Perplexity launched Computer for Counsel. It is an agentic AI system built for legal teams. The product extends Perplexity Computer, the company’s LLM-agnostic agentic system. It is available now to Perplexity Enterprise and Max subscribers.

Lawyers lose hours to administrative work. Computer for Counsel targets that work directly. Nearly 75% of lawyers call administrative tasks a major time challenge, a Thomson Reuters survey found. The story is mostly architectural. It is an orchestration layer wired into the tools lawyers already use.

TL;DR

• Perplexity launched Computer for Counsel on June 24, 2026, for Enterprise and Max subscribers.
• It routes 20+ frontier AI models per subtask, with no single-vendor lock-in.
• Premium sources include Midpage (case law + citator), Deel, and LegalZoom; 400+ tools connect via MCP.
• Every output links back to its source, so lawyers verify each citation before use.
• It is a workflow layer, not a Westlaw replacement; good-law checks still depend on Midpage.

What is Computer for Counsel?

It is not a new legal research database. Perplexity is explicitly not trying to replace Westlaw, LexisNexis, or Bloomberg Law. Instead, it sits as a research, drafting, and workflow layer. That layer reasons over the open web, firm systems, and specialized legal sources.

The mechanics are agentic. The system decomposes a legal task into subtasks. It routes each subtask to a model and a data source. It then assembles the results into a brief, memo, or deal summary. Every output links back to its source. Attorneys verify a citation in seconds before it enters client work. Judgment and strategy stay with the lawyer.

The Multi-Model Orchestration Layer

Computer is powered by 20+ frontier AI models. It selects the best model for each subtask automatically. Research, reasoning, and contract work can each use a different model. Perplexity keeps the model pool current through ongoing evaluation. For legal teams, this removes the pressure to bet on one AI vendor.

Connectors run on the Model Context Protocol (MCP). MCP is an open standard for linking AI systems to external tools and data. Administrators can also install custom MCP connectors for internal systems.

The Data Layer: Sources and Connectors

Premium legal sources ground the answers. The connector list spans research, contracts, and document management.

App Connectors also reach Microsoft 365, Google Workspace, and 400+ other tools. Inside Microsoft 365, Computer drafts in Word and retrieves files from SharePoint. It references context from Outlook or Teams conversations.

How Legal Teams are Using It

Three current workflows show the agentic pattern in practice:

• Third-party NDA intake: Computer reviews third-party NDAs for red flags. It fills in entity and signatory information. It prepares clean copies. It routes them for approval and signature via Docusign.
• Regulatory monitoring: Computer builds a shareable dashboard for US state privacy and adtech laws. It shows which states have laws in effect. It cites Midpage for relevant cases.
• Case research with citation review: Computer researches non-compete enforceability after the FTC’s 2024 ban. It summarizes key cases and flags unsettled ones. It exports a PDF with citations.

Interactive Explainer

For Developers: The Cited-Search Primitive

Computer for Counsel ships as a product, not an SDK. But it builds on Perplexity’s cited search. That primitive is exposed publicly through the Sonar API. The API is OpenAI-compatible and returns sources with every answer. Domain filters let you restrict grounding to trusted sites, the way a lawyer would.

# Perplexity's cited search primitive — the foundation Computer for Counsel builds on.
# This is the public Sonar API, not the Computer for Counsel product itself.
import os, requests

resp = requests.post(
    "https://api.perplexity.ai/chat/completions",
    headers={"Authorization": f"Bearer {os.environ['PERPLEXITY_API_KEY']}"},
    json={
        "model": "sonar-pro",
        "messages": [
            {"role": "user",
             "content": "Is a non-compete signed in California enforceable in 2026?"}
        ],
        # Restrict grounding to trusted sources, the way a lawyer would.
        "search_domain_filter": ["law.cornell.edu", "courtlistener.com", "ca.gov"],
    },
    timeout=60,
)
data = resp.json()
print(data["choices"][0]["message"]["content"])   # the answer
for url in data.get("citations", []):              # every source, for verification
    print("source:", url)

The pattern maps to the product. The model returns a grounded answer. The citations field returns the sources behind it. Computer for Counsel adds model routing, MCP connectors, and a review step on top. The lawyer still checks each cited claim before it ships.

How It Compares

Perplexity enters a crowded legal AI market. The positioning differs by design.

Perplexity is not trying to out-Westlaw Westlaw. It targets the work before, around, and after formal research. Multi-model routing is no longer unique; Harvey routes across vendors too. The real differentiator is reach into the open web and everyday firm tools.

Strengths and Limitations

Strengths

• Multi-model routing reduces lock-in to a single AI vendor.
• Every output links to a source for one-click verification.
• 400+ MCP connectors put it inside tools lawyers already use.
• Enterprise tier does not train on company data; connected files stay under firm control.
• Early enterprise traction: at Gunderson Dettmer, 80% of lawyers actively use Perplexity Enterprise, with 35,000+ queries a month.

Limitations

• It is not a standalone citator; good-law checks depend on Midpage coverage.
• Several connectors, including Clio and Ironclad, are still listed as coming soon.
• Lawyers must verify every citation; Perplexity faces unresolved data-sourcing lawsuits.
• Web grounding can miss paywalled or unpublished opinions.