Centari vs Syntracts: how they compare in 2026
Centari and Syntracts both extract defined data points from a law firm's contracts and deal documents and feed them into the firm's knowledge systems. Centari sits in the top two bands on ten of fifteen axes and Syntracts on six of fifteen, and the difference is where the work happens. Syntracts runs entirely inside the firm's own environment, on small open source models fine tuned for each customer, and says no document leaves the firm and no third party model is called. Centari is a hosted platform that names OpenAI and Anthropic as its AI providers. Centari leads on what surrounds the extraction. It names Fried Frank, Ropes & Gray and Gilbert + Tobin with senior users quoted, and its terms state that it is not a law firm. Every value cites its source language, and a Tasks view tracks human verification. Syntracts names no customer, publishes no terms and has completed only a SOC 2 Type I audit. Its models are fine tuned on synthetic data generated from each customer's own documents.
At a glance
All 15 axes, side by side
The same grid applied to every vendor in the index, graded from public sources. 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.
Centari sells the database its AI builds. The Deal Reasoning Engine reads a firm's credit agreements, limited partnership agreements and M&A closing sets and turns them into structured, citation-backed data points, and the platform overview describes multi-stage reasoning that resolves defined terms, traces cross-references and evaluates conditional logic in sequence rather than skimming a document as flat text. Everything else a firm buys runs on that output: precedent search, market benchmarking, Views dashboards, Projects grids and the Centari Intelligence sidebar. The MCP server and Microsoft Copilot integration let a firm's other AI tools query the same data, and they belong to the integration picture rather than to what Centari itself generates. Remove the models and there is nothing in the database to search or chart. Verified 20 September 2026.
The models are the product. Syntracts exists to extract defined data points from contracts using models fine-tuned for each customer, and to deliver that structured output into the firm's other systems; the review screen and the API carry the models' output. Without the models there is nothing to deliver. Verified 22 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.
Every extracted value comes back with a citation, and nothing about accuracy is measured. The platform overview says each data point traces to its source language and connects to related provisions across the deal documents, with a verification view for checking it, and the 24 August 2026 release post says the Centari Intelligence sidebar answers with citations to the source language that a partner can open in one click. The method behind the extraction is described rather than asserted: defined terms resolved, cross-references traced, conditional logic evaluated in sequence. What a buyer cannot weigh is performance. The site claims attorney-level precision and unmatched accuracy with no test set, no score and no failure mode named, so the only check on a given field is the firm's own reviewer. The citations run to the firm's own agreements rather than to primary law. Verified 20 September 2026.
Accuracy is claimed, not measured. The home page promises no hallucinations because the models are custom trained, and shows headline statistics for data extraction accuracy without a figure; the company's releases describe the output as highly accurate and verifiable. No test set, accuracy figure or error rate is published, and nothing describes how an extraction links back to the clause it came from. Verified 22 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.
Centari is built around people checking what the AI extracts, and it gives a firm a way to track that checking. The 24 August 2026 release post describes the product as designed for human in the loop verification and introduces Tasks, which gathers every open verification step across Databases and Projects so an owner can assign reviewers and see which data points a person has checked. The platform overview describes a verification view beside each extraction. Projects are kept apart from the governed record: nothing in a Project writes back to a Database. What is not published is where the system itself draws a line. Nothing says when extraction stops or flags low confidence, and nothing says what unverified output must not be used for, so those rules are left to each firm. Verified 20 September 2026.
A review screen is offered and little more is said. The home page describes an interface for confirming each extraction and correcting errors, with corrections used to improve the models over time. Nothing commits that a lawyer or knowledge manager reviews output before it enters a database or an AI assistant, and no threshold, limit or audit trail is described. Verified 22 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.
Centari names large law firm customers and puts senior people on the record, but publishes no measured result. The homepage, platform overview and For Law page carry attributed endorsements from Fried Frank (Global Head of Innovation and Knowledge), Willkie (Counsel, Asset Management), Ropes & Gray (Counsel), Wilson Sonsini (Senior Manager of KM) and Gilbert + Tobin (Partner, Corporate Advisory), and from Sentinel Global's general counsel on the fund side. The blog lists a Gilbert + Tobin case study dated 30 April 2026 describing a firm wide M&A deployment, and announcements of the Fried Frank and Ropes & Gray adoptions. No figure for time saved, accuracy or outcomes is published. The case study links on the site did not open a readable page on 20 September 2026, so the detail of the Gilbert + Tobin deployment could not be read. What is on the record is endorsement by named senior users, not a measured result. Verified 20 September 2026.
