Counsel Stack
Deep legal research platform for United States law firms, built around what the vendor describes as a fleet of specialised research language models assembled for particular practices and jurisdictions, with an emphasis on structured citation verification. Synthesises federal, state and local doctrine, and positions itself against generic models on highly technical, boutique, cross jurisdictional and multi doctrinal questions. Automatically tracks and saves research, conversations, sources, proof of citation verification and timekeeping entries. Access is restricted to United States licensed attorneys, verified at signup, with no credit card required and API access on request. Founded 2023. Placed first among all participants in the 2025 Vals Legal AI Report legal research study. Note that the company also operates separate legal marketing, lead generation and web design lines; only the research product is graded here.
Capability grades
All 15 axes, graded from public sources on the date shown. Hover a grade to see what the letter means on that axis.
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.
For the research product graded here, the artificial intelligence is the product. The vendor describes a fleet of specialised research language models assembled by its attorneys, engineers and legal professionals for particular practices and jurisdictions, and the evaluator independently confirms multiple specialised models purpose built for legal research. Retrieval, synthesis and citation verification are all model driven. One scope note recorded rather than deducted for: the company also operates legal marketing, lead generation and web design lines that have nothing to do with AI. Those are separate offerings and are excluded from this record, which covers the research product the seed list names and the benchmark measured.
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 strongest measured accuracy on the index, and the measurement is independent. In the 2025 Vals Legal AI Report legal research study, Counsel Stack placed first among all participants across all three criteria, ahead of every other legal AI product, a generalist model and the lawyer baseline: 81 percent accuracy against a 71 percent lawyer baseline, 77 percent authoritativeness against 68 percent, 71 percent appropriateness against 60 percent, and a 78 percent weighted aggregate against 69 percent. It answered 196 of 200 questions with four technical timeouts, which the evaluator published alongside the scores. The rubric and weights were set by the evaluator in advance and the questions were contributed by Am Law 100 firms, so the figures are checkable by an outsider against the evaluator's own site rather than resting on any vendor claim. The product also ships a mechanism aimed directly at this axis rather than only claiming accuracy: structured citation verification, with proof of citation verification saved automatically as part of the research record. Recorded from the same evaluator and applying to every participant: all systems struggled on multi jurisdictional questions and underperformed a generalist model on fifty state statutory surveys.
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.
Autonomy is present and oversight is implied by a record keeping mechanism rather than described as a control structure. The product automatically tracks and saves research, conversations, sources and proof of citation verification, which lets a supervising lawyer reconstruct what was done, and a published customer account describes the tool empowering a small team rather than replacing human work. Reconstruction after the fact is transparency, not a control point. Searched the vendor site, the deep research product page and third party coverage on 29 Aug 2026 and located no statement of what the system does unaided, no threshold at which it stops or escalates, no review surface a lawyer must clear before output is used, and no statement of what the vendor commits to when an output is wrong. Same reasoning as applied to Noxtua, where a traceability feature was held not to satisfy this axis.
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.
Testimonials stand in for deployment evidence, though they are unusually specific about the shape of the practice. Published accounts describe a solo attorney with one other attorney, a paralegal and an intern replacing existing practice management software and using the product for research, and a legal content creator using it across Pennsylvania and federal law. Those are real use descriptions rather than logo walls, and they identify the firm size honestly as very small. Searched the vendor site, the product pages and third party coverage on 29 Aug 2026 and located no named organisation paired with figures and a date, and no assessable method. The independent benchmark result is test set performance rather than a production outcome, and the two are different things.
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.
Searched the vendor site, the deep research product page and third party coverage on 29 Aug 2026, and ran targeted searches for a Counsel Stack security page, privacy policy or trust centre without reaching one. Nothing was located on how client confidences are handled: no statement on training, no retention or deletion terms, no segregation model, no treatment of attorney client privilege or work product. The product saves research, conversations and sources by design, so material accumulates in it, and no published terms attach to that material. Rebuttable with one link.
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.
A real published position enforced as a product gate rather than stated as a disclaimer, which no other record on this index has. Access is restricted to United States licensed attorneys, verified at signup, with the vendor stating plainly that only US licensed attorneys qualify at this time. That is a professional responsibility boundary implemented in the product rather than asserted in terms: a non lawyer cannot obtain the tool. Short of an A because the position addresses who may hold the product without addressing what the lawyer remains responsible for: searched the vendor site and product pages on 29 Aug 2026 and located no treatment of competence or supervision duties, no statement on the advice line, and no jurisdiction limits within the United States despite the product spanning federal, state and local doctrine.
