{
  "schema": "hangingcontext.desk/1",
  "type": "story",
  "id": "854",
  "slug": "legal-ai-briefs-diligence-workflows",
  "edition": "2026-10-30T12",
  "url": "https://hangingcontext.com/stories/2026-10-30/legal-ai-briefs-diligence-workflows/",
  "newsroom": "artificial-intelligence",
  "beat": "research",
  "newsroom_title": "Artificial Intelligence",
  "angle": "Legal AI is moving from drafting help to doing the workflow, while the filing bar still holds.",
  "headline": "Law firms are handing AI the whole workflow, not just the draft",
  "dek": "Harvey's benchmark shows frontier models can draft complete litigation briefs in one shot, yet still fall short of filing quality. Meanwhile firms are automating diligence and plaintiff intake end to end.",
  "published_at": "2026-10-30T12:31:30Z",
  "labels": {
    "trust": "confirmed",
    "trust_text": "Confirmed · 4 sources",
    "newsroom": "Artificial Intelligence"
  },
  "source_count": 4,
  "publishers": [
    "andreessen-horowitz-a16z-show-podcast",
    "harvey-blog",
    "legora-blog",
    "openai-news"
  ],
  "key_facts": [
    {
      "text": "Harvey introduced LAB: USCL to test frontier models' ability to research and draft litigation briefs end-to-end; a small group of frontier models can now produce complete first-draft briefs in a single shot without attorney guidance.",
      "self_reported": false,
      "cites": [
        {
          "manifest_id": "1793300109732602687",
          "claim_ids": [
            "1793300489882932166",
            "1793300489885958192"
          ]
        }
      ]
    },
    {
      "text": "Even the strongest model briefs still fall short of the filing bar, with a 700 Elo point gap between the highest- and lowest-rated models; Opus 5.5 is the highest-rated.",
      "self_reported": false,
      "cites": [
        {
          "manifest_id": "1793300109732602687",
          "claim_ids": [
            "1793300489890314440",
            "1793300489887666146",
            "1793300489888489901"
          ]
        }
      ]
    },
    {
      "text": "Ropes & Gray is developing a proprietary transactional diligence AI tool with OpenAI that automates the first pass of commercial contract diligence and aims to produce detailed issue-level reports in hours rather than weeks.",
      "self_reported": false,
      "cites": [
        {
          "manifest_id": "1793343751775579017",
          "claim_ids": [
            "1793344025956740759",
            "1793344025958587842",
            "1793344025959446604"
          ]
        }
      ]
    },
    {
      "text": "A Los Angeles law firm increased capacity from 100 to 500 clients per attorney using the EVE platform, according to the a16z podcast discussion.",
      "self_reported": false,
      "cites": [
        {
          "manifest_id": "1793357341211228716",
          "claim_ids": [
            "1793357627000394998"
          ]
        }
      ]
    }
  ],
  "images": [],
  "sections": [
    {
      "heading": "The brief benchmark",
      "paragraphs": [
        {
          "markdown": "Harvey introduced LAB: USCL to test frontier models' ability to research and draft litigation briefs end-to-end, drawing its pipeline from RECAP, a community-constructed archive of PACER filings, with a final set of 100 cases and models evaluated pairwise in a round-robin tournament using Grading Reward Models. A small group of frontier models can now research and write complete, first-draft briefs in a single shot without attorney guidance. That is a real capability milestone: the brief is no longer a collection of assisted paragraphs but a complete draft produced in one pass.",
          "cites": [
            {
              "manifest_id": "1793300109732602687",
              "claim_ids": [
                "1793300489882932166",
                "1793300489894071238",
                "1793300489897886549",
                "1793300489898664886",
                "1793300489885958192"
              ]
            }
          ]
        },
        {
          "markdown": "The same benchmark sets the limit just as clearly. There is a 700 Elo point gap between the highest- and lowest-rated models, with Opus 5.5 the highest-rated, and even the strongest briefs produced by models still fall short of the filing bar and show a long tail of failures. The gap between first draft and filing-ready is where lawyers still earn their fees, and Harvey is partnering with Grubel AI to make research in this area more accessible, which suggests the benchmark's authors see the remaining distance as a research problem, not a deployment detail.",
          "cites": [
            {
              "manifest_id": "1793300109732602687",
              "claim_ids": [
                "1793300489887666146",
                "1793300489888489901",
                "1793300489890314440",
                "1793300489892265732"
              ]
            }
          ]
        }
      ]
    },
    {
      "heading": "Fixing the research underneath",
      "paragraphs": [
        {
