in” on Claude, rolling out the general model plus legal add-ons firm-wide for attorneys and professional staff. According to Hanson Bridgett’s chief operating and financial officer Laura Long, this is about building long-term capability and helping people adapt thoughtfully as AI tools evolve. The firm uses Claude for daily work ranging from document review and drafting to research, organization, and internal operations. Typical tasks include summarizing deposition testimony and lengthy records, drafting routine correspondence and memos, comparing document versions, and supporting due diligence in corporate transactions. Professional staff in operations, marketing, HR, finance, and knowledge management are also in scope, showing how the Claude for Legal platform is permeating both legal and business support workflows.
Beyond Point Solutions: Integrating Agents Into the Legal Tech Stack
The Claude for Legal platform is designed to sit alongside, not replace, existing legal technology. Its MCP connectors let Claude legal AI agents talk to legal databases, document management systems, and other tools already in a firm’s stack. This enables agents to run “always-on” workflows over incoming documents, emails, or matter streams, such as weekly sweeps of signed agreements to flag deviations from playbooks. Anthropic’s legal team stresses that the Opus 4.8 model and its plugins are built with explicit safeguards: source attribution on citations, jurisdiction captured during an onboarding interview, and hard stops before anything is filed or sent so lawyers can review outputs. The goal is to make review easier, not to skip it. In practice, firms can use agents to automate narrow workflows while keeping human sign-off, integrating AI into existing governance rather than bolting on yet another point solution.
Granular, Composable Agents vs Monolithic AI Platforms
The proliferation of more than 90 Claude legal AI agents signals a shift away from monolithic AI platforms toward specialized, composable tools. Instead of a single “contract review” button, lawyers can pick and tune agents that match specific workflows, then adapt their practice profiles and connectors in natural language. This granularity increases usefulness and accuracy because each agent is scoped to a narrow task, and many can be set to run continuously over defined data streams. Comparable custom workflows can be built with other legal tech platforms, but Claude offers a direct interface with a major language model that legal teams can shape without heavy engineering. Some engineering skill still helps with enterprise integration, yet the barrier to entry is lower. Together, the expanding agent catalog and early enterprise deployments point toward a future where firms assemble tailored AI workflows from many small agents instead of relying on one all-encompassing system.
