eBrevia vs Pactly: how they compare in 2026
A team reviewing a large agreement collection can use either product, but eBrevia centers on contract intelligence while Pactly combines analysis with negotiation and lifecycle work. eBrevia extracts provisions and supports review across a portfolio, with drafting and question answering added to that foundation. Pactly Projects organizes repeatable questions into columns and exposes reasoning and quoted support for individual results. In maintaining an analyst's work, AI Legal Index highlights Pactly's protection of human corrected values when the same analysis runs again. The surrounding systems are different: eBrevia concentrates on finding and organizing contractual information; Pactly also handles playbook based Word redlines, approvals and signatures. Neither a vendor's broad speed claim nor an extracted date proves that a result is ready for a legal decision.
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.
AI drives eBrevia's extraction, contract questions, and suggested revisions. Contract Analyzer applies more than 700 prepared fields and supports optional custom extraction, while Lens answers questions without requiring a new model for each request. DraftPro applies playbooks and draws clauses from previous agreements to assist Word editing. Those capabilities sit alongside a conventional operating layer in Command: a repository, contract requests, assignees, priorities, due dates, and status changes. Removing AI would remove the intelligence and drafting functions, but the surrounding storage and contract work system would still have functions. The suite therefore combines an AI engine with ongoing agreement administration.
Models identify clauses and concepts for playbook review, generate proposed revisions and extract values across contract collections. Assist adds questions about a contract's text and history, with proposed edits and comments in Word. Projects applies the same questions to many agreements and returns a structured table with reasoning and source passages. These are core analysis functions alongside the conventional platform: questionnaires generate approved templates, workflows route approvals, signatures execute agreements and reminders track renewals. Those administrative features do not depend on generative output. Projects is available separately, while Growth and Ultimate include it within an unspecified fair use allowance.
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.
Contract Analyzer presents extracted information beside the agreement and lets a reviewer jump from a result to the exact source text. Lens uses the same contract material for contextual answers, and DraftPro draws reusable clauses from agreements already in the repository. Users can validate, annotate, or correct results before exporting them. This gives contract findings a traceable basis, rather than treating generated language as an unsupported conclusion. Published review speed and accuracy claims are not accompanied by a reproducible evaluation dataset or a detailed failure analysis. The source links concern agreements, not a verified collection of judicial authority.
Projects connects an extracted value to reasoning, a quoted source passage and a document view that highlights the relevant text. Users can correct a value, preserve the original AI extraction and mark a result as verified. The guidance names concrete failure modes, including confusion between effective and commencement dates, loss of qualifiers in compound liability caps and missing values in drafts with placeholders. Word review also exposes the clauses behind each playbook assessment. No reproducible benchmark or measured error rate accompanies these mechanisms. The terms expressly warn that AI answers can be incomplete or wrong and require checking against the source.
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.
DraftPro proposes redlines after applying the legal team's playbook, but the lawyer chooses which revisions enter the Word file. The review explains whether a provision passes or fails the chosen standard and allows navigation to the relevant clause. Contract Analyzer separately supports reviewer assignments, progress states, annotations, and quality assurance workflows. Command tracks ownership and activity as an agreement moves through drafting, review, negotiation, and signature. These are practical review surfaces and responsibilities. The product does not describe a confidence based stopping rule, an automatic route for every uncertain answer, or a recovery procedure after an incorrect result has been accepted.
Assist never applies a contract edit or comment silently: proposed changes require acceptance and enter Word as tracked changes. A reviewer can reject, revise or copy the proposal, and a support message is not sent without the user's choice. Playbook results can be Uncertain, returning the decision to a human; accepted deviations carry a written justification. Projects preserves corrected and verified values during reruns and identifies outdated results when a column question changes. The external MCP connection is read only and cannot create, modify, delete or send signature requests. Standalone Word generation remains described as an upcoming release rather than an existing unrestricted action.
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.
Named users describe concrete work with eBrevia. McDermott, Will & Emery attributes its ability to meet difficult review deadlines to the product. MUFG describes using custom trainable AI across different review needs, while Morris, Manning & Martin connects it with reducing data handling so lawyers can focus on analysis. Baker McKenzie discusses international deals, and Best World Group describes visibility across regional contracts. The product also advertises review time reductions of 30 to 90 percent. These accounts establish deployed legal and business uses, but the cited figures are not tied to a dated study with a reproducible measurement method.