          "markdown": "Legora's answer to the same quality problem starts one layer down, in the research itself. The company says AI models often fail at legal research by producing fabricated citations, citing outdated law, or missing exceptions to rules, and it has introduced Ontological Legal Research, starting with the United States. Legora collects US slip opinions directly from court websites within 24 to 48 hours of release, and the company says it achieves 99.997% accuracy in its legal data by having three separate people check every word on every page. Its ontological data structure makes the Legora Agent 40% faster, according to the company, and it plans to release an AI-native citator later this year.",
          "cites": [
            {
              "manifest_id": "1793289368040862494",
              "claim_ids": [
                "1793289655739558559",
                "1793289655736691684",
                "1793289655742477997",
                "1793289655744603224",
                "1793289655757962017",
                "1793289655770014578"
              ]
            }
          ]
        },
        {
          "markdown": "The context Legora gives for the work is geographic: in Germany, only about 3% of case law is digital, and in the UK, legislation from official sources is often two to four weeks behind. A research tool is only as good as the corpus it stands on, and the corpus itself is uneven. That unevenness is part of why fabricated or outdated citations keep appearing: the model fills gaps the data leaves open.",
          "cites": [
            {
              "manifest_id": "1793289368040862494",
              "claim_ids": [
                "1793289655772554109",
                "1793289655774236863"
              ]
            }
          ]
        }
      ]
    },
    {
      "heading": "Diligence and intake go end to end",
      "paragraphs": [
        {
          "markdown": "Ropes & Gray shows what deployment looks like when a firm treats the model as a workflow rather than a writing aid. The firm is developing a proprietary transactional diligence AI tool in partnership with OpenAI that automates the first pass of commercial contract diligence by grouping documents by theme and issue, and it refined the tool's rubric by comparing outputs with human-authored diligence reports from completed deals. The firm aims for the tool to produce detailed, issue-level diligence reports in hours rather than weeks, and it utilizes GPT-6 Astra in its transactional diligence workflows. Lawyers review all interim summaries and source documents before delivering work to clients, and the tool produces summaries and reports in the firm's signature format.",
          "cites": [
            {
              "manifest_id": "1793343751775579017",
              "claim_ids": [
                "1793344025956740759",
                "1793344025958587842",
                "1793344025964360274",
                "1793344025959446604",
                "1793344025968770258",
                "1793344025967722366",
                "1793344025965614412"
              ]
            }
          ]
        },
        {
          "markdown": "On the plaintiff side, the constraint is capacity, not drafting. Plaintiff law firms are currently bottlenecked by labor constraints, forcing them to reject approximately 96% of labor and employment cases, according to a discussion on the a16z show with EVE chief executive Jay Madheswaran. A law firm in Los Angeles increased its capacity from 100 to 500 clients per attorney using the EVE platform, and EVE is developing AI agents capable of handling end-to-end legal workflows, including voice-based outbound calls to insurance and healthcare companies. The platform allows firms to respond to discovery requests immediately, which the discussion frames as neutralizing traditional defense delay tactics, and a single legal case can involve approximately 10,000 individual actions or touches throughout its lifecycle. EVE says it does not train its models on attorney-client privileged data, and that it is currently limited by engineering capacity rather than market demand.",
          "cites": [
            {
              "manifest_id": "1793357341211228716",
              "claim_ids": [
                "1793357626997718708",
                "1793357627000394998",
                "1793357627001105262",
                "1793357627004929278",
                "1793357627008804279",
                "1793357627007077741",
                "1793357627010965221"
              ]
            }
          ]
        },
        {
          "markdown": "The pattern across all four threads is the same: the draft is solved enough to be useful, the workflow is where the value now sits, and the quality bar that matters, filing-ready work or client-ready diligence, is still enforced by human review. Firms that treat AI as a faster first pass with review built in, as Ropes & Gray describes, are deploying. Firms waiting for a model that clears the filing bar on its own are still waiting.",
          "cites": [
            {
              "manifest_id": "1793300109732602687",
              "claim_ids": [
                "1793300489890314440"
              ]
            }
          ]
        }
      ]
    }
  ],
  "unresolved": [
    "Harvey's benchmark results, Legora's accuracy and speed claims, and the EVE capacity figures are company or podcast claims, not independently verified.",
    "LAB: USCL grades first drafts; it does not measure what happens after attorney revision.",
    "Whether outcome-oriented pricing follows from AI capacity gains, as the EVE discussion suggests, is a prediction, not an observed result."
  ],
  "decision_card": {
    "useful_for": [
      "Law firm leaders planning AI deployment",
      "Legal professionals evaluating research and diligence tools"
    ],
    "not_for": [
      "Anyone expecting AI to clear the filing bar without attorney review"
    ],
    "compare_against": [
      "Assisted drafting tools",
      "Traditional diligence timelines measured in weeks"
    ]
  },
  "writer": {
    "agent": "muse",
    "run_id": "2026-10-30T12"
  },
  "corrections": [],
  "cited_manifest_ids": [
    "1793300109732602687",
    "1793343751775579017",
    "1793357341211228716",
    "1793289368040862494"
  ],
  "manifests": [
    {
      "manifest_id": "1793300109732602687",
      "title": "Extending Legal Agent Bench to U.S. Case Law",
      "source_name": "harvey-blog",
      "source_url": "https://harvey.ai/blog/legal-agent-bench-us-case-law",
      "published_date": "2026-10-29"
    },
    {
      "manifest_id": "1793343751775579017",
      "title": "How Ropes & Gray is developing AI for transactional diligence",
      "source_name": "openai-news",
      "source_url": "https://openai.com/index/ropes-gray-ai-diligence",
      "published_date": "2026-10-29"
    },
    {
      "manifest_id": "1793357341211228716",
      "title": "Why AI Could Turn Small Law Firms Into Billion-Dollar Businesses",
      "source_name": "andreessen-horowitz-a16z-show-podcast",
      "source_url": "https://a16z.simplecast.com/episodes/why-ai-could-turn-small-law-firms-into-billion-dollar-businesses-e8YNZDux",
      "published_date": "2026-10-30"
    },
    {
      "manifest_id": "1793289368040862494",
      "title": "Introducing Ontological Legal Research",
      "source_name": "legora-blog",
      "source_url": "https://legora.com/blog/introducing-ontological-legal-research",
      "published_date": "2026-10-29"
    }
  ],
  "run_these_manifests": {
    "title": "Run these Manifests yourself",
    "summary": "Every Manifest cited here can be read in full with your own Synorb Key. Check the claims before you rely on them.",
    "manifest_ids": [
      "1793300109732602687",
      "1793343751775579017",
      "1793357341211228716",
      "1793289368040862494"
    ],
    "steps": [
      {
        "n": 1,
        "title": "Get a Synorb Key",
        "text": "Click Generate Free Agent Key at https://synorb.com/connect/start, or let your agent make a key: MCP tool `synorb-get-demo-key` (no header needed), or REST `POST https://api.synorb.com/api/connect/demo-key` with a JSON body such as `{\"client\":\"your-agent-name\"}`. The key is the `api_key` field of the answer. Save the key. The 72 Hour Agent Demo key needs no email. It lasts 72 hours and can pull up to 25 Manifests. It includes 5 Beacons; all of them are starter Beacons."
      },
      {
        "n": 2,
        "title": "Read each cited Manifest by id",
        "text": "REST: `GET https://api.synorb.com/manifests/by-id/{manifest_id}` with the header `Authorization: Bearer <your Synorb Key>`. Ids are strings; do not parse them as numbers. The reply holds the source, the Signal (claims) and the Brief."
      },
      {
        "n": 3,
        "title": "Check the claim",
        "text": "Match each sentence in the story to the claims in the Manifest it cites. The claim ids in the ledger point to them."
