L
LexChat

LexChat is an agentic AI platform for Turkish legal professionals, built by ÜÇ Yazılım Limited Şirketi in Istanbul and led from the idea stage by Ümit Çakmak, who earlier founded the low code backend platform Altogic. Its first open beta launched in April 2024, and it runs on the open source Agnost platform built by the same team. The database starts from more than 10 million collected court decisions, of which more than 3 million are filtered and analyzed, alongside more than 14,000 legislation items.

The assistant builds a research plan, runs sub agents in parallel, loads saved skills and produces files in a sandbox for each chat, citing decisions and statutes taken from the database and showing earlier statutory wording and changes in case treatment. Gemini and Claude run through Google Cloud Vertex AI. The editor tracks revisions in pleadings, opinions and contracts and exports UDF, PDF and DOCX. Professional Plus brings case records and filings from the UYAP court portal through a Chrome extension and tracks new activity and deadlines, and an MCP server lets Claude or ChatGPT draw on LexChat's research. One account works across the web, iOS and Android.

Monthly plans run from ₺2,600 for 250 assistant requests to ₺9,800 for Professional Plus, with a seven day trial that needs no card. Members of the Ankara and Kırklareli bars describe their use, and users rate it 4.5 out of 5 across 3,237 ratings.

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.

BB on AI CentralityThe models are the engine of a core capability, layered on a product that would still function without them as a document or workflow system.

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.

LexChat is sold as an agentic AI platform for legal professionals. The assistant builds a research plan, runs sub agents, loads saved skills and produces files in a sandbox for each chat, and research, drafting and file review all run through the models. The case law and legislation database, the versioned document editor and the case workspace would still open without them, but the product's main job, planned research and drafting with cited answers, would not.

Source: Vendor Published
BB on Citation Accuracy and Hallucination DisclosureGrounding is real and documented, with linked primary sources and a described retrieval method, short of published accuracy figures an outsider can test.

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.

Answers take case identifiers from LexChat's own database rather than the model's memory, after full text and semantic retrieval with reranking across filtered court decisions and legislation, and each citation links to the underlying decision or statute. Decision views can open the official source and show citing judgments, changes in precedent and later negative treatment where recorded, and statutes keep their amendment history. Results carry a relevance ranking, but no citation accuracy benchmark on a reproducible test set is given.

Source: Vendor Published
BB on Autonomy and Oversight ModelA written commitment that the models work alongside a supervising lawyer, with real review surfaces, short of the full control structure: commonly the threshold at which the system stops or what happens after it is wrong.

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 assistant shows its research plan and the time spent on each step as it runs, and Focused, Comprehensive and Deep Research modes set how widely it looks, with Deep Research splitting work into parallel subtasks. The editor tracks insertions and deletions against the original, takes accept or reject decisions and comments, and lets a lawyer return to an earlier version. The terms make the user responsible for verifying output and for final work. No confidence level at which the assistant holds back a legal conclusion is described.

Source: Vendor Published
BB on Operational and Outcome EvidenceReal deployment evidence with substance, short of full attribution or measurement: a named customer without figures, or figures without the named customer.

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.

Çağatay Çakır of the Ankara Bar describes using LexChat to find precedent and legislation with less time spent on research and drafting, and Ali Günaydın of the Kırklareli Bar describes changes to his daily research routine. Users rate the overall experience 4.5 out of 5 across 3,237 ratings. Neither named account comes with timed work, a sample or a period.

Source: Vendor Published
BB on Privilege and Confidentiality PostureSubstantive published commitments on confidentiality and training use, short of the full picture: commonly silence on segregation between users or matters, or on what the underlying model provider may retain.

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.

The subscriber owns uploaded material, and the terms limit product improvement to aggregated and anonymized usage data and bar training on user inputs and directly identifiable outputs without express consent for a personalized feature, subject to other provisions of the terms. Google Cloud Vertex AI processes text for Gemini and Claude, and only the information a task needs goes to the provider. Each chat runs in an isolated workspace, and team members share selected chats, documents and case files by role. Matter walls inside a firm and what the model provider keeps are not described.