A September 2022 case study identifies Virtuos and its Senior Legal Counsel, Johnathan Yong, and describes an NDA process before and after adopting Pactly. Requests previously took several days or sometimes a week across Word, shared drives and email. Following template questionnaires, legal review and DocuSign execution, reported median finalization fell to two hours and median completion of a signed agreement to twelve hours. Yong describes feedback more than two months after implementation. The account explains the workflow change and measured contract type, although it does not provide the sample size. It measures contract automation rather than the accuracy of today's generative review features.
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 service agreement treats uploaded Licensee Data as confidential and restricts disclosure to authorized recipients who need the information and carry matching confidentiality duties. It permits injunctive relief for a breach and requires steps to recover improperly disclosed material. Live customer data is deleted at termination or written request, with encrypted backups and legal retention exceptions. Public marketing promises no training on client data, while the incorporated Privacy Notice permits service personal data to support product improvement. The contract does not expressly exclude model training from that permission. Attorney client privilege, matter barriers, and downstream model provider retention receive no specific public treatment.
The service agreement protects nonpublic customer data as confidential information and preserves customer ownership. Its improvement license nevertheless permits analysis of service information involving customer data during the term and use of anonymized aggregate customer data for lawful business purposes afterward. Public marketing says contracts never train AI models, without the same express restriction in the agreement. Sensitive groups can hide contracts from nonmember administrators, but deliberate sharing and project membership can widen access. The provider list explains where contract data travels. No specific attorney client privilege, work product or accidental disclosure protection is stated for lawyers using these features.
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.
eBrevia's service agreement defines its role as a tool for reviewing, summarizing, and managing legal material, expressly excluding replacement of legal advice. The customer remains responsible for decisions based on generated information. Authorized users include employees, attorneys, paralegals, and professional staff performing legal or related services. A licensee may share analysis with its clients, but direct client access requires a separate license. DraftPro reinforces lawyer control over proposed changes. These boundaries identify the product's professional role without setting out jurisdiction specific eligibility rules or a detailed account of how a firm should satisfy competence, supervision, and client consent duties.
Pactly's agreement says the company is not a law firm, use creates no attorney client relationship and the service does not solicit legal advice. It separately warns that AI answers may be wrong and makes the customer responsible for comparison with the source. Product guidance describes the reviewer accepting edits and resolving uncertain playbook findings, and the company explicitly rejects a fully automatic robot lawyer role. Corporate legal departments are its principal audience, with business users working through forms and approvals. The material does not map the controls to named bar guidance or publish jurisdiction specific professional responsibility limits.
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.
eBrevia offers Legal Advisory services covering AI use case selection, secure architecture, governance mapping, pilot evaluation, and adoption. Those services describe work for a customer's rollout, rather than a published policy governing eBrevia's own model development. Its leadership materials identify technical responsibility for the AI platforms, and its security program concerns protection of information. No public framework describes model release approval, bias evaluation, or results across languages and agreement types. Customer playbooks specify review positions, but they do not reveal how the vendor evaluates errors or uneven performance before introducing changes to its underlying AI.
Published AI guidance explains how customers verify results, handle uncertain findings and correct extraction mistakes. Release notes describe feature changes, and security materials identify a data protection officer and engineering responsibilities for incidents. These do not establish an AI governance program with an accountable model owner, release testing criteria or results on uneven behavior across languages, populations or contract categories. Positive and negative playbook examples help customers configure review, rather than disclose Pactly's own evaluation program. No formal bias assessment, model card or governance framework accompanies the descriptions of Assist, Projects and playbook review.
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 customer agreement provides deletion of live Licensee Data at termination or on written request, while allowing encrypted backup copies for six months and retention required by law. The Privacy Notice supplies a similar rule for service personal data. Contract Analyzer describes encryption in transit and storage, and the wider platform offers access controls for enterprise use. Public materials also describe monitoring and independent security audits. They do not name a complete current subprocessor chain or establish a specific incident notification deadline. The service terms exclude protected health information, payment card data, and certain financial personal information from authorized uploads.