Results without names. The company's June 2025 release announces a multi-year enterprise partnership with an unnamed AmLaw 25 firm after a six-month pilot, and says Syntracts was one of two companies selected for A&O Shearman's Fuse incubator, which is a programme selection rather than a customer result. The figure quoted in coverage of its October 2025 funding, an 80 per cent cut in contract review time, carries no customer or method, and the home page's own statistics display no numbers. Verified 22 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.
The commitments about client material are specific, and they live on a security page rather than in a contract. The security page states that customer data is siloed and never commingled, with single tenant deployments available, that it is never used to train or fine tune the underlying models, that it is encrypted in transit and at rest with bring your own key supported, and that access can be controlled down to the data point with SSO and ethical wall integration. The Terms of Use dated 16 September 2025 say nothing about customer content and state that they sit alongside any other agreement; that other agreement is not published, so a buyer cannot read any of these promises as a term before signing. Nothing addresses privilege or work product in the deal documents a firm uploads, how long they are held, or what OpenAI and Anthropic, named as AI providers in the Trust Center, may retain. For a product that ingests a firm's whole deal history, that last gap is the one a general counsel will raise first. Verified 20 September 2026.
The architecture carries the commitment. The home page says Syntracts runs entirely within the customer's controlled environment, and the company's releases say no data leaves client systems or reaches third-party language models or APIs and that each customer's models are built for that customer. The home page says only synthetic data is used to fine-tune the models, never the customer's data, while the June 2025 release says that synthetic data is generated from each customer's own legal documents, so a buyer should read the two together. No agreement is published, and privilege and work product are not addressed by name. Verified 22 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. 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.
Section 4 of the Terms of Use, dated 16 September 2025, is direct about what Centari is not. It states that the company is not a law firm, attorney, staffing firm or lawyer referral service, that nothing on the service is legal advice, that no attorney-client relationship arises, and that employees who are licensed attorneys are not practising law in that capacity. The audience is professional throughout: transactional practices, knowledge teams, in-house legal and investment funds. The other half of the question is untouched. Nothing addresses how a supervising lawyer should treat extracted terms that feed advice, negotiation positions or the External Views dashboards a firm shares with its own clients, and no jurisdiction limits are stated. Verified 20 September 2026.
Checked the home page and the company's two 2025 releases on 22 September 2026, and searched for published terms. Nothing states what the product is and is not, that its extractions are not legal advice, or how it supports the supervising lawyer's duties, and no terms are published. Verified 22 September 2026.
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.
What Centari publishes is how a firm checks the AI's work, not how Centari builds and controls it. Calibration of each firm's taxonomy by domain experts is described on the homepage and the For Law page, an account team of attorneys and engineers runs it, and the 24 August 2026 release post describes the Tasks verification workflow. That tooling helps a firm govern its own use; it says nothing about how Centari tests and controls its models. No accountable owner inside the company is named, nothing describes what is tested before a release ships, no evaluation result is published, and nothing addresses whether extraction quality is uneven across document types, drafting styles, jurisdictions or languages. Checked the homepage, platform overview, For Law, security and about pages, the blog and the Trust Center on 20 September 2026. Verified 20 September 2026.
Checked the home page and the company's two 2025 releases on 22 September 2026. No AI governance framework, accountable owner, testing before release or bias disclosure was located. Verified 22 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.
The controls protecting the data are published; what happens to a firm's documents afterwards is not. The security page states encryption in transit and at rest with bring your own key, siloed data with single tenant options, access control down to the data point, SSO and regular penetration testing, and the Trust Center lists security controls including a record of incidents and a subprocessor list. No retention period for uploaded deal documents or for questions put to the product is published, no deletion commitment applies on termination, and no incident notification timeline was located. The Privacy Policy dated 16 September 2025 covers personal information collected through the website and services rather than the contracts a firm loads, and no customer agreement or data processing addendum is published. Verified 20 September 2026.
The position is architectural and unwritten. The company says documents stay in the customer's own environment and no third-party model is called, which puts retention and deletion largely in the customer's hands. No privacy policy, retention or deletion commitment, subprocessor list or incident practice is published for what Syntracts itself handles, such as support access or the synthetic data derived from customer documents. Verified 22 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.
What Centari refuses is published in full; what it stands behind is not. The Terms of Use dated 16 September 2025 provide the service as is and disclaim warranties of accuracy, reliability and fitness (section 15), cap total liability at the greater of fees paid in the prior six months or one hundred US dollars (section 16), and require the customer to indemnify Centari (section 17). No indemnity runs the other way, no warranty attaches to extracted output, and no insurance position appears. The Terms state that they sit alongside any other agreement, and that agreement, where an enterprise buyer's real allocation of loss would sit, is not published, so the only readable position is the one that allocates the risk of a wrong extraction to the firm. Verified 20 September 2026.
Checked the home page and the company's two 2025 releases on 22 September 2026, and searched for published terms. No customer agreement or terms are published, so nothing states who bears the loss when an extraction is wrong. Verified 22 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.
The connections are named and none of them is documented. The platform overview says Centari's MCP Server makes a firm's deal intelligence available to the AI tools it already uses, the blog lists a 16 June 2026 announcement of that server and a one-click Microsoft Copilot integration, and the security page names SSO and ethical wall integration. There is no integrations page, no developer documentation and no API reference, and the June announcement does not open a readable page. Nothing states how deal documents get from a document management system such as iManage or NetDocuments into Centari, which is the step a firm has to plan and staff, or what the Copilot integration exposes to a user's assistant. Projects grids are described as exportable. Verified 20 September 2026.
Integration is claimed in general terms only. The home page says contracts can be ingested from the firm's document management system and results inserted into any existing database or workflow, and the company describes the platform as API-first, feeding dashboards and AI assistants. No document management system, knowledge platform or assistant is named, and no API documentation is published. Verified 22 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.
The tenancy model is stated and the geography is not. The security page says customer data is siloed and never commingled, that single tenant deployments are available, that bring your own key encryption is supported, and that regional hosting and processing are available for customers around the world. No region is named, nothing says which arrangement or tier carries single tenancy, and nothing separates where the database sits from where OpenAI and Anthropic process the text of a firm's agreements. A firm with a UK or EU residency requirement would have to establish all of that in a sales conversation. Verified 20 September 2026.
Deployment in the customer's environment is the core of the offer. The home page says Syntracts operates entirely within the customer's controlled environment, and the company's releases describe full on-premises deployment in which processing and storage both stay inside the firm's systems, with no third-party model calls. What differs between deployment options, the infrastructure required and any hosted alternative are not published. Verified 22 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.
Centari states SOC 2 Type II and ISO 27001 certification and regular third party penetration testing on its homepage and security page, and links a Trust Center hosted by Sprinto. Only part of the Trust Center could be read on 20 September 2026. The part that could be read shows a compliance section with two entries marked compliant, a list of controls and a subprocessor list. It names no auditor, report period or scope, and no route to obtain the reports, so the certifications stand as the vendor's statement until a buyer sees the reports. Verified 20 September 2026.
A point-in-time attestation, with more promised. The home page states that Syntracts has completed a SOC 2 Type I audit and is working to complete ISO 27001 certification and a SOC 2 Type II audit. The Type I report is not offered, no auditor or date is given, and the two further audits are not yet claimed as complete. Verified 22 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 providers are named; the models are not. Centari's Trust Center carries a subprocessor list naming OpenAI and Anthropic as AI providers and Google as a cloud provider. Only part of that list could be read on 20 September 2026, so it may name others. The marketing pages refer to 'our underlying AI models' and to a patent pending Deal Reasoning Engine without identifying either: no model, no version, and nothing about where the AI providers run. No commitment to tell customers when the models behind their extractions change was located on the security page, the platform overview or the Trust Center, which matters here because a firm's benchmarks are built on extractions made by whatever model was running at the time. Verified 20 September 2026.
The architecture is described without the base models. The company says it uses its own stack of small open-source language models, fine-tuned for each customer on synthetic legal data and run inside the customer's environment, with no third-party model or API involved. Which open-source models are used, and whether customers are told when they change, is not published. Verified 22 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.
Nothing about price is published, including the unit of charge. Checked the homepage, the full navigation and footer, the platform overview, the For Law and For Finance pages, the security and about pages, the Terms of Use and the blog on 20 September 2026: there is no pricing page, no tier names, no unit, no trial and no figure anywhere. Every route offered is a demo request. Section 13 of the Terms of Use reserves the right to charge fees for the services without stating what they are. Verified 20 September 2026.