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.
Submitting to independent measurement and permitting publication is the governance act on this record. Counsel Stack was one of four systems evaluated and named in the Vals legal research study, in a field where the evaluator and trade press both recorded that major vendors declined and at least one participated then withheld permission to publish. Agreeing to publication of results including four technical failures is a real accountability position. It is nonetheless a point in time evaluation rather than a management system. Searched the vendor site, the product pages and third party coverage on 29 Aug 2026 and located no AI governance framework, no AI management certification, no named owner of model governance, no pre release testing regime, and nothing on uneven output across matter types, parties or populations.
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.
Searched the vendor site, the deep research product page and third party coverage on 29 Aug 2026, and ran targeted searches for a security page or trust centre without reaching one. No retention period, no deletion control, no access control detail, no encryption statement, no hosting disclosure, no subprocessor list and no incident or breach notification practice was located. The gap is sharpened by the product's own design: it automatically saves research, conversations, sources and timekeeping entries, so it accumulates a durable record of a lawyer's work with no published terms governing that record. Rebuttable with one link.
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.
Searched the vendor site navigation, the deep research product page and third party coverage on 29 Aug 2026. No published indemnity, liability cap, carve out, warranty on output or insurance position was located, and no customer terms of service was located as published on the property. Recorded as a pure absence on the surfaces reached. Worth naming the shape of it: this vendor's entire positioning rests on measured accuracy and structured citation verification, and it publishes nothing about who bears the loss if a verified citation is wrong.
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 surfaces exist and none is documented. API access is offered on request, which is a real integration route, and a published customer account describes the product having replaced their existing practice management software, which implies matter and time tracking functionality native to the product rather than connected to it. Searched the vendor site, the product pages and third party coverage on 29 Aug 2026 and located no integrations page, no named connector for document management, practice management, court filing or Microsoft Word, and no API documentation reachable without contacting the vendor. Recorded at C because routes are named without being documented.
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.
Searched the vendor site, the deep research product page and third party coverage on 29 Aug 2026, and ran targeted searches for infrastructure or security documentation without reaching any. Nothing was located on the deployment model: no tenancy statement, no hosting provider, no region, no residency option, and no statement of where processing happens. The product is evidently cloud delivered and browser reachable, but that is inference from how it is sold, and inference earns nothing on this axis.
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.
RECHECKED 29 Aug 2026 during the trust portal sweep; grade held at D and the finding is now better evidenced than when first recorded. A second targeted search specifically for this vendor's security page, privacy policy, terms, trust centre or certification listing returned no vendor material. That matters more than a single failed search would, because the same sweep located security pages for both other legal research vendors on this index immediately: Alexi publishes a security page and a Trust Center carrying a security addendum, architecture whitepaper, data processing agreement and audit reports, and Midpage publishes a security page stating annual SOC 2 Type II validation with retention periods and encryption specifics. Two of three surfaced on the first proper search. This one has not surfaced on two. Recorded as an absence on the surfaces reached, with the qualification that a failed search is weaker evidence than a located page: it establishes that a buyer performing ordinary diligence would not find security material, not that none exists. Rebuttable with one link. Fourth D on this axis on the index, and the vendor holds the highest independently measured accuracy score in the pull, which makes the contrast between what it publishes about performance and what it publishes about handling the sharpest on the index.
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 vendor describes its own model layer without identifying what sits underneath it. Published and independently confirmed: a fleet of multiple specialised research language models built for particular practices and jurisdictions, described by the vendor as assembled over years by its own attorneys, engineers and legal professionals. That tells a buyer the architecture is specialist rather than a thin wrapper. Searched the vendor site, the product pages and third party coverage on 29 Aug 2026 and located no named foundation model or provider underneath that layer, no statement of where models run, no subprocessor list, and no commitment to notify customers when the supply chain changes.
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.
Real commercial terms are published at the entry point while no rate is. A free tier is published and reachable without a sales conversation, with the vendor stating signup requires only a name and professional email and no credit card, and free trial access to its chat product. That is a genuine published commercial term and a self serve route, which is more than most of this index offers. What is missing is the number: searched the vendor site, the product pages and third party coverage on 29 Aug 2026 and located no rate for any paid tier, no unit of charge, and no tier structure, with API access directed to a contact request.