Pactly describes encrypted storage and transport, monitoring, backups, vulnerability testing and separate production and test environments. Administrators can require two factor authentication, and high criticality incidents trigger notice to affected customers or all customers when the affected group cannot be identified. A public supplier register details processing functions and regions with advance change notice. The terms provide sixty days to retrieve data after termination, followed by requested deletion with an anonymized aggregate exception. Assist attachments expire after seven days, but ordinary chat history, backup deletion and underlying AI provider retention lack a complete fixed schedule. No definite breach notification deadline is stated.
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.
The service agreement provides an intellectual property indemnity for claims that eBrevia's technology infringes third party rights, subject to a customer modification exclusion. That indemnity is expressly outside the general liability limit. Ordinary direct damages are capped at fees paid during the preceding 12 months, with consequential losses excluded and a one year limit for bringing an action. Separate exceptions cover specified personal injury, misconduct, and fraud claims. The functionality commitment uses commercially reasonable efforts, while accuracy and completeness are disclaimed. These terms provide defined recourse for technology infringement, but no specific indemnity or correctness warranty for generated legal output.
The service agreement includes an indemnity for third party claims involving patents, copyright or trade secrets infringed by the service, subject to stated exclusions and control of the defense. Available remedies include replacement, modification, a license or termination with unused fees returned. General liability is capped at fees paid in the preceding twelve months and excludes data inaccuracies and several categories of loss. AI answers are expressly described as potentially incomplete or wrong, with verification assigned to the customer. There is no separate output accuracy warranty or AI insurance promise. Availability remedies have separate claim deadlines and exclude beta features.
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.
DraftPro works inside Word and obtains clause language from the licensed eBrevia repository; users inspect suggestions and apply selected redlines to the draft. Connect handles incoming agreements and pushes extracted data into downstream systems. Its listed connections include iManage, NetDocuments, HighQ, Relativity, Salesforce, SharePoint, Microsoft applications, and reporting tools. Described operations include tagging files, assigning employees, validating data across systems, and generating reports. This establishes movement into and out of the contract platform. The public descriptions do not provide connector specific field mappings, permission synchronization rules, or installation procedures showing what each firm must configure.
The Word plugin uploads an agreement for playbook review, displays matched clauses and proposed fixes, inserts approved language as tracked changes and records review decisions between rounds. The MCP connection exposes eight read only tools for contract text, metadata, parties, playbooks, clauses and account information to external clients such as Claude and Cursor. Public instructions specify API key or OAuth authentication, administrator consent, filters, returned fields and request limits. Separate APIs can generate contracts from templates and support webhooks. DocuSign and Adobe Sign support execution, while the Ultimate plan's SharePoint connection is described as backup only rather than general document synchronization.
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.
eBrevia operates as a hosted contract platform with a Word add in connected to the licensed environment. Its Privacy Notice says hosting defaults to the United States unless the customer instructs otherwise, while also identifying facilities across several continents. The same notice explains that business processes cross borders and processing cannot always be confined to the individual's country. No public tier matrix identifies the alternative regions available for every product, and no separate location is supplied for each generative model task. A hosting instruction therefore provides some regional control without a complete account of storage, processing, and provider locations.
Core hosting, compute and Bedrock inference use AWS in Singapore by default, with Malaysia for specified Malaysian customers. Structured data in MongoDB Atlas remains in Singapore for all customers. The supplier table separately identifies United States processing for document conversion, OCR, Cerebras inference and fallback Anthropic or OpenAI services, plus Langfuse monitoring in Germany and Cloudflare's global edge. Those routes make regional hosting different from exclusive regional processing. The SLA also recognizes fully managed private deployments, without a standard public price for them. Singapore and Malaysia have separate service entry points, and the published provider map identifies functions as well as locations.
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.
eBrevia states that it is independently certified for SOC 1 and SOC 2, and Contract Analyzer specifically names SOC 2 Type II infrastructure. The security description refers to continuing audits and monitoring, encryption, and controls for authorized access. It also claims GDPR and HIPAA compliance, which are separate from a disclosed audit report. No accessible report supplies the audit period, exceptions, or precise service scope. The public customer agreement additionally restricts protected health information, so the HIPAA marketing statement does not override that upload restriction or establish that a customer has an applicable business associate agreement.
