Counsel Stack vs Omnilex: how they compare in 2026

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.

The models are the engine of what a buyer uses and a substantial content asset sits beneath them. The corpus is counted openly at 1,057,541 sources across five categories, dominated by 797,321 Swiss court decisions and 22,181 laws and articles, and that collection would remain a usable Swiss law database if every model were removed, which is the product several incumbents in this market already sell. What the AI adds is the reasoning layer over it, plus one thing that is genuinely model-created: the Omnilex Commentary, 222,525 annotations the company writes itself article by article on Swiss law, which exists only because the models produced it. Agents built without code from a firm's own playbooks sit on top. The pricing page frames the whole offering as one licence covering corpus, models and agents together, which is an accurate description of a product where the machine learning is the mechanism and the collection is the substrate. Verified 2 September 2026.

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.

Grounding is real, documented and unusually well labelled. The stated design is that every claim is cited and ready for the file, and the Omnilex Commentary carries the line that every statement is citable, with the worked example on the home page showing an annotation to article 336c of the Code of Obligations footnoted back to its authorities. The user also selects which source types the research draws on, choosing between court rulings, commentary or internal data, which is a described retrieval control rather than an opaque one. One practice deserves specific credit and is rare in this corpus: the commentary the vendor generates is expressly labelled as AI-drafted, so a lawyer can tell machine-written analysis from published doctrine. What is absent is measurement. No accuracy figure, evaluation, benchmark or test set appears anywhere. Clause 6 of the terms goes the other way and disclaims it directly, stating that the provider accepts no liability for the accuracy or legal usability of generated content, which is candour about the limitation rather than evidence about the rate. Verified 2 September 2026.

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.

The review obligation is contractual and the agent layer is user-triggered. Clause 6 of the terms states that the user remains responsible for reviewing, adapting and using all content, which places the checkpoint on the lawyer in the operative document rather than in marketing. The product framing is consistent with it, describing AI-assisted suggestions at clause 2 and, on the product page, a system that analyses documents, laws and judgments, structures arguments and highlights relevant content. Agents are described as built from a firm's own playbooks and review steps and run on demand, so they execute when a person starts them rather than autonomously, and the worked example sets out its four steps openly. What is not published is the boundary. Nothing states what an agent completes without a human once started, what happens when a step fails or returns nothing, or what threshold separates a suggestion from an action. The firm authors the workflow, so the operating envelope is customer-set and undescribed. Verified 2 September 2026.

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.

Ten customers are named by logo across private practice, insurance, corporates and the state: the Swiss Confederation, Bayer, the legal-protection insurer Dextra, the pension fund Asga, the disability charity Pro Infirmis, and the firms SwissLegal, Ruoss Voegele, Neuwerk, Domenig and Seeger Frick. Two carry dedicated case pages with named individuals speaking on video, Florian Probala, Chief Claims Officer at Dextra, and Dr. iur. Marco S. Marty, Founding Partner at MV Legal Partners. A named public authority among the references is worth noting on its own, because a federal administration adopting an AI research tool is a procurement signal a buyer can weigh. One figure is published, that over 6,000 lawyers use the platform, described as the most-used AI workspace in Swiss law. What holds this below A is measurement: the 6,000 figure is an adoption count rather than an outcome, no figure is attached to any named customer on the pages read, and nothing is dated. The two case pages were not opened this pass. Verified 2 September 2026.

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.

The privilege limb is met squarely, which most records in this pull fail, and the training limb is not addressed at all. Omnilex engages the professional-secrecy question in its own legal system's terms rather than gesturing at confidentiality: the home page states that models are processed on Swiss infrastructure so that attorney-client privilege stays intact, that the platform was built for professional secrecy from day one, and that the licence agreement with its data processing agreement is drafted to respect professional secrecy and auxiliary-person liability. That last concept is the Swiss doctrine governing a lawyer's responsibility for the third parties they engage, and naming it is a substantive engagement with the buyer's own obligations. Retention and deletion are addressed at clause 7 of the terms, with data deleted after the contract ends subject to statutory retention. The position on model providers is partly answered by keeping processing on Swiss infrastructure. Two limbs fail. Nothing published describes segregation between customers, users or matters, despite the product organising work into named projects and mandates. And nothing located addresses whether customer content is used for training, in either direction, as set out on that signal. Verified 2 September 2026.

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.