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 described with substance and the target is stated honestly rather than inflated. Jurisdictional scope is federal, state and local United States doctrine, with the vendor claiming specialised models built for particular practices and jurisdictions. The competitive position is stated specifically and unusually narrowly: highly technical, complex, boutique, cross jurisdictional and multi doctrinal research, which is a claim about where the product is strong rather than a claim to cover everything. Published customer accounts are from very small firms, and the vendor does not claim enterprise scale it cannot show. Short of an A because practice areas are not enumerated for the research product, jurisdictional coverage is not stated at state level, and no statement of what the product does not cover was located, with the independently measured weakness on fifty state surveys coming from the evaluator rather than the vendor.
Legal Signals
What each signal meansA signal records what public sources say on the date shown. It is not a grade and it is not a recommendation. Where a signal reads Not addressed, it means the index did not locate the material in public sources on that date, which is a statement about disclosure rather than about the product.
Client Data in Training
Can material a lawyer puts into this product be used to train a model?
No located term or policy addresses the question either way.
Searched the vendor site, the deep research product page and third party coverage on 29 Aug 2026, and ran targeted searches for a Counsel Stack privacy policy, terms of service or security page without reaching one. No located material states whether customer content may be used to train models, either way. Recorded as silent under the rule that a value is never inferred from the absence of a contradiction. The question carries weight here because the vendor states it has assembled its own specialised models over years, so a buyer would want to know what went into them and whether their own research contributes.
Prompt and Output Retention
How long does the product keep what a lawyer typed, and can that be set to zero?
Retention is acknowledged in public materials with no stated period.
Retention is acknowledged as a product feature with no period attached. The vendor states the product automatically tracks and saves research, conversations, sources, proof of citation verification and timekeeping entries, so retention is not incidental here, it is the value proposition: the record is what the customer is buying. What was not located as of 29 Aug 2026, after searching the vendor site, the product page and third party coverage, is how long any of it is held, whether the customer controls that window, or whether deletion is available. A product built to retain a durable record of a lawyer's work with no published terms governing that record is the sharpest version of this gap on the index.
Ethical Walls and Matter Segregation
Does retrieval respect the firm’s ethical walls, or can the model read across them?
No located public material addresses walls or matter level segregation.
Searched the vendor site, the deep research product page and third party coverage on 29 Aug 2026. No vendor material addresses segregation of any kind: not between customers, not between users, not between matters. No document management integration was located whose permissions the product could inherit. Noted for context: published customer accounts describe very small firms of two attorneys plus support staff, where formal ethical walls are less commonly operated than at scale, though conflicts obligations apply regardless of firm size.
Third Party Request and Subpoena Notice
If someone subpoenas the vendor for a firm’s data, does the firm hear about it first?
No located term or policy addresses third party requests for customer data.
Searched the vendor site, the deep research product page and third party coverage on 29 Aug 2026, and ran targeted searches for published terms or a privacy policy without reaching one. No clause committing to notify a customer of a government or law enforcement request for their data was located, and no transparency report was located. The gap is more consequential than usual given the product durably stores research, conversations and sources tied to a lawyer's matters.
Primary Law Corpus Provenance
Where does the law in this product come from, and does the vendor have the right to use it?
Coverage is described by jurisdiction with no identification of the underlying corpus.
Coverage is stated by jurisdictional layer with no identification of the underlying sources. The vendor states the product synthesises federal, state and local United States doctrine and describes models grounded in US law built for particular practices and jurisdictions, and the independent evaluator confirms broad coverage across federal and state jurisdictions on its test set. Searched the vendor site, the product page and third party coverage on 29 Aug 2026 and located no named source or publisher for the primary law, no licence or public domain basis, no completeness statement per jurisdiction, and no update cadence or lag. Local doctrine coverage is claimed without any statement of which localities, which for a research product is a material undefined boundary.
Good Law Verification
Does the product tell you when the authority it just cited has been overruled?
No located public material addresses whether authority is checked for subsequent history.
A verification mechanism is published and what it verifies is not defined, which is why this does not reach a positive value. The vendor puts structured citation verification at the centre of its positioning and states that proof of citation verification is saved automatically with each research record, and the independent evaluator scored it highest of all participants on authoritativeness at 77 percent, defined as citing relevant primary sources that are valid and support the statements made. Searched the vendor site, the product page and third party coverage on 29 Aug 2026 and located nothing stating whether verification checks that authority exists and supports the proposition, or whether it also checks subsequent history and treatment. Those are different questions and no commercial citator licence was located. Recorded at not addressed because the good law question specifically is unanswered, with the verification feature noted here so a reader can weigh it.
Refusal and Uncertainty Behaviour
What does the product do when the answer is not in the corpus?
No located public material addresses what the product does when it cannot ground an answer.
Searched the vendor site, the deep research product page and third party coverage on 29 Aug 2026. No published material describes what the product does when it cannot ground an answer, and no explicit no answer path or confidence signal exposed to the user was located. The independent evaluator recorded four cases where the product returned nothing due to technical timeouts, which is a failure mode rather than principled abstention, and unlike one other participant in the same study no instances were recorded of it explaining that sources did not support an answer.
Fabricated Citation Record
Does a public court record exist involving output from this product?
No court order, opinion or disciplinary record naming this product has been located as of the date shown. This is a statement about the public record, not a finding about the product.
No court order, opinion or disciplinary record naming this product has been located as of 29 Aug 2026. Instrument searched: the AI Hallucination Cases database maintained by Damien Charlotin, which tracks court decisions worldwide involving AI generated hallucinated content and records the AI tool implicated where it is known. Also checked published 2026 sanctions summaries and secondary sanctions trackers. The entries located name filers, and in some rows other products, rather than this one. This is a statement about the public record on the date shown and not a clearance. The exposure is direct: a US litigation research product produces authority bound for filings, and this vendor's independently measured authoritativeness score was the highest in its study.
Bar Guidance Alignment
Has the vendor engaged in public with the ethics opinions its buyers are bound by?
No located public material engages with bar or ethics guidance.
Searched the vendor site, the deep research product page and third party coverage on 29 Aug 2026. No engagement with any named ethics opinion or professional guidance was located, including ABA Formal Opinion 512 and state bar guidance. Worth recording the adjacent fact rather than crediting it here: the vendor restricts access to United States licensed attorneys and verifies licensure at signup, which is a professional responsibility boundary implemented in the product. That is a real position on who may use the tool, and it is credited on the UPL axis, but it is not engagement with published guidance and the two were not conflated.
Billing and Fee Posture
Does the vendor address what happens to the bill when the work takes an hour instead of six?
A usable record of AI assisted work exists with no published fee guidance.
First record on the index to reach a value above savings claims on this signal. The product automatically tracks and saves timekeeping entries alongside research, conversations, sources and proof of citation verification, which is a per matter record of AI assisted work generated by the product itself and available to the firm. That is precisely the artifact this signal exists to look for: a firm asked what was done and how long it took has something to produce. Short of the positive value because the vendor publishes no guidance on how that record should be treated for fee or client disclosure purposes: searched the vendor site, the product page and third party coverage on 29 Aug 2026 and located nothing on billing treatment, no position on whether AI assisted time is billable, and no client disclosure material. The record exists; the guidance does not.
Outside Counsel Guideline Readiness
Can a firm get this vendor through a client’s AI clause without a bespoke negotiation?
No located public material supports a client side disclosure obligation.
Searched the vendor site, the deep research product page and third party coverage on 29 Aug 2026, and ran targeted searches for a trust centre, security page or certification listing without reaching one. No subprocessor list, no statement naming which model providers see client content, no published data processing agreement, no certification and no client facing consent or notification material was located. A firm bound by a client AI clause could not assemble a response from this vendor's published material, notwithstanding that the vendor's own models being proprietary would simplify the answer if it were stated.
Court Disclosure Support
If a judge’s standing order requires an AI disclosure, can the product produce one?
Some elements of the record are available, short of a document level export.
The most complete disclosure trail on the index for a research product, short of the model identification. The product automatically tracks and saves research, conversations, sources and proof of citation verification, so a lawyer facing a judicial AI disclosure order has a retained record of what was asked, what was retrieved, what was cited and that the citations were checked, generated as a by product of normal use rather than assembled after the fact. Two elements are missing: no export format covering that record as a single disclosable artifact was located, and no model is identified anywhere in published material so the model used could not be stated. Recorded at partial record on that basis. Noted for a reader: of the products on this index, litigation research output is among the most likely to attract such an order.