Pactly identifies ISO 27001 certification in its product, pricing and trust materials and offers its certificate, security whitepaper and penetration test results on request. The public trust FAQ describes Amazon's certified data centers when explaining ISO coverage, so infrastructure attestations need to be distinguished from Pactly's own claim. No openly supplied certificate names its current auditor, validity period and exact company scope. SOC, PCI and FISMA references in the infrastructure section concern AWS rather than a separate Pactly audit. Security practices include vulnerability scans, access logging, staff training and incident response, without resolving that certification scope question.
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 suite distinguishes structured extraction from Lens, its generative layer for questions across contract material. Contract Analyzer has prepared fields and optional custom models, while DraftPro combines AI classification, playbook review, and clause reuse. eBrevia describes its own long development history in machine learning and natural language processing, but does not identify the foundation model providers serving current Lens or DraftPro requests. No version inventory, provider retention arrangement, or notification commitment for model changes is published in the product and contract materials. Named business integrations identify connected applications, not the model services that may process a customer's agreement.
Pactly names AWS Bedrock for core inference, Cerebras for tasks requiring low latency, and Anthropic and OpenAI as fallback providers when Bedrock is unavailable. The supplier register identifies processing locations and also lists Langfuse for AI monitoring. Customers can subscribe to at least thirty days' written notice before a new subprocessor is engaged and raise an objection during that period. Exact production model families and versions are not supplied for each feature, nor is there a promise to notify every model version change within an existing provider. External MCP clients bring their own model relationship in addition to Pactly's built in AI.
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.
eBrevia quotes review projects according to contract volume, review scope, and required capabilities. Its service agreement sets fees and access in a proposal and defines a processed Document as no more than 300 pages. The default contract period is one year with annual renewal unless the proposal changes it, and nonrenewal requires 30 days' notice. Contract Analyzer, DraftPro, and Connect can form part of the licensed services. No numeric subscription rate or implementation charge is supplied publicly. Training and support appear within the service definition, but their inclusion and any additional cost depend on the negotiated proposal.
Standalone Projects starts at $69 a month for one user, fifty documents and 250 monthly runs, or $690 annually with 3,000 runs available immediately. Larger packages, additional documents and extra runs have published charges. The wider CLM starts at $99 per user monthly on an annual plan; Growth is $139 with five users minimum and Ultimate $179 with ten. Their monthly AI review allowances are ten, fifty and one hundred respectively. Growth and Ultimate include Projects under fair use without a numerical allowance. Enterprise, migration and some implementation services require a quote. Projects has a fourteen day trial, while the CLM trial lasts thirty days.
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 product addresses law firms, corporate legal departments, financial institutions, and audit or consulting teams. Law firm workflows include mergers and acquisitions diligence, bankruptcy and financing review, and compliance reporting. Contract Analyzer also supports leases, repapering, and migration of agreement data. DraftPro covers repeat commercial, employment, privacy, technology, finance, real estate, and corporate agreements, with sample playbooks for selected types and custom positions for others. Command extends contract information to procurement, sales, finance, and related business teams. Coverage is described through these tasks and examples, without a complete list of supported jurisdictions or performance boundaries for each language.
Pactly primarily serves corporate legal departments, including solo counsel and small teams across Southeast Asia and other Asia Pacific markets. Larger organizations can configure approval routes, business intake and administrator controls. Supported examples include NDAs, services, procurement, leases, employment and software licenses; Projects extends analysis to loan agreements, insurance and related portfolios. Sales, HR, finance and procurement can participate without turning the product into a consumer legal advice service. The company explicitly describes most customers as internal legal departments rather than firms. No measured language coverage or comprehensive jurisdiction matrix defines where AI interpretation is most reliable.
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 service agreement incorporates the Privacy Notice for uploaded material and service personal data. That notice permits personal information to support developing and improving products and services, without expressly excluding model training from that permission. The scope is personal data covered by the notice, not an assertion that every uploaded agreement is used for training. Public event material separately promises no training on client data, but a matching prohibition does not appear in the customer contract.
