A
Annlex
Annlex is a case law research platform for United States court opinions, operated by Annlex Systems LLC and created by founder Doug Hall. Its conversational tool, Annlex Chat, classifies each question into one of ten research patterns, retrieves relevant opinions before the model writes anything, and links every citation to the full opinion text, with Anthropic's Claude Sonnet named as the model. A companion tool, Opinion Lens, works on a single opinion: it extracts the cases, judges and statutes cited, locates the question presented, rule and holding by paragraph, and answers questions from that opinion alone, stating when the opinion does not answer.
The corpus is 10.5 million opinions from 3,355 courts spanning 1658 to the present, with 71 million citation links, loaded from the CourtListener bulk export maintained by the Free Law Project and updated quarterly. The vendor names pro se litigants, law students, solo and small firm practitioners, paralegals and journalists as its audience, and prices AI queries from $25 a month with Boolean and semantic search free.
The terms are governed by South Carolina law with arbitration seated in Charleston, and the company states it is independent of any law firm, institution, data provider or AI company.
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.
The metered unit is the model. Every paid plan, the credit pack and the free allowance are counted in AI queries, which the pricing page defines as each Annlex Chat question, each AI case analysis and each synthesis request, while Boolean, semantic and hybrid search are given away free and unlimited. What a buyer pays for is Annlex Chat's retrieval and synthesis over 10.5 million opinions and the Opinion Lens tools (Key Passages, Summary, Case Brief, Ask AI), and even the free semantic search runs on ModernBERT embeddings fine tuned for legal text by the Free Law Project.
Remove the models and what remains is a free search box over a public corpus the vendor does not own. Checked the Annlex Chat page, pricing, the FAQ, the terms and the Opinion Lens page on 15 September 2026.
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.
Grounding is real, documented and unusually candid about what it does not fix. The FAQ (version 1.2, March 2026) describes the method: each question is classified, matched to one of ten research patterns and routed through a pipeline that retrieves opinions before the model writes, every claim must cite a case from the database, and every citation opens the full opinion, which the vendor states it holds on its own servers from the CourtListener bulk export.
Answers carry a Verify link into Opinion Lens, where a characterisation can be checked against the opinion passage by passage, and Opinion Lens answers only from the open opinion and says so when the opinion does not answer. The vendor names the failure that grounding leaves behind rather than claiming it away: a real case cited correctly and described wrong, a dissent quoted as the majority, a rule applied in the wrong jurisdiction.
The terms list misread precedent, missed or inappropriate authority, outdated law and missed controlling authority as expected failures. Held at B on the band: no measured accuracy of any kind is published, with no test set, no citation resolution rate and no characterisation error rate, and returned authority is not checked for subsequent history. One overstatement noted: the FAQ's opening answer says the design eliminates the conditions that cause hallucination, while the same page and the terms describe a constraint that shifts the failure mode, which is the accurate claim. Read 15 September 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.
The product is built around a reader checking the machine, and the review surfaces are real rather than asserted. Opinion Lens keeps the opinion on screen at all times, the generative tools sit beside the text and point to the paragraph an answer rests on, Key Passages anchors the question presented, rule, holding and limitation to paragraph numbers, and Ask AI declines when the opinion does not contain the answer. Annlex Chat links each citation to its opinion and offers a Verify route into Opinion Lens.
The FAQ states that attorneys remain responsible for independently verifying all authority before reliance, that the tool suits preliminary research rather than replacing verification, and that it should not be anyone's sole source. Nothing acts on a matter; output is research text and downloadable summaries and briefs. Held at B because the control structure stops short: no threshold at which Annlex Chat declines is described, the FAQ's promise to show confidence levels where applicable is not specified, and nothing addresses what happens after an answer is found to be wrong. Read 15 September 2026.
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.
No production evidence located. No named customer, firm, law school, library or user count, no case study, testimonial or usage figure, and no outcome measure appears on the Annlex Chat page, pricing, the FAQ, the terms or the Opinion Lens page, and the static sitemap lists no customer, news or blog page. The product is live with published self serve pricing, and the founder's public profile records a pitch at the Dig South Tech Summit in Charleston, which is launch activity rather than deployment evidence under the band. Checked those five surfaces, the static sitemap and a general web search on 15 September 2026.
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.
Substantive commitments on training and on the model provider, written into the terms rather than a separate policy page, with segregation silent and the storage account internally inconsistent. Section 10 of the terms (last modified date shown as 27 February 2026) states that saved conversations are not used to train any AI model, the vendor's or anyone else's; that Annlex Chat history saves by default to the vendor's own servers for registered accounts, is kept up to one year and then deleted, can be switched off with a Save history toggle and can be deleted immediately and irreversibly; that nothing is saved for users without an account; and that queries go to Anthropic's API, which does not train on API data and may retain query content up to 30 days, longer where a safety system is triggered.
The vendor states plainly that Zero Data Retention with Anthropic is not active and sits on its roadmap, which answers the provider retention question most records leave open. Privilege is engaged in the FAQ, but as a positioning argument tying attorney client privilege to that future arrangement rather than as a stated handling position. Held at B on three gaps. Nothing addresses segregation between users or any team or matter structure.
The third party section of the same terms says Annlex stores the text of Annlex Chat queries and conversations in no database, and the pricing page FAQ says queries are not stored, both contradicted by the history paragraph, so a reader has to work out which statement is current. And no data processing addendum or separate customer agreement exists for a firm to sign. Read 15 September 2026.
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 position on the advice line, carried onto the product surface itself, short of full treatment. The terms open with a section headed as a statement that the service is not your lawyer, calling it an experimental research tool that does not provide legal advice and directing users to a licensed attorney; the FAQ adds that payment does not create an attorney client relationship and lists prohibited uses including reliance as legal advice, sole source research and FCRA purposes; and the Annlex Chat page, which names pro se litigants first among its audiences, carries a line stating it is a research tool only, not legal advice, and to consult a licensed attorney.
That consumer facing disclosure at the point of use is what most records selling to the public lack. The competence dimension is present in outline, with attorneys told they remain responsible for verifying all authority before reliance. Held at B because jurisdiction limits are not named beyond the corpus being American case law, bar guidance is deferred to each practitioner's jurisdiction without engagement, and nothing speaks to supervising the paralegals the FAQ names as users. Read 15 September 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 or release testing, no bias or accuracy monitoring, no model card, no named owner and no external standard. The nearest material is a list of limitations in the terms and FAQ and a design statement on the Opinion Lens page that credibility rests on falsifiability, which describes a product choice rather than a governance mechanism. The gap has a specific shape here: the ten research patterns that route every question decide which opinions the model ever sees, and nothing describes how those patterns were built, tested or changed. Checked the Annlex Chat page, pricing, the FAQ, the terms and the Opinion Lens page on 15 September 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.
Retention and deletion are specific enough to hold the vendor to; the rest of the set is thin. Published: saved conversations kept up to one year then automatically deleted, a user toggle that stops saving, immediate and irreversible deletion of saved conversations, no history saved for users without an account, Google Analytics data deleted after 26 months with IP anonymisation, server access logs said to hold request metadata only, and named third parties with their data terms, being Anthropic (no training on API data, retention up to 30 days, longer on a safety trigger), Stripe for payments and Google Analytics.
Access, correction and deletion requests route to a published privacy address. Held at B on four gaps. The server infrastructure provider is referred to but not named, so the subprocessor list is incomplete. No access control practice is described. Security is stated only as reasonable measures including HTTPS, with nothing on encryption at rest. And no incident or breach practice is published. The third party section's statement that chat text is kept in no database also conflicts with the default on history described earlier in the same document. Read 15 September 2026.
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.
Liability is addressed through a standard clause that disclaims all of it. The terms provide the service as is with every warranty disclaimed, and exclude liability for any direct, indirect, incidental, special or consequential damages arising from use, with no cap figure because nothing is retained to cap. Disputes go to binding AAA arbitration under the Consumer Arbitration Rules seated in Charleston, South Carolina, with class action and jury waivers, under South Carolina law.
The recourse that does exist concerns availability rather than output: prorated credit or refund for a substantial outage, full refunds for billing errors, and 30 days notice with prorated refunds if the service is discontinued. The terms list the ways AI output can be wrong and place reliance at the user's risk. No indemnity, accuracy undertaking or correction route for wrong output was located. Read 15 September 2026.
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.
No integration into practice systems located. No document management, practice management, Word or Outlook add in, API or connector is published. Summaries and case briefs download as formatted documents, which is export rather than integration. The absence reads as a position rather than an oversight: the FAQ argues that tools reaching Claude through MCP connectors cannot qualify for Anthropic's Zero Data Retention while a direct API architecture can, so the vendor has chosen not to be an assistant plugin. Checked the Annlex Chat page, pricing, the FAQ, the terms and the Opinion Lens page on 15 September 2026.
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.
Cloud delivery is plain and little else is stated. The product is a hosted web application, the corpus is stated to sit on the vendor's own servers, and research queries are processed through Anthropic's Claude API, but no hosting provider, region, tenancy model or processing location is named, and the terms refer only to an unnamed server infrastructure provider. There are no deployment options to compare. Held at C because what processes a query and where the corpus is held are described, while the region and tenancy questions go unanswered. Read 15 September 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 independent security attestation located. No SOC 2, ISO 27001 or other certification is claimed, no trust centre exists, and security is described in the terms only as reasonable measures including HTTPS encryption, with no guarantee of absolute security. Stripe's PCI DSS standards are cited for payment handling, which covers Stripe and not Annlex. Checked the Annlex Chat page, pricing, the FAQ, the terms, the Opinion Lens page and the site footer on 15 September 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 models are named to a level most of this index does not reach, and change notification is the gap. The FAQ states that Annlex presently runs Anthropic's Claude Sonnet as its leading model, calling the Claude Messages API directly, that semantic search uses ModernBERT embeddings fine tuned for legal text by the Free Law Project, and describes the vendor's own contribution as an orchestration layer that directs leading models.
The provider's data terms are stated alongside: no training on API data, retention up to 30 days, Zero Data Retention not yet active. Held at B because no model version is pinned, the word presently signals change without any commitment to tell customers when it happens, and where the provider processes requests is not stated. Read 15 September 2026.
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 full price list is public and the unit is defined. Starter is $25 a month for 200 AI queries and Power is $75 a month for 600, both with a seven day trial that requires a card; a one time pack of 100 queries costs $10 and never expires; three AI queries are free without an account, and Opinion Lens allows three questions per opinion before signup. Boolean, semantic and hybrid search are free and unlimited. The pricing page defines what counts as a query, and the terms publish trial conversion, the absence of rollover, 30 days notice of price increases and the refund rules for packs and subscriptions.
Signup is self serve, so nothing is added for implementation, and only volume beyond the Power plan is by contact. One loose end: the refund terms refer to annual subscriptions, and no annual plan is published. Read 15 September 2026.
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.
Audience and use boundaries are stated precisely; corpus boundaries are not. The vendor names pro se litigants, law students, solo practitioners and small firms priced out of Westlaw and Lexis, paralegals and journalists, lists appropriate uses (case discovery, preliminary research, academic work, journalism) and prohibited ones (legal advice, sole source research, FCRA purposes), and says plainly the tool suits preliminary research rather than replacing verification.
The corpus is described as 10.5 million full text opinions from 3,355 federal and state courts, 1658 to the present, with 71 million citation links and a taxonomy of 20 legal areas and more than 1,125 concepts, updated quarterly from CourtListener's bulk export. Held at B because nothing on the vendor's own estate enumerates courts or date ranges per court, states what curation from CourtListener left out, or says that statutes, regulations and secondary sources sit outside the corpus.
The FAQ also describes opinions as retrieved live from CourtListener, while the Annlex Chat page and the quarterly cadence describe a stored copy. Read 15 September 2026.
5 public documents
The public pages on file for Annlex, with the recorded signals each one supports and the date it was last read. Open any of them and check the reading against the record.
-
annlex.com/terms4 signals
Client Data in Training, Prompt and Output Retention, Third Party Request and Subpoena Notice and 1 more
Read Sep 15, 2026
-
annlex.com/faq3 signals
Primary Law Corpus Provenance, Good Law Verification, Bar Guidance Alignment
Read Sep 15, 2026
-
annlex.com/opinion-lens1 signal
Refusal and Uncertainty Behaviour
Read Sep 15, 2026
-
annlex.com/pricing1 signal
Billing and Fee Posture
Read Sep 15, 2026
-
Fabricated Citation Record
Read Sep 15, 2026
From $25 per monthUSD, as published, never converted
- Searching the case law is free, with no account needed.
- The AI features are paid by the question: $25 a month buys 200 and $75 a month buys 600.
- If you do not want a subscription, $10 buys 100 questions that never run out.
- You can try three AI questions free before signing up, and both plans have a seven day free trial.
Metered on AI queries, defined as each Annlex Chat question, each AI case analysis and each synthesis request. Starter $25 per month for 200 queries; Power $75 per month for 600 queries; both monthly, auto renewing, with a seven day trial that requires a card and no rollover of unused queries. One time credit pack of 100 queries for $10 that never expire. Three AI queries free without an account, and three Opinion Lens questions per opinion before signup. Boolean, semantic and hybrid search free and unlimited. Volume beyond the Power plan by contact.
Implementation: None published. Signup and payment are self serve through Stripe.
Note: Terms publish 30 days written notice before any subscription price increase, a 7 day refund window on credit packs with no more than 10 queries used, and prorated refunds on outage or discontinuation. The refund terms mention annual subscriptions, and no annual plan is published.
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?
The published terms prohibit training on customer content. Not a policy page, the agreement.
The terms a user accepts by using the site carry the commitment in their privacy section: saved conversations are not used to train any AI model, the vendor's or anyone else's. The model provider limb is stated too, with Anthropic's commercial API terms described as excluding API data from training. Scope as written covers saved conversations, and unsaved queries are stated not to be kept by the vendor at all. Recorded as contractual because the privacy policy is section 10 of the terms document itself rather than a separate policy page.
Prompt and Output Retention
How long does the product keep what a lawyer typed, and can that be set to zero?
The customer controls the retention window, by product configuration or by contractual instruction, but zero retention is not stated as available.
Retention on the vendor's side is under the user's control: history saves by default for registered accounts, a Save history toggle stops it, saved conversations delete immediately and irreversibly, and anything kept is deleted automatically after one year. Zero is not available end to end and the vendor says so: queries pass through Anthropic's API, which may retain content up to 30 days and longer where a safety system is triggered, and Zero Data Retention is stated as not yet active.
The third party section of the same terms says chat text is kept in no database, which the history paragraph contradicts.
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.
No located material addresses segregation between users, teams or matters. The product is described around individual accounts with per account history, and no shared workspace or permission model is described. Checked the Annlex Chat page, pricing, the FAQ, the terms and the Opinion Lens page on 15 September 2026.
Third Party Request and Subpoena Notice
If someone subpoenas the vendor for a firm’s data, does the firm hear about it first?
Published terms or policy address disclosure to authorities or in response to legal process, and no commitment or reservation regarding customer notice is located anywhere. The vendor has told the customer that data can leave and has said nothing about whether the customer hears of it.
The terms state that saved conversations are not shared with third parties except as required to operate the service or where the law requires it. No commitment or reservation about notifying the user of a legal demand is located, and no transparency report is published.
Primary Law Corpus Provenance
Where does the law in this product come from, and does the vendor have the right to use it?
Sources are identified without stating the licence or rights basis.
Sources are named at dataset level with a stated cadence. The opinions are described as loaded from the CourtListener bulk export maintained by the Free Law Project, with historical material credited to the Harvard Law School Library Innovation Lab's Caselaw Access Project, the Library of Congress, Public.Resource.Org, Lawbox and Justia, and the data is stated to be updated quarterly. The rights basis is described only as publicly available legal data and public court records, which speaks to availability rather than a licence or public domain basis for each source, and no per court enumeration is published on the vendor's own estate.
Good Law Verification
Does the product tell you when the authority it just cited has been overruled?
The product instructs the reader to check the citation without performing the check.
The product tells the reader to verify and does not check subsequent history itself. The terms direct users to verify independently and consult primary sources and list output that does not reflect current law as a known failure, and the FAQ states attorneys remain responsible for verifying all authority. A citation network of 71 million links shows which cases cite an opinion without treatment flags, and the Verify link in Annlex Chat checks a characterisation against the opinion rather than whether the authority is still good law. No citator, licensed or computed, is named.
Refusal and Uncertainty Behaviour
What does the product do when the answer is not in the corpus?
The vendor describes refusal or abstention behaviour in public materials.
Documented for Opinion Lens, where Ask AI answers only from the open opinion and the vendor states that when the opinion does not answer, Annlex says so rather than guessing, calling that refusal the feature. The public demo on the page shows answered questions only, so the no answer path is described rather than shown. For Annlex Chat, the FAQ promises confidence levels where applicable without describing them, and no abstention path is stated.
Fabricated Citation Record
Does a public court record exist addressing fabricated or hallucinated legal citations in output from this product?
No court order, opinion or disciplinary record addressing fabricated or hallucinated legal citations produced by this product has been located as of the date shown. This is a statement about the public record on that one subject, not a finding about the product, and this signal is not a litigation history.
No court order, opinion or disciplinary record addressing fabricated or hallucinated legal citations in output from this product was located as of 15 September 2026. The tracker searched was the AI Hallucination Cases database maintained by Damien Charlotin, by product name across its full downloadable export, alongside a general search of the public record. This is a statement about the public record on that one subject as of that date. It is not a finding about the product, and this signal is not a litigation history.
Bar Guidance Alignment
Has the vendor engaged in public with the ethics opinions its buyers are bound by?
Public materials refer to professional responsibility in general terms without naming guidance.
The FAQ states that bar association guidance on AI use in legal practice is evolving and that practitioners should consult their own jurisdiction's rules. No ethics opinion, including ABA Formal Opinion 512, is named or mapped.
Billing and Fee Posture
Does the vendor address what happens to the bill when the work takes an hour instead of six?
Public materials claim time savings without addressing billing or disclosure, and the product sits inside a fee relationship between a lawyer and a client where those savings would change the bill.
Public material sells speed and price to the researcher, with case law searchable in seconds and relevant opinions surfaced quickly for solo and small firm practitioners, and says nothing about how AI assisted research should be billed or disclosed to a client. Part of the named audience sits outside any fee relationship (pro se litigants, students, journalists), which does not change the value for the practitioners the vendor also targets.
Outside Counsel Guideline Readiness
Can a firm get this vendor through a client’s AI clause without a bespoke negotiation?
A current subprocessor or model provider list is published.
The terms name the third parties that process data, being Anthropic for AI queries, Stripe for payments and Google Analytics, each linked to its privacy terms, and the FAQ names Claude Sonnet as the model. The server infrastructure provider is referred to without being named, so the list is incomplete, and no client facing disclosure material is published.
Court Disclosure Support
If a judge’s standing order requires an AI disclosure, can the product produce one?
No located public material addresses court disclosure or verification certification.
No located material addresses court disclosure orders or certification of AI use. Case briefs and summaries download as formatted documents and Opinion Lens output states it was generated from the one opinion alone, but no record of model used, sources retrieved or human verification is produced for a filing. Checked the Annlex Chat page, pricing, the FAQ, the terms and the Opinion Lens page on 15 September 2026.