Source: Vendor Published
AA on UPL and Professional Responsibility PostureThe vendor states plainly what the product is and is not, who may use it, and how it supports a lawyer’s competence and supervision duties. Jurisdiction limits are named and any consumer facing surface carries a clear disclosure.

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. Where the advice line is not the duty a product raises, the axis is read through the nearest professional duty it does raise: judicial conduct rules and the reviewing duty for products sold only to courts, and the duty to bill for time actually spent for products that draft time entries.

LexChat frames its output as information and research material, does not practice law, forms no attorney client relationship and tells users to consult a competent lawyer before any legal decision. Use is limited to people working in law with legal knowledge, such as lawyers, judges, prosecutors, legal counsel, law faculty and trainees, who must be able to evaluate and verify output. Statutory history, cassation treatment and tracked revisions give them material to check a draft, and the platform is built around Turkish law and the UYAP court system.

Source: Vendor Published
BB on AI Governance and Bias DisclosureA published governance framework with real substance, short of testing results or a named owner.

AI Governance and Bias Disclosure

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

Raw court decisions are screened for quality before they enter retrieval, parties, claims and outcomes are separated, legislation is tracked by effective period, and case identifiers come from the database. Each release is developed with feedback from lawyers and tested on real files, and teams get usage, quota and audit logs. No owner of model testing and no results on uneven output across areas of law or kinds of user are given.

Source: Vendor Published
BB on AI Safety and Data StewardshipSubstantive published policy covering most of the ground, short of the full set: commonly no named subprocessor list or no stated incident practice.

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.

Transfers, stored conversations and documents are encrypted, access is restricted by role, and each chat runs in an isolated workspace with routine backups and service monitoring. Conversations, documents and workspace content stay until the user deletes them or closes the account, after which data is deleted or deidentified except records the law requires. Google Cloud Vertex AI is named as the processor for Gemini and Claude, alongside mobile distribution, authentication and diagnostics suppliers. No deadline is set for telling customers of an incident or for removing processor copies.

Source: Vendor Published
CC on AI Liability and RecourseLiability is addressed only through a standard limitation clause that disclaims the exposure the product creates.

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 for reliance on platform outputs is disclaimed, indirect losses are excluded subject to mandatory law, and no warranty of accuracy, completeness or reliability is given. Users remain responsible for verifying the research and any draft they send out. No correction, indemnity or refund covers a materially wrong answer or a missed legal development.

Source: Vendor Published
AA on Practice Systems Integration DepthDocumented, verifiable integrations into the systems legal work already lives in, with the depth described: what syncs, in which direction, and what a firm must configure.

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.

Professional Plus adds a Chrome extension that, once the user signs in to the UYAP lawyer portal, brings case metadata, procedural history and selected court documents into a LexChat case file, matches existing cases and filters routine administrative records, then tracks new activity and deadlines. Drafts export as UDF for upload to the court system, as well as PDF and DOCX. A separate MCP server, with 250 to 1,000 calls a month by plan, lets Claude or ChatGPT retrieve decisions and legislation with source references over an OAuth connection.

Source: Vendor Published
BB on Deployment Model and Data ResidencyDeployment model is stated clearly with partial residency detail, or residency is offered without the processing location being addressed, or the tenancy model is stated on its own with no residency detail published.

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.

Delivery is cloud software with one account across the web and the iOS and Android apps, and the role model separates content between users and organizations while each chat runs in its own workspace. Google Cloud Vertex AI runs inference, and some storage suppliers may sit outside Turkey under local transfer rules. The specific storage and compute regions are not stated.

Source: Vendor Published
DD on Security Certifications and Trust CenterNo independent security attestation located.

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.

Communications and stored documents are encrypted, access is limited to authorized users, chats run in separate workspaces, and backups, service monitoring and role based sharing cover team material. Mobile apps keep authentication tokens in secure device storage, and users hold rights under Turkey's personal data law. No independent security attestation covers the product.

Source: Vendor Published
BB on Model Supply Chain DisclosureThe supply chain is partly disclosed: providers named without change notification, or architecture described without the providers.

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.

Google Cloud Vertex AI runs Gemini and Anthropic Claude for text and document processing, and the platform picks a model by task, with a fallback when one is unavailable. Only the information a task needs goes to the provider. Model versions, the processing region and notice of a model change are not stated.

Source: Vendor Published
BB on Commercial TransparencyReal pricing is published for part of the range, with enterprise tiers withheld, or the unit and structure are stated without the figure.

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.

Monthly plans renew automatically at prices including VAT. Başlangıç, the starter plan, is ₺2,600 for 250 assistant requests and 250 MCP calls with team use for 2 to 10 people, Profesyonel is ₺4,700 for 500 of each with project management, and Professional Plus is ₺9,800 for 1,000 with UYAP case work, case file questions and deadline reminders. Prepaid usage packs are sold separately, deeper research can use more than one unit, and the seven day Professional Plus trial needs no card. Corporate and custom setups are quoted.

Source: Vendor Published
AA on Firm and Practice CoverageWho the product serves is documented precisely: firm segments, in house and government use, and the practice areas actually supported, with the limits stated.

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.

The contract limits the software to people working or training in law, including sole practitioners, firms, in house counsel, judges and prosecutors, and the platform is built for Turkish law. Case law covers Turkish national and regional courts, including the Court of Cassation, Council of State and Constitutional Court, along with European Court of Human Rights decisions, with a daily Official Gazette and case law bulletin.

Pleadings, case monitoring, contract review and legislation research are supported, and UYAP case work sits in Professional Plus.

Source: Vendor Published
Sources on file

6 public documents

The public pages on file for LexChat, 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.

Pricing

₺2,600 per month

TRY, as published, never converted
  • The Starter plan costs ₺2,600 per month.
  • Higher plans include more research and case features.
  • You can try Professional Plus for seven days without providing a card.

Starter is ₺2,600 per month for 250 assistant requests and 250 MCP calls. Professional is ₺4,700 for 500, and Professional Plus is ₺9,800 for 1,000 with UYAP case work. Individual subscriptions renew monthly, prepaid usage packs are also available, and monthly subscription rates include VAT.

Implementation: Individuals can open an account and start a seven day Professional Plus trial without a card. Enterprise onboarding and team prices are quoted.

Note: Professional Plus includes UYAP case imports. Deeper research can consume more than one query unit. Additional quota packs are separate from the subscription, and the terms allow their availability to vary.

Legal Signals

What each signal means

A 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.

Confidentiality and Privilege

Client Data in Training

Can material a lawyer puts into this product be used to train a model?

Opt in

Training occurs only where the customer has affirmatively enabled it.

The terms bar training on user inputs and directly identifiable outputs without express consent for a personalized feature, subject to other provisions, and limit product improvement to aggregated, anonymized usage data.

Source: Vendor Publishedsize özel bir özellik için açık rızanız olmaksızınAs of Nov 21, 2026Evidence

Prompt and Output Retention

How long does the product keep what a lawyer typed, and can that be set to zero?

Customer controlled, no zero option

The customer controls the retention window, by product configuration or by contractual instruction, but zero retention is not stated as available.

Conversations, documents and workspace content stay until the user deletes an item or closes the account, after which data is deleted or deidentified, apart from records the company must keep by law.

Source: Vendor Publishedsiz silene veya hesabınız kapatılana kadar saklanırAs of Nov 21, 2026Evidence

Ethical Walls and Matter Segregation

Does retrieval respect the firm’s ethical walls, or can the model read across them?

Own model, documented

The product maintains its own permission model, documented, requiring the firm to keep it aligned.

Each conversation has an isolated workspace, and members share selected conversations, documents, case files, projects and tasks with colleagues by role.

Source: Vendor PublishedSohbet, doküman, dava dosyası, proje ve görevlerinizi ekip üyelerinizle rol bazında paylaşınAs of Nov 21, 2026Evidence

Third Party Request and Subpoena Notice

If someone subpoenas the vendor for a firm’s data, does the firm hear about it first?

Disclosure addressed, notice absent

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 privacy notice under Turkey's personal data law allows required disclosures to authorized public bodies, without promising the subscriber advance notice of a demand.

Source: Vendor PublishedYetkili Kamu Kurum ve KuruluşlarınaAs of Nov 21, 2026Evidence
Accuracy and Authority

Primary Law Corpus Provenance

Where does the law in this product come from, and does the vendor have the right to use it?

Sources named, basis unstated

Sources are identified without stating the license or rights basis.

Answers draw on Turkish court decisions and legislation from public sources, refreshed daily, with case identifiers taken from the database rather than the model and no licensing basis stated for each source.

Source: Vendor PublishedCevaptaki her künye modelin hafızasından değil veritabanından geliyorAs of Nov 21, 2026Evidence

Good Law Verification

Does the product tell you when the authority it just cited has been overruled?

Own treatment signal

The vendor computes and surfaces subsequent history itself, with the method described.

Decision views show citation links, changes in precedent and later negative treatment where recorded, and statutes keep their amendment history over time.

Source: Vendor PublishedMaddeleri değişiklik geçmişiyle birlikte tutuyorAs of Nov 21, 2026Evidence

Refusal and Uncertainty Behavior

What does the product do when the answer is not in the corpus?

Not addressed

No located public material addresses what the product does when it cannot ground an answer.

The assistant plans its research and reranks retrieved material before citing it, and Deep Research splits the work into subtasks, with no stated response for a question that has no supporting authority in the database.

Source: Operator VerifiedAs of Nov 21, 2026

Fabricated Citation Record

Does a public court record exist addressing fabricated or hallucinated legal citations in output from this product?

None located

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.

Damien Charlotin's AI Hallucination Cases database lists no court decision involving fabricated citations from LexChat.

Source: Operator VerifiedAs of Nov 21, 2026Evidence
Professional Responsibility

Bar Guidance Alignment

Has the vendor engaged in public with the ethics opinions its buyers are bound by?

Generic reference

Public materials refer to professional responsibility in general terms without naming guidance.

The terms restrict use to legal professionals who can evaluate and verify output and tell users to consult a competent lawyer, without tying that to a named Turkish bar opinion on AI.

Source: Vendor PublishedÇıktıları değerlendirme ve doğrulama kapasitesineAs of Nov 21, 2026Evidence

Billing and Fee Posture

Does the vendor address what happens to the bill when the work takes an hour instead of six?

Savings claims only

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.

LexChat is sold on saving lawyers time in research, review and drafting, with no guidance on recording AI assistance on a client invoice.

Source: Vendor PublishedZamandan tasarruf edip iş kalitesine odaklanmakAs of Nov 21, 2026Evidence

Outside Counsel Guideline Readiness

Can a firm get this vendor through a client’s AI clause without a bespoke negotiation?

Subprocessors listed

A current subprocessor or model provider list is published.

The privacy notice names Google Cloud Vertex AI as the inference processor for Gemini and Claude, along with mobile distribution, authentication and diagnostics suppliers.

Source: Vendor PublishedGoogle Cloud Vertex AIAs of Nov 21, 2026Evidence

Court Disclosure Support

If a judge’s standing order requires an AI disclosure, can the product produce one?

Partial record

Some elements of the record are available, short of a document level export.

Chat transcripts can be exported, and teams keep document revisions, usage and audit logs, without a record certifying human verification for a court.

Source: Vendor Publishedkullanım istatistikleri, kota kullanımı ve denetim kaydıAs of Nov 21, 2026Evidence
Contact

Correct a record, or ask how something was graded

Every grade and every signal on this index is drawn from public sources and dated. If a record is wrong, out of date, or missing an artifact the index did not locate, send the source and it will be reviewed and the record redated. Vendors are welcome to submit documentation. Nothing on this index is for sale, including a listing, a placement, or a grade.

AI Legal Index

The AI Legal Index is an independent index that tracks changes to AI vendors in legal. It holds 670 vendors across 9 categories, each graded on the same 15 capability axes and recorded against 12 legal signals, from public sources. No vendor pays for inclusion, placement, or rating.

Index Status
Last index update
November 21, 2026
The AI Legal Index is an editorial reference. It is not a regulatory body, not a law firm, and nothing published here is legal advice or a recommendation to retain or avoid a vendor. Records are verified against published sources, bar guidance and public court records. Where a record reads not addressed, the material was not located in public sources on the date shown. See the Methodology page for evaluation standards and limitations.
© 2026 AI Legal Index
3801 N Capital of Texas Hwy, Ste E240 · Austin, TX 78746