The agreement permits analysis of service information involving customer data during the subscription for improvement and development. It also allows anonymized customer data to enter aggregate datasets used for lawful business purposes during and after the term, with safeguards against reidentification. Marketing separately promises that contracts never train AI models. The published agreement does not repeat that prohibition or exclude model improvement from its permission.
This records the contractual scope, not a claim that Pactly actually feeds every raw agreement into a shared training process.
Prompt and Output Retention
How long does the product keep what a lawyer typed, and can that be set to zero?
The customer can instruct eBrevia in writing to delete live Licensee Data, and termination also triggers that deletion duty. The Privacy Notice similarly permits removal of personal data from live services on request. Encrypted backups may remain for six months, and legal retention requirements create an exception. This is control through a contractual instruction, rather than a published retention slider. No mode promises that prompts and generated answers are never retained during processing.
Contract data remains retrievable for sixty days after termination. The standard terms then provide deletion on written request, excluding anonymized data already combined into aggregate datasets; online plans may delete after the same access window. Assist attachments expire after seven days, but a complete schedule for normal chat history, backups and provider copies is absent. The upcoming standalone Word generation description gives a thirty day file expiry, which should not be treated as the lifetime of all current AI outputs or contracts saved to the repository.
Ethical Walls and Matter Segregation
Does retrieval respect the firm’s ethical walls, or can the model read across them?
DraftPro ties user access to the licensed eBrevia environment and can filter clause material by project, matter, contract type, or jurisdiction. Contract Analyzer supports assignments and enterprise access controls. Those features do not establish that retrieval enforces a firm's ethical walls or inherits the permissions of an upstream document repository. A matter filter organizes material for review; it is not, by itself, a documented security boundary preventing access to another client's information.
Pactly uses its own groups and roles rather than inheriting a document management system's matter walls. Sensitive groups hide contracts even from nonmember administrators, but an authorized person can deliberately share a contract outside the group. Projects creates another boundary: every project member sees all present and future project documents, even when the normal repository link is unavailable. Administrators can see all projects.
This is a described access model with important widening rules, not a promise that an original contract restriction automatically follows every AI analysis surface.
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 Notice allows disclosure in response to an information request when eBrevia determines that law, regulation, or legal process permits or requires it. It also covers disclosures to protect rights and defend legal claims. Neither that provision nor the service agreement commits to informing the customer before producing material, and no transparency report is supplied. The confidentiality clause limits ordinary sharing but does not add a separate notice procedure for compulsory demands.
The service agreement incorporates Pactly's law enforcement request policy for compelled disclosure of customer data. That policy requires evaluation of governmental requests and notification to the customer where legally permitted, allowing an opportunity to seek protective measures. It applies to hosted and fully managed deployments, while excluding self hosted or customer managed solutions. Foreign authorities are directed through applicable legal and diplomatic channels.
No report of request volumes or outcomes accompanies this commitment, and the general privacy notice's legal disclosure permissions do not replace the more specific customer data policy.
Primary Law Corpus Provenance
Where does the law in this product come from, and does the vendor have the right to use it?
eBrevia's contract answers and clause library derive from agreements supplied to its repository. Lens asks questions of that material, while DraftPro reuses provisions from earlier contracts with filters for the current context. The service terms require the customer to hold the rights needed for uploaded material. No separate primary law collection, publisher license, or legal update schedule is described. Contract source traceability therefore establishes where an agreement answer came from, rather than the provenance of external legal authority.
The analysis context is the customer's agreements, playbooks, approved clauses and related files. Projects reads each row's main contract and supporting amendments or schedules; Word review uses configured positions and fallback language. These are customer supplied materials rather than a catalog of primary law or licensed legal commentary. Pactly does not name an external research corpus, describe the source rights behind general model knowledge or supply an update process for legislation and case law. The public subprocessor list identifies processing suppliers, not a legal content licensing arrangement.
Good Law Verification
Does the product tell you when the authority it just cited has been overruled?