Checked the home page and the company's two 2025 releases on 22 September 2026. No price, tier or unit of charge is published; access is by demo request. Verified 22 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.
Who the product is built for is set out clearly; where it stops is not. The For Law page addresses transactional practices and names partners, knowledge management, associates and business development as its users, and the For Finance page addresses investment funds across legal, investor relations, finance and compliance. Document types are named rather than implied: credit agreements, limited partnership agreements and M&A closing sets, with the work described as high stakes M&A, fund formation and financings. The demo form offers law firm, in-house legal, financial services and government. Nothing states what falls outside, such as litigation material, agreements in other languages, or deal types for which the firm's taxonomy has not been calibrated, and calibration is how every deployment starts. Verified 20 September 2026.
The buyer and the work are specific: knowledge management teams at large law firms, and corporate legal teams, extracting defined data points from contracts to build deal profiles and knowledge databases. What the product does not handle, by document type, language or firm size, is not stated. Verified 22 September 2026.
The 12 legal signals, side by side
Recorded rather than graded. These are the questions a practitioner has to answer before a tool touches a client matter, and the answers are taken from public material only.
Client Data in Training
Can material a lawyer puts into this product be used to train a model?
The security page and homepage state that customer data is never used to train or fine-tune Centari's models. No published agreement carries the commitment: the Terms of Use (16 September 2025) are silent on customer content and supplement an unpublished customer agreement.
The company's June 2025 release says its models are trained on synthetic legal data generated from each customer's own legal documents, and the home page says corrections help the system learn and improve over time; the home page also says only synthetic data, never the customer's data, is used to fine-tune the models. Customer documents therefore shape a model built for that customer. The qualifiers the company states are that the training data is synthetic, the model is per customer, and it runs in the customer's own environment. No agreement is published.
Prompt and Output Retention
How long does the product keep what a lawyer typed, and can that be set to zero?
Checked the security page, the platform overview, the Terms of Use, the Privacy Policy, the 24 August 2026 release post and the Trust Center on 20 September 2026. No retention period is stated for uploaded deal documents, for questions put to the Intelligence sidebar or for extracted output, and no deletion commitment applies on termination; the security page says only that a customer's data is always under its control.
Checked the home page and the company's two 2025 releases on 22 September 2026. Documents are described as staying in the customer's own environment, but no retention or deletion position is published for what Syntracts holds, including the synthetic data derived from customer documents.
Ethical Walls and Matter Segregation
Does retrieval respect the firm’s ethical walls, or can the model read across them?
The security page claims access control down to the data point, SSO and ethical wall integration, and siloed customer data. No published material describes which systems the wall integration reads from or how access is enforced at query time.
Checked the home page and the company's two 2025 releases on 22 September 2026. Contracts can be ingested from the firm's document management system, but nothing says whether its access controls or ethical walls carry through to the extracted data in the knowledge management database.
Third Party Request and Subpoena Notice
If someone subpoenas the vendor for a firm’s data, does the firm hear about it first?
The Privacy Policy (16 September 2025) permits disclosure of information to comply with legal process and says nothing about notifying the customer. It covers personal information; no published term addresses requests for customer deal documents, and the Terms of Use are silent on the point.
Checked the home page and the company's releases on 22 September 2026, and searched for published terms or a privacy policy. Nothing addresses requests from authorities or other third parties for customer data.
Primary Law Corpus Provenance
Where does the law in this product come from, and does the vendor have the right to use it?
Checked the homepage, the platform overview, the For Law page and the security page on 20 September 2026. Centari works over the deal documents a firm loads and its benchmarks are drawn from that material; no external legal corpus is described, so provenance here is the firm's own.
Checked the home page and the company's releases on 22 September 2026. The product works on each customer's own contracts, and no body of primary law behind its output is identified.
Good Law Verification
Does the product tell you when the authority it just cited has been overruled?
Checked the homepage, the platform overview, the For Law page and the 24 August 2026 release post on 20 September 2026. Centari cites clauses in the firm's own agreements rather than legal authority, so the question of subsequent history does not arise for this product and nothing addresses it.
Checked the home page on 22 September 2026. The product extracts contract data rather than citing legal authority, and nothing addresses checking authority for subsequent history.
Refusal and Uncertainty Behavior
What does the product do when the answer is not in the corpus?
Checked the homepage, the platform overview, the For Law page, the security page, the 24 August 2026 release post and the Trust Center on 20 September 2026. Nothing describes what happens when the engine cannot find a data point or the Intelligence sidebar cannot answer, and no confidence or grounding score is exposed. Verification runs through Tasks, which routes finished output to a human reviewer rather than describing any point at which the system declines to answer.
Checked the home page and the company's releases on 22 September 2026. A review screen lets users confirm or correct extractions, but no confidence indicator or path in which the model declines an extraction it cannot make reliably is described.
Fabricated Citation Record
Does a public court record exist addressing fabricated or hallucinated legal citations in output from this product?
Searched the AI Hallucination Cases database maintained by Damien Charlotin on 20 September 2026 on the product name Centari and the corporate name Centari, Inc. 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, and the exposure is structurally lower than for a research tool: Centari cites a firm's own agreements and is sold for transactional work rather than for court filings.
Searched the AI Hallucination Cases database maintained by Damien Charlotin on 22 September 2026 for Syntracts, and no recorded case was returned. 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.
Bar Guidance Alignment
Has the vendor engaged in public with the ethics opinions its buyers are bound by?
Checked the homepage, the platform overview, the For Law page, the security and about pages, the Terms of Use and the blog on 20 September 2026. Section 4 of the Terms states that Centari is not a law firm and gives no legal advice, but no material engages with ABA Formal Opinion 512, a state bar opinion or any other named ethics guidance on the use of AI.
Checked the home page and the company's releases on 22 September 2026. No material refers to lawyers' professional or ethical obligations or names any ethics opinion.
Billing and Fee Posture
Does the vendor address what happens to the bill when the work takes an hour instead of six?
The For Law page says associates find on-point precedent in seconds to bring to drafts and redlines, and the platform page contrasts the engine with manual work, which is work billed to clients on live deals. Much of the product also serves pitch and knowledge work that bills no client. No material addresses fee or disclosure treatment.
The home page promises reduced costs, less manual data entry and a reduction in deal profiling time, and coverage of the October 2025 funding cites an 80 percent cut in contract review time. Nothing addresses how work done with the product is billed or disclosed to a firm's clients.
Outside Counsel Guideline Readiness
Can a firm get this vendor through a client’s AI clause without a bespoke negotiation?
Centari's Trust Center carries a subprocessor list that names OpenAI and Anthropic as AI providers and Google as a cloud provider. Only part of the list could be read on 20 September 2026, so it may name others. No material written for a firm to pass to its own clients, such as an AI use summary or a response to outside counsel guidelines, was located.
Checked the home page and the company's releases on 22 September 2026. No subprocessor or model provider list is published; what a firm can pass to a client is the company's statement that processing stays in the firm's environment with no third-party model or API.
Court Disclosure Support
If a judge’s standing order requires an AI disclosure, can the product produce one?
Every extracted data point cites its source language, and Tasks records which data has been verified by a human reviewer. The product serves transactional work and nothing addresses court disclosure or records which model produced an output.
Checked the home page and the company's releases on 22 September 2026. No record of AI involvement, export of that record or disclosure guidance is described.
The questions both sides leave open
Derived from the records above rather than written, so it cannot favor either vendor. Take these into both conversations and ask each side the same question.
- Commercial Transparency
- Prompt and Output Retention
- Primary Law Corpus Provenance
- Good Law Verification
- Refusal and Uncertainty Behavior
- Bar Guidance Alignment
Which one fits
Choose Centari if
- You want named peers using it on live deal work. Centari quotes senior users at Fried Frank, Willkie, Ropes & Gray, Wilson Sonsini and Gilbert + Tobin, and published a Gilbert + Tobin case study in April 2026 on a firm wide M&A deployment.
- You want to share deal data with your own clients. Centari's External Views let a firm share white labeled dashboards with clients, and its Projects build one off extraction grids that do not write back into the governed database.
- You want the data inside the assistants your lawyers already use. Centari offers an MCP server and a Microsoft Copilot integration, and its Intelligence sidebar answers questions with citations to source language a partner can open in one click.
Choose Syntracts if
- Your policy bars client documents leaving the firm. Syntracts runs entirely inside the firm's own environment, with processing and storage on premises, and states that no data leaves client systems and no third party language model or API is called.
- You want a model built for your firm alone. Syntracts fine tunes small open source models for each customer on synthetic data generated from that customer's documents, and uses reviewers' corrections to improve that model over time.
- You need extracted data delivered into your own knowledge systems. Syntracts ingests from the firm's document management system, lets knowledge managers confirm or correct each extraction on a review screen, and delivers results through an API into databases, dashboards and AI assistants.
In summary
Centari
Centari is a deal intelligence platform from New York for transactional law firms and investment funds, turning credit agreements, fund documents and M&A closing sets into a searchable, citation backed database calibrated to each firm's taxonomy by an account team of attorneys and engineers. Firms use it for precedent search, term benchmarking, matter profiles and client dashboards, with an Intelligence sidebar, an MCP server and a Microsoft Copilot integration. The AI Legal Index grades it in the top two bands on ten of fifteen capability axes. Its terms state that it is not a law firm, and it names Fried Frank and Gilbert + Tobin among its customers. As of 20 September 2026 the index located no price, retention period or measured accuracy.
Syntracts
Syntracts, from Syntracts Inc. of Washington, DC, is a contract intelligence platform that runs entirely inside a law firm's or legal department's own environment, extracting the data points a knowledge management team defines with small models fine tuned for each customer and delivering results through an API into knowledge databases and AI assistants. The AI Legal Index grades it in the top two bands on six of fifteen capability axes, with an A on AI centrality. It says no data leaves the customer's environment and no third party model is called, and it has completed a SOC 2 Type I audit. It was selected for A&O Shearman's Fuse incubator. As of 22 September 2026 the index located no published terms, named customer or price.
Questions buyers ask
Centari vs Syntracts: which is better for law firm deal data?
On published evidence Centari sits in the top two bands on ten of fifteen AI Legal Index capability axes and Syntracts on six of fifteen. Centari publishes more about verification, named customers and its advice line. Syntracts is built to run entirely inside a firm's own environment with no third party model. Firms whose policies forbid client documents leaving their systems have more to read from Syntracts.
Does Syntracts send documents to an outside AI model?
Syntracts says it does not. It describes processing and storage inside the customer's own environment, on premises, using its own small open source models fine tuned for each customer, with no data leaving client systems and no third party language model or API called. Which open source models it uses is not published. Centari names OpenAI and Anthropic as AI providers. Graded by AI Legal Index against 15 capability axes and 12 legal signals, including privilege handling and citation accuracy, from each vendor's own published materials, verified September 25, 2026. No vendor pays for placement.
How do Centari and Syntracts train their models?
Centari's security page says customer data is never used to train or fine tune its underlying models. Syntracts fine tunes a model for each customer on synthetic data generated from that customer's own documents, says it never uses the customer's data itself, and uses reviewers' corrections to improve the model over time. Neither position appears in a published agreement. Graded by AI Legal Index against 15 capability axes and 12 legal signals, including privilege handling and citation accuracy, from each vendor's own published materials, verified September 25, 2026. No vendor pays for placement.
Who uses Centari and Syntracts?
Centari names Fried Frank, Willkie, Ropes & Gray, Wilson Sonsini and Gilbert + Tobin, with senior users quoted, and serves investment funds as well as law firms. Syntracts announced a multi year deployment at an unnamed AmLaw 25 firm in June 2025 and was one of two companies selected for A&O Shearman's Fuse incubator; it names no customer. Graded by AI Legal Index against 15 capability axes and 12 legal signals, including privilege handling and citation accuracy, from each vendor's own published materials, verified September 25, 2026. No vendor pays for placement.
What do Centari and Syntracts both leave unpublished?
The price, the contract and the error rate. Neither publishes a price or unit of charge, and neither publishes the agreement a customer would sign. Neither measures how often its extraction is wrong or says what happens when the model cannot find a term. Neither addresses retention of what it holds, documents how a firm's ethical walls carry through to extracted data, or names bar guidance on AI. Graded by AI Legal Index against 15 capability axes and 12 legal signals, including privilege handling and citation accuracy, from each vendor's own published materials, verified September 25, 2026. No vendor pays for placement.
Three readings to weigh. Syntracts says only synthetic data trains its models, and also that the synthetic data is generated from each customer's own documents; both statements are the vendor's, and together they mean customer documents shape a model built for that customer. Syntracts publishes no terms, so its low grades on liability and professional responsibility record what could be read. Centari's terms defer to a customer agreement that is not published. Centari was verified on 20 September 2026 and Syntracts on 22 September 2026. Neither vendor reviewed this page.
Neither vendor paid for inclusion, placement or a grade, and neither reviewed this page before it published. Everything above comes from public material on the dates shown. How the index grades.