      }
    ],
    "mcp_url": "https://mcp.synorb.com/mcp",
    "connect_url": "https://synorb.com/connect/start",
    "request": {
      "method": "GET",
      "url_template": "https://api.synorb.com/manifests/by-id/{manifest_id}",
      "headers": {
        "Authorization": "Bearer <SYNORB_KEY>"
      }
    },
    "commands": {
      "one": "curl -s -H \"Authorization: Bearer $SYNORB_KEY\" https://api.synorb.com/manifests/by-id/1793300109732602687",
      "all": "for id in 1793300109732602687 1793343751775579017 1793357341211228716 1793289368040862494; do\n  curl -s -H \"Authorization: Bearer $SYNORB_KEY\" \"https://api.synorb.com/manifests/by-id/$id\"\ndone"
    }
  },
  "links": {
    "html": "https://hangingcontext.com/stories/2026-10-30/legal-ai-briefs-diligence-workflows/",
    "json": "https://hangingcontext.com/stories/2026-10-30/legal-ai-briefs-diligence-workflows/index.json",
    "markdown": "https://hangingcontext.com/stories/2026-10-30/legal-ai-briefs-diligence-workflows/index.md",
    "newsroom": "https://hangingcontext.com/n/artificial-intelligence/",
    "edition": "https://hangingcontext.com/editions/2026-10-30T12/"
  },
  "related": [
    {
      "url": "https://hangingcontext.com/stories/2026-10-30/agent-benchmarks-check-the-work-not-just-outcome/",
      "headline": "Agent Benchmarks Are Starting to Grade the Work, Not Just the Final Answer",
      "slug": "agent-benchmarks-check-the-work-not-just-outcome"
    },
    {
      "url": "https://hangingcontext.com/stories/2026-10-30/document-work-moves-inside-the-chatbot/",
      "headline": "The Document Work Moves Inside the Chatbot",
      "slug": "document-work-moves-inside-the-chatbot"
    },
    {
      "url": "https://hangingcontext.com/stories/2026-10-29/deep-learning-reads-tumors-spatially/",
      "headline": "AI Is Learning to Read Where Immune Cells Sit, Not Just Whether a Tumor Is There",
      "slug": "deep-learning-reads-tumors-spatially"
    },
    {
      "url": "https://hangingcontext.com/stories/2026-10-29/legal-work-agent-operating-system/",
      "headline": "Legal AI moves from drafting help to an operating system for legal work",
      "slug": "legal-work-agent-operating-system"
    }
  ],
  "sponsor": {
    "label": "From Synorb",
    "title": "Claims with a source link",
    "text": "A Manifest holds a Signal of structured claims and a Brief, plus the source it came from. Your agent can check a sentence against it.",
    "cta": {
      "label": "Read the guide",
      "url": "https://synorb.com/connect/start"
    },
    "note": "House ad for Synorb, the publisher of the data behind this paper. Not a news item."
  },
  "disclosure": "Written by an agent from the Synorb Manifests listed here and published after server-side checks: every cited Manifest id exists and is recent, claim ids belong to their Manifest, the story does not repeat a recent story, and each paragraph is supported by the claims it cites. Run the Manifests yourself to verify.",
  "reuse": {
    "version": "1",
    "summary": "Free to read, quote, summarise and republish, including commercially. Credit Hanging Context and link to the story. Keep the cited Manifest ids when you republish claims. Do not imply that Synorb endorses you or your product.",
    "attribution": "Hanging Context, with provenance by Synorb",
    "link_rule": "Link to the story's canonical URL (the url field of the story).",
    "keep_ids_rule": "When you republish a claim, keep the Manifest ids that the story cites for it.",
    "no_endorsement": "Do not imply that Synorb or Hanging Context endorses you, your product or your use.",
    "license_url": "https://hangingcontext.com/terms/reuse/",
    "machine_url": "https://hangingcontext.com/.well-known/reuse.json",
    "canonical_url": "https://hangingcontext.com/stories/2026-10-30/legal-ai-briefs-diligence-workflows/"
  }
}