A real position on tooling versus advice is published in the operative terms rather than a footer. Clause 2 characterises the service as software that supports users in working on legal questions with AI-assisted suggestions, which frames output as input to a lawyer's work. Clause 6 states that the provider accepts no liability for the accuracy or legal usability of generated content and that the user remains responsible for reviewing, adapting and using all content, which is the supervision dimension stated as an obligation. Coverage is bounded in practice, since the product, the corpus and the commentary are Swiss law throughout and the terms are governed by Swiss law with jurisdiction in Zurich. The professional frame is engaged more directly than usual through the references to professional secrecy and auxiliary-person liability. Two things are missing. No express statement that output is not legal advice, and no statement about the professional relationship, appears anywhere on the surfaces read. And no bar or professional body guidance is named, with neither the BGFA nor Swiss Bar Association material referenced, which is recorded on the bar guidance signal. Verified 2 September 2026.

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.

A governance surface exists and its contents could not be read. The SafeBase trust centre carries a dedicated AI section listing AI Security, AI Governance and AI Monitoring as published items, which is more structure than most records in this corpus offer and is evidence that a position exists rather than that none does. The item pages themselves are driven by query parameters that did not render, so what those headings contain is unestablished, and this grade rests on the existence of the surface rather than on any substance credited from it. Around it sit an ISO/IEC 27001:2022 certification audited across the whole organisation, a dated penetration test report, and an ESG section covering anti-bribery, anti-competitive practices and modern slavery, all of which are adjacent subjects this axis treats separately. What was located nowhere, on any surface, is anything about bias or uneven output: no statement addresses whether the system performs differently across cantons, languages, court levels or party types, which matters for a product whose corpus spans a federal system with three official languages. Verified 2 September 2026.

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.

Substantive across most of the ground, short of specificity on two elements. Access control is the strongest part and is stated as the default set legal teams expect: SAML single sign-on, audit logs, IP allow-listing and data lifecycle management, with the trust centre adding credential management, brute-force protection and account hardening, endpoint detection and response and disk encryption. Encryption is stated at rest and in transit. Subprocessors are named, with the trust centre legal section identifying Amazon Web Services and Microsoft Azure. Incident practice is stated, with a dedicated response team and an incident response item in the trust centre, and backups, business continuity and disaster recovery and anti-DDoS all appear as published items. What keeps this off the top band is that two of the five elements are stated without being specific enough to hold the vendor to. Retention is given only as data deleted after the end of the contract unless statutory retention applies, with no period for anything during the term. And the incident commitment carries no notification deadline to the customer, the trust centre saying instead that more detail is available on request. The named subprocessors are also infrastructure only, which is examined on the model supply chain axis. Verified 2 September 2026.

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.

A real position is published and it is short of the full picture. Clause 6 of the terms sets out the allocation in four sentences: use is at the user's own risk; the provider accepts no liability for the accuracy or legal usability of generated content; the user remains responsible for reviewing, adapting and using all content; and the provider's liability is limited to gross negligence and intent. That last limb is more informative than it looks, because it is the maximum exclusion Swiss law permits, so a reader knows precisely where they stand, with nothing recoverable for ordinary negligence and no monetary cap at all on the residual liability for gross negligence and intent. Cyber insurance is separately published as a document in the trust centre, which is one of the four things the top band asks for. What is absent is the rest. No indemnity runs in either direction, no warranty is given on output and clause 6 expressly disclaims it, and no cap figure appears. The availability commitment at clause 5 is weak and honest about it, targeting at least 90 per cent outside maintenance windows and stating it is not guaranteed. One scope limit belongs on the record: clause 9 states that use is based on a separate licence agreement, and that agreement is not published, sitting instead as a template behind the trust centre's access flow, so what a signed customer actually receives is not established. Verified 2 September 2026.

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.

Integration is claimed and never specified. The product page states that a firm can connect its document management and legal tools without media breaks and keep its proven workflows, which is a direct claim to integrate with the systems legal work already lives in. Not one of those systems is named. No document management product is identified, no practice management or e-filing tool, no connector list, and no integrations page exists. Enterprise plans are stated to include custom integrations and APIs, but that is a scoping conversation rather than a published capability, and no API or developer documentation was located. What is concrete is authentication rather than workflow: SAML single sign-on across plans and company SSO at enterprise level. A claim to integrate, with the systems unnamed and nothing an implementer could use, is what this band describes. Checked the home page, product page, pricing page, terms, privacy policy and trust centre on 2 September 2026. Verified 2 September 2026.

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.

Residency is stated with a named city and a named cloud, and the tenancy limb is silent. Omnilex publishes that it is hosted on Microsoft Azure in Zurich, that data is encrypted at rest and in transit and hosted entirely on its Swiss Azure cloud, and that models run on Swiss infrastructure, which is the point on which the privilege claim rests. Processing is separated from hosting and bounded, with the pricing FAQ stating that data is processed in Switzerland and in selected EU countries recognised as adequate by the Swiss Federal Data Protection and Information Commissioner. Naming the supervisory authority rather than asserting adequacy is a good habit. Two things hold this below the top band. No tenancy or isolation model is published anywhere: nothing states whether the platform is multi-tenant, single-tenant or how one firm's data is separated from another's, which is the limb this axis pairs with region. And there is a small tension a buyer should notice between hosting stated as entirely on the Swiss cloud and processing stated as extending to selected EU countries; both are published, neither is reconciled. No on-premises or customer-cloud option is offered. Verified 2 September 2026.

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.

A real trust centre exists, it renders, and it is inventoried. The SafeBase portal at trust.omnilex.ai lists ISO/IEC 27001:2022 under compliance, and among its documents a penetration test report dated 5 September 2025, the Omnilex Licence Agreement including a DPA template, technical documentation, cyber insurance, a data security policy and a network diagram, alongside sections for product, data, application and endpoint security, infrastructure and legal. The certification is described on the home page as audited across the whole organisation, which is a scope statement rather than a bare badge, and a document carrying a date is visible without any request. What is not established is the access tier for the documents themselves. The portal offers a public and private split with a get-access flow, and it does not state whether access is granted instantly on an email or an NDA click-through, or only after review, so the lower tier is graded and the reason recorded. No auditor or certification body is named, and no certificate number, issue date or validity period is published. No request was submitted. Verified 2 September 2026.

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.

The models are named to the version on the home page, which nothing else in this pull does, and the disclosure stops short of the rest. Five are listed as selectable, GPT-5.6, Claude Opus 5, Mistral Large 3, Kimi K2.6 and Grok 4.6, with the user choosing which answers a given question, and the accompanying claim is that every frontier model is available and processed on Swiss infrastructure so that attorney-client privilege stays intact. Where inference runs is therefore stated at estate level, on Microsoft Azure in Zurich. The trust centre names Amazon Web Services and Microsoft Azure as subprocessors. Two limbs are missing. No model house is identified as a legal entity and none appears in the subprocessor list, so a reader can see that Claude Opus 5 is available without learning which entity contracts for it or what it may retain, and the inference that the models run inside the Swiss cloud estate rather than through the vendors' own APIs is left to be drawn rather than stated. And no commitment to notify customers when the model set changes was located, which matters on a product that markets access to whichever frontier model is current. Verified 2 September 2026.

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.

The strongest commercial disclosure located in this pull. Rates are published with the unit and the term: CHF 2,000 per user billed annually for a single user, CHF 1,600 per user billed annually for teams from two users, and a custom tailored agreement for enterprise from twenty users, all stated excluding VAT, with an annual and monthly toggle so a buyer can compare billing cadences. The unit is explicit and the vendor makes a point of it, stating that the price scales only with the people who use it and that corpus, models, agents and security are in every plan. The limb this axis asks for that almost no vendor answers is answered directly: implementation is not an extra. Onboarding, set-up, training and support are listed as included in every plan without asterisks, and the FAQ states that nothing essential is held back in a higher tier, with Team adding collaboration and know-how integration and Enterprise adding SSO, custom integrations and APIs. A fourteen day free trial of the full product requires no card and no commitment. Usage limits are published too, at up to 1,000 pages and 500MB per document with otherwise unlimited use. The only withheld figure is the enterprise tier, which the page explains is a scoping conversation about integrations and support rather than a different product. Verified 2 September 2026.

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.

Four buyer segments each have their own page and each is described in terms of the work rather than as a label: law firms handling research, drafting and review across mandates; in-house teams moving from contract review to regulatory questions; public administrations applying federal and cantonal sources; and insurers assessing claims against statute and precedent. Covering government and insurance explicitly is unusual and is borne out by the named references, which include the Swiss Confederation and a legal-protection insurer. Jurisdictional coverage is stated precisely through the corpus itself, with federal and cantonal decisions, statutes, official documents and literature counted by category. What is missing is the boundary. No practice areas are enumerated, and while the worked examples on the home page range across employment, tenancy and accident insurance law, that is illustration rather than a coverage statement. No firm size band is given beyond the seat thresholds in pricing, nothing addresses whether the product serves any jurisdiction other than Switzerland, and nothing states what it does not support. Verified 2 September 2026.

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.

Checked the home page, product page, pricing page and its FAQ, the terms and conditions in full, the privacy policy in full and the trust centre index on 2 September 2026. Nothing addresses whether customer content is used to train or improve models, in either direction. The terms are silent: clause 7 covers data protection by reference to the privacy policy and deletion after contract end, and clause 8 reserves rights in the software, content, models and generated data to the provider without touching training. The privacy policy is expressly website-scope, stating that use of the application at app.omnilex.ai is additionally governed by the data protection terms of the licence, in particular the data processing agreement documented in the trust centre. That agreement exists as a licence agreement including a DPA template listed among the trust centre documents, behind an access flow, and it was not requested. Two adjacent statements point toward a protective posture without reaching the question: models are stated to be processed on Swiss infrastructure so that attorney-client privilege stays intact, and the licence is described as drafted to respect professional secrecy and auxiliary-person liability. Neither names training. Under the naming test the honest record is that the question is unaddressed on every public surface.

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.

Retention is acknowledged in the operative terms and no period is attached to it. Clause 7 states the quoted position, which fixes an event rather than a duration: deletion follows the end of the contract, with no stated window for how long after, and with an open carve-out for statutory retention duties. Nothing states how long prompts, chats, generated drafts or uploaded documents persist during the term, and no retention setting is offered to the customer. The trust centre lists a data erasure item and a data lifecycle management control among the defaults, and the home page names data lifecycle management as one of the controls legal teams expect, but neither carries a figure on any surface that could be read. The one specific limit published anywhere concerns size rather than time, with the pricing page capping documents at 1,000 pages and 500MB. The data processing agreement that would normally carry retention detail sits behind the trust centre access flow and was not requested.

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.

Checked the home page, product page, pricing page, terms, privacy policy and trust centre index on 2 September 2026. Nothing describes segregation between customers, between users inside a firm, or between matters. The product is visibly organised around matters, with the interface showing named projects such as a share purchase, a due diligence, a litigation matter and an estate, and the pricing page adds team and project collaboration at the Team tier and know-how integration, so the structure for separation plainly exists. What is absent is any statement that it functions as a boundary: nothing says whether one user in a firm can reach another's project, whether ethical walls can be configured, or how tenants are isolated from one another. Access controls are published at the account layer instead, with SAML single sign-on, audit logs and IP allow-listing. The gap sits awkwardly against the vendor's own professional-secrecy framing, since conflicts walls are part of what Swiss professional secrecy requires of a firm.

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.

Checked the terms and conditions in full, the privacy policy in full, the home page, product page, pricing page and trust centre index on 2 September 2026. Nothing addresses disclosure to authorities or in response to legal process, and nothing addresses notice to the customer if a demand arrives. The terms have no confidentiality article at all and no required-disclosure clause. The privacy policy lists legal obligations as a processing basis but is expressly scoped to the website rather than the application, and its recipients are website service providers. The question is therefore not reached rather than answered adversely. Two things are recorded so a later grader can weigh the gap: the licence agreement including a DPA template is listed among the trust centre documents behind an access flow and was not requested, and it is the document where a compelled-disclosure clause would sit; and the vendor's professional-secrecy framing makes the silence more conspicuous, since a demand for a lawyer's file is precisely the scenario auxiliary-person liability contemplates.

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.

The corpus is identified by category and counted to the unit, which is more precise than any other record in this pull: 797,321 court decisions, 222,525 commentaries, 22,181 laws and articles, 13,162 official documents and 2,352 pieces of literature, totalling 1,057,541 sources, described as federal and cantonal decisions, statutes, official documents and literature refreshed continuously. Cadence is therefore described and the composition is transparent. One category carries its own provenance disclosure and deserves credit: the Omnilex Commentary is the vendor's own, written article by article, and it is labelled as AI-drafted and cited back to statute and case law rather than presented as published doctrine. What is not stated anywhere is the rights basis. No publisher, database or data supplier is named for any category, and no licence, agreement or permission is described. That gap matters most for the 2,352 pieces of literature and for whatever underlies the commentary category, since Swiss legal literature is commercially published and is not, unlike federal and cantonal case law, free to redistribute by default.

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.

Checked the home page, product page, pricing page, terms and trust centre index on 2 September 2026. No public material addresses whether a decision returned by the product is still good law. Nothing describes treatment flags, subsequent history, or whether a judgment has been confirmed, distinguished or departed from. The nearest claims concern the freshness of the collection rather than the standing of any individual authority: sources are described as refreshed continuously, and the product page offers to keep a user informed about the latest changes in legislation and jurisprudence at federal, state and cantonal levels. Those speak to what has been added, not to what has been overtaken. The question bites here because the product retrieves case law and its own commentary as the basis for cited answers, and because Swiss practice depends heavily on whether the Federal Supreme Court has since moved.

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.

Checked the home page, product page, pricing page, terms and trust centre index on 2 September 2026. Nothing describes what the platform does when it cannot ground an answer, and no confidence, relevance or grounding indicator is described as shown to the user. The published answer to the same underlying risk is verification by the reader rather than abstention by the system: every claim is stated to be cited, the commentary carries the line that every statement is citable, and clause 6 of the terms places responsibility for reviewing and adapting all content on the user. The user can also restrict which source types are consulted, which shapes retrieval rather than describing behaviour when retrieval comes back thin.

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.

Searched the AI Hallucination Cases database maintained by Damien Charlotin, and reporting drawing on it, on 2 September 2026 on the product and corporate name Omnilex and Omnilex AG. No court order, opinion or disciplinary record naming the product was located. This is a statement about the public record rather than a finding about the product. One structural caveat bounds it: the database is heavily weighted to United States filings, its European coverage is thinner, and Switzerland does not feature among the jurisdictions commonly reported in it, so a Swiss product is less likely to surface even where an incident occurred. Swiss judgments are also published in three languages, which further limits how reliably an English-language search reaches them.

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.

Professional obligations are referred to directly but no authority or instrument is named. Omnilex states that the platform was built for professional secrecy from day one, that models are processed on Swiss infrastructure so attorney-client privilege stays intact, and that its licence agreement and data processing agreement are drafted to respect professional secrecy and auxiliary-person liability. Naming auxiliary-person liability is a substantive reference to the doctrine governing a Swiss lawyer's responsibility for third parties they engage, and it is more than most records in this corpus offer. What is missing is the source. No instrument is cited, with neither the Federal Act on the Free Movement of Lawyers nor the criminal provision on professional secrecy named, and no guidance from the Swiss Bar Association or any cantonal bar is referenced. Nothing addresses what a lawyer must do to satisfy those duties when using the product, as opposed to what the vendor has done to make it possible.

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.

Checked the home page, product page, pricing page and FAQ, terms and trust centre index on 2 September 2026. Nothing addresses how AI-assisted work is recorded, billed or disclosed to a client, and no per matter record of AI-assisted work was located. Unusually for this corpus, no quantified savings claim appears on any first-party surface either: the vendor's language is about being faster, more precise and dependable, and about winning the matter rather than the admin, without publishing a time or cost figure, so the weakest value is not made out. A third-party report attributes a 93 per cent research time saving to user reports; that is an excluded source and is not recorded. The raw material for a per matter record does exist in the product, which organises work into named mandates and carries audit logs, but nothing describes either as reportable against a bill.

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.

A subprocessor list is published and reachable without an agreement: the trust centre legal section identifies Amazon Web Services and Microsoft Azure, and the same portal carries a data processing agreement item, a cyber insurance item and a licence agreement including a DPA template. The pricing FAQ confirms that a data processing agreement is part of every licence. That is enough for a firm to begin answering a client, which is why the bottom value is false here. It stops short of the top value on the limb this signal treats as decisive. The two named subprocessors are infrastructure, and infrastructure alone does not answer whose model saw the content: five frontier models are named on the home page as selectable, and not one of their providers appears in the list or anywhere else as a contracting entity. The forwardable material is also gated rather than published, with the licence and DPA sitting behind the trust centre access flow, so what a firm can hand to a client without asking is the subprocessor naming and the certification rather than the documents themselves.

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.

Checked the home page, product page, pricing page, terms and trust centre index on 2 September 2026. Nothing addresses disclosure of AI use to a court or authority, and no exportable per document record of model used, sources retrieved and human verification is described. The product does leave a usable trail for the lawyer's own purposes, since every claim is cited and ready for the file, the commentary is labelled as AI-drafted, and audit logging is published as a standard control, but none of these is presented as a record of model use and none captures which of the five selectable models produced a given passage. That last point is the sharpest version of the gap on this record: a platform that lets a user choose between five frontier models, and that labels its own commentary as machine-written, is closer than most to being able to emit exactly this record, and does not say that it does.