A reviewer can follow an extracted provision back to the contract and assess it against a playbook. Neither that process nor a Lens answer checks whether a judicial authority has later been reversed or limited. The products focus on contract language, obligations, and company positions, with no named citator or subsequent treatment mechanism. A governing law field identifies a contract term; it does not establish that the law applied to the agreement remains current.
A source passage in Projects establishes where a contract value came from, and playbook review identifies the agreement language relevant to a configured rule. Neither function determines whether a case remains good law or legislation has changed. No licensed citator, subsequent history service or independent treatment signal is described. The legal team maintains its own clause positions and decides whether they remain appropriate.
Contract source highlighting and a verified cell marker therefore support review of supplied material without establishing the continuing validity of an external legal proposition.
Refusal and Uncertainty Behavior
What does the product do when the answer is not in the corpus?
Lens is described as producing contextual answers linked to contract material, but no public example specifies what it returns when the agreement cannot support an answer. DraftPro's pass or fail result concerns compliance with a chosen playbook, not uncertainty in the model's interpretation. Users can correct extraction, add missing clauses, and reject revisions. Those review controls leave room for human judgment without defining an automatic refusal or abstention path for unsupported output.
Playbook review includes an Uncertain result when a clause cannot be conclusively assessed, directing a person to decide. Each position also defines what happens when no relevant clause is found: compliant, not compliant or uncertain, according to the customer's chosen rule. Projects treats placeholders such as an unfilled name as not found and explains common interpretation failures. These are described negative and uncertainty states rather than a general guarantee of refusal. A wrong configuration of the absent clause rule can still produce a misleading result.
Fabricated Citation Record
Does a public court record exist addressing fabricated or hallucinated legal citations in output from this product?
The AI Hallucination Cases database maintained by Damien Charlotin has no entry naming eBrevia or e Brevia. The database records court decisions involving hallucinated AI material and identifies tools when the proceedings do so. eBrevia mainly analyzes agreements and proposes contract language, rather than preparing briefs from judicial authorities. That focus does not make its output infallible, and the absence of a named court case is not a test of extraction accuracy or drafting quality.
Damien Charlotin's AI Hallucination Cases database contained no entry naming Pactly on October 16, 2026. The database concerns reported court decisions involving fabricated AI material and does not capture every private error in contract analysis. Pactly principally supports corporate agreements rather than preparation of court authorities, which limits what that incident record can say about its usual work. Its terms independently warn that AI answers may be incomplete or incorrect. No named court incident is therefore a limited reporting observation, not a validation of model accuracy.
Bar Guidance Alignment
Has the vendor engaged in public with the ethics opinions its buyers are bound by?
The service agreement separates software assistance from legal advice and places responsibility for decisions with the customer. DraftPro also keeps proposed changes subject to lawyer approval. These provisions establish a supervised product role, but no named bar opinion or jurisdiction specific ethics mapping accompanies them. The public materials do not connect use of Lens, shared client material, or automated contract revisions with particular duties of competence, confidentiality, disclosure, or supervision under a professional rule.
Pactly explains that it is not a law firm and requires people to verify AI answers against source text. Its review guidance describes accepting tracked edits, recording deviations and resolving uncertain results. These are practical controls for legal work, but the materials do not map them to a named professional ethics opinion, bar rule or regulator's jurisdiction specific AI guidance. References to Singapore privacy law and a data protection officer address data regulation rather than a lawyer's professional obligations when serving a client.
Billing and Fee Posture
Does the vendor address what happens to the bill when the work takes an hour instead of six?
eBrevia markets reduced review time and cost to law firms as well as corporate buyers. Its law firm use cases include diligence, financing review, and compliance reports, and the customer license expressly permits sharing resulting analysis with clients. These uses place the product inside legal service delivery where efficiency can affect a bill. The public product and contract materials do not explain how lawyers should record saved time, adjust billed hours, or disclose an AI related charge.
The principal buyer is a company's own legal department, with sales, procurement and HR using forms and approvals around that team's contracts. The Virtuos case measures internal NDA turnaround, and the product's savings claims concern corporate workloads and staffing capacity. Those examples do not involve a lawyer billing an external client for AI assisted work. Published subscription and run charges describe Pactly's software fees, without a client invoice method, pass through rule or accounