Descrybe

AI Centrality

How much of the product is actually AI. Whether the machine learning is the mechanism the buyer is paying for or a feature layered onto conventional software, and whether the vendor is specific about which is which.

The corpus itself is a model output, which is as central as this axis goes. Every one of the 3.6 million judicial opinions in the product was summarised by AI, and that summarisation is not a feature layered over a database, it is how the database was built. On top of it sit DescrybeLM as a purpose built legal reasoning engine, Cytator as an AI driven citator producing issue level treatment analysis, and an engine layer exposing retrieval and verification tools to external assistants. Remove the models and there is no corpus, no citator and no product, only public domain opinions the company never had rights to sell. Third on this index at A, after Reveal and Jhana.ai.

Citation Accuracy and Hallucination Disclosure

Whether the vendor publishes measured accuracy on citations and assertions, grounds output to primary sources, and says plainly what its system does when it does not know. Legal has a documented public record of fabricated citations reaching filed briefs, so an untested claim of accuracy is not evidence.

The best structured grounding disclosure in this category and still short of a published measurement. DescrybeLM answers carry a table of authorities with citations linked back to the primary law, the reasoning is stated to be visible at every step, and the product includes quote verification and citation resolution as first class tools rather than as claims. The vendor also discloses against its own interest: the terms of service state plainly that Descrybe does not review or validate outputs to confirm they are accurate, truthful, relevant, reliable or not misleading, and earlier product material warned users not to assume summary accuracy without checking against the original opinion. A vendor telling a reader that its output is unverified is doing the opposite of overclaiming, and it is rare enough on this index to name. Held at B on two gaps. No measured accuracy figure of any kind is published by the vendor: no summarisation fidelity rate, no citation resolution accuracy, no hallucination rate, no test set. And a benchmark claim is circulating in third party material that DescrybeLM outperforms named frontier models on bar exam benchmarks, which was not located in vendor material with any methodology, evaluator or result table attached, and is therefore not credited here. Checked the home page, the FAQ, the user guide, the terms of service and the product pages on 29 Aug 2026.

Autonomy and Oversight Model

What the system decides on its own, what a lawyer must approve, and whether the vendor documents where the review point sits. A tool that drafts under review and a tool that files without one are different products and different risks.

Oversight is described as product behaviour rather than as policy, which is the useful form. DescrybeLM is documented to clarify jurisdiction, posture and key facts with the user before proceeding, which puts a human checkpoint at the start of the task rather than only at the end, and it is documented to tell the user when it needs more information and to flag uncertainty rather than filling gaps with guesses. Reasoning is visible at each step and work product is exported deliberately to Word rather than acted on. In the engine configuration the user can see which Descrybe tools an external assistant called and read the data each returned, which is oversight of a tool chain and not merely of an answer. Held at B because none of it is quantified or bounded: no statement of when the system proceeds without clarification, no confidence threshold, and no description of what the uncertainty flag actually triggers.

Operational and Outcome Evidence

Named, dated evidence that the product works in production at real firms or legal departments. Case studies with figures and identified customers count. Unattributed testimonials and launch announcements do not.

Adoption claims are institutional and specific, and none of them was located in vendor material. Third party research material states that Descrybe was added to the NSLT curriculum replacing Casetext, and selected as an approved NELLCO e-resource reaching nearly 150 law libraries. If published by the vendor with detail those would be strong evidence, because a law library consortium and a curriculum adoption are procurement decisions by institutions that evaluate research tools for a living. As located they are third party assertions. Independently verifiable and dated: sustained coverage by a named legal technology journalist across four separate product stages from 2024 to 2026, an ABA Woman of Legal Tech recognition for cofounder Kara Peterson in 2024, and an Anthem Award for Responsible Technology. Held at C because no vendor published customer, deployment, usage figure or outcome measure was located, and because the corpus milestones the vendor does publish describe its own build progress rather than any customer result. Source basis Third Party Estimated on that footing.

Privilege and Confidentiality Posture

How client confidences are handled: attorney client privilege and work product treatment, segregation of one client matter from another, whether client data trains any model, and what the vendor commits to in writing rather than in marketing.

Binding published terms exist and nothing in them addresses privilege. The terms of service are framed explicitly as the legal equivalent of a signed written contract, incorporate the privacy policy, and govern the platform rather than merely the website, which puts this vendor ahead of several records in this pull where the only published document was a marketing site disclaimer. Against that: no treatment of legal professional privilege or work product was located, and nothing addresses the confidentiality of the briefs, pleadings and documents that DescrybeLM and Descrybe Review accept as inputs, which is a change in posture from a product that once only served public domain opinions and now ingests a user's own filings. Research limitation stated rather than hidden: a privacy policy exists and is referenced from the FAQ, and its text was not read on 29 Aug 2026. This grade and the AI Safety grade are both correction candidates on that basis.

UPL and Professional Responsibility Posture

Whether the vendor is clear that it supplies a tool rather than legal advice, who its audience is, and how it addresses unauthorized practice of law, competence and supervision duties, and jurisdiction limits. ABA Formal Opinion 512 is the reference point.

Not addressed, and this is the record on the index where it most obviously should be. The vendor states directly that the product brings legal reasoning to anyone who needs it, lawyers and non lawyers alike, and the founding mission is access to justice for members of the public without formal legal training. A guided reasoning engine that takes a member of the public's question and returns a citation backed analysis is the unauthorised practice question in its clearest form, and no position on it was located: no statement that output is not legal advice, no guidance on when to consult a lawyer, and no engagement with any bar rule. The closest thing is the terms disclaiming that outputs are reviewed or validated, which allocates risk without addressing the professional question. Checked the home page, the FAQ, the user guide, the terms of service and the product pages on 29 Aug 2026.

AI Governance and Bias Disclosure

Published governance over model behaviour: who owns it inside the vendor, what is tested before release, and what is disclosed about disparate output across matter types, parties, or populations.

Nothing published. No AI policy, no evaluation methodology, no bias or fairness assessment, no accuracy monitoring, no drift statement, no model card, no named governance body and no external standard. The gap has a specific shape here that is worth recording: the entire corpus is machine generated summaries of judicial opinions, so any systematic bias in summarisation propagates into every search result and every citator treatment downstream, and it would be invisible to a user reading the summary rather than the opinion. The vendor rebuilt all its summaries once already, on newer models, which is an implicit acknowledgement that summary quality is model dependent and improvable, and no evaluation of either generation was published. Checked the home page, the FAQ, the user guide, the terms of service and the published product announcements on 29 Aug 2026.

AI Safety and Data Stewardship

Retention, deletion, access control, and what happens to prompts and documents after they are processed. Whether the vendor states its subprocessors and its incident practice, or leaves the buyer to assume.

No stewardship position was located for user submitted content. DescrybeLM and Descrybe Review accept briefs, pleadings and documents as inputs, and research sessions are saved and revisited as a product feature, so user content is both ingested and persisted by design. Nothing located states whether that content is used to train or improve any model, how long it is retained, whether a user can delete it, or how it is handled when passed to the third party AI models the terms disclose are in use. Same research limitation as Privilege: the privacy policy exists, is referenced from the FAQ, and was not read on 29 Aug 2026, so this grade is a correction candidate and the absence is recorded against the material actually checked, being the home page, the FAQ, the user guide, the terms of service and the product pages.

AI Liability and Recourse

What the vendor stands behind contractually when its output is wrong. Indemnities, caps, carve outs, insurance, and whether any of it is published or only reachable through a negotiated agreement.

An actual published liability position exists, which most of this roster lacks, and it runs almost entirely one way. The terms of service state that the user indemnifies and holds Descrybe harmless from liability, loss, claim and expense including reasonable attorneys' fees related to use of the service or its outputs, and that any liability found on Descrybe's part is limited to the amount the user actually paid in the twelve months before the action giving rise to it. Read against published pricing that caps vendor exposure at $300 to $600 per user. The same document states that Descrybe does not review or validate outputs for accuracy. Graded C rather than D because a specific, quantified and readable cap is genuine disclosure that a buyer can price, and it is more than the vendors on this index who publish nothing. No warranty, accuracy undertaking, service level or correction mechanism was located.

Practice Systems Integration Depth

How deeply the product reaches into the systems legal work already lives in: document management such as iManage and NetDocuments, Word and Outlook, contract lifecycle management, matter management, e-billing, and court filing systems.

Integration is the product rather than an afterthought, and it is documented at tool level. Descrybe Legal Engine exposes citation lookup, quote verification, treatment review and source retrieval to external assistants over an MCP interface, with named supported hosts including Claude, ChatGPT and Perplexity, and an Open Connector for building further tools. A user guide describes the call pattern: the assistant invokes one or more Descrybe tools, Descrybe performs the search, lookup, verification or retrieval, and returns focused results, with the user able to see which tools were called and read what each returned. Work product exports to Word. Held at B because the integrations are to AI assistants rather than to legal practice systems: no document management system, no practice management platform, and nothing connecting to a firm's existing matter estate. Notable as the first record in this pull whose integration story is an interoperability protocol rather than a connector list.

Deployment Model and Data Residency

Where the software runs and where the data sits. Multi tenant cloud, single tenant, private deployment, on premises, and whether region of residence is a published option or an enterprise conversation.

Nothing located. No hosting provider, no region, no data residency commitment, no single tenant or private option, and no statement of where user submitted briefs and pleadings are processed or stored. The engine architecture makes this more pointed than usual rather than less: user queries and returned legal material move between the Descrybe service and a third party assistant host such as Claude, ChatGPT or Perplexity, and nothing published describes what crosses that boundary, where either side sits, or which party holds what. Checked the home page, the FAQ, the user guide, the terms of service and the product pages on 29 Aug 2026.

Security Certifications and Trust Center

Independent attestation a buyer can pull without a sales call: SOC 2, ISO 27001, penetration test summaries, a trust center with current reports and named scope rather than a badge image.

No certification, attestation or security documentation of any kind was located. No SOC 2 of either type, no ISO 27001, no penetration testing statement, no named auditor, and no trust centre, security page or documentation request route. Under the three tier test the artifact is absent rather than gated. Some context without changing the grade: this is a self funded two founder company that priced the product at $25 to $50 per month and states it carries no enterprise sales overhead, and a SOC 2 examination is a material cost against that model. The index grades what a buyer can verify, so the grade stands, and the note records why the absence is unsurprising rather than treating it as concealment. Checked the home page, the FAQ, the user guide, the terms of service and the site footer on 29 Aug 2026.

Model Supply Chain Disclosure

Which models sit underneath, whose they are, where they run, and whether the vendor commits to telling customers when that changes. A legal buyer inherits every dependency it cannot see.

The category is disclosed in the binding document and no provider is named, and a third party claim to the contrary was rejected. The terms of service state that Descrybe uses third party AI models to summarise and make searchable primary law and judicial cases. That is a real supply chain disclosure, made in the contract rather than in marketing, and it establishes that outside models process the corpus. Third party research material asserts the opposite, that DescrybeLM is the company's own model and is not reliant on third party models such as ChatGPT or Claude. Where a directory and a vendor's own terms of service conflict, the terms govern, and the third party claim is not credited. Held at C because no provider, model or version is named, no subprocessor list exists, and nothing states which models touch user submitted briefs as opposed to the public opinion corpus. Compare Onspring at B, the only record on this index naming its provider outright.

Commercial Transparency

Whether a buyer can learn what this costs without entering a sales process: published rates, the unit being charged, what sits behind an enterprise tier, and what implementation adds.

The first A on this axis in the pull, and it is earned on the full set. Exact prices are published for every tier: $25 per month for Descrybe Legal Engine and $50 per month for the full Descrybe Platform with the Engine included. The unit of charge is a monthly subscription per user, stated plainly. Feature gating is explicitly ruled out, with the vendor stating that every feature is included at either tier, which removes the usual variable where a headline price buys an unusable subset. The vendor goes further and explains the pricing basis, stating that it is self funded, without outside investor timelines or enterprise sales overhead, and prices for the work rather than the market. A buyer can determine total cost of ownership from the public site without contacting anyone, which is the top of this axis. Every other record in this pull to date requires a demo request or a login.

Firm and Practice Coverage

Who the product is actually built for. AmLaw, midlaw, small firm and solo, in house departments, government and courts, and which practice areas are supported rather than merely claimed.

Coverage is stated concretely and its boundaries are honest. More than 3.6 million judicial opinions covering state supreme and appellate courts across all fifty states and the District of Columbia, extended to federal district and appellate opinions, with statutes and regulations also addressed by the current platform. Corpus growth was published as it happened, from seven states and 1.2 million opinions to national coverage, which is a checkable record rather than a static claim. Bilingual English and Spanish search and summaries are a genuine coverage dimension almost nothing else on this index offers, and plain language versions extend reach to non specialists. Held at B rather than A because the corpus is not enumerated at the level a researcher checks: no per court or per jurisdiction breakdown, no historical date range, and no update lag or refresh frequency, so a practitioner cannot confirm whether last quarter's appellate decision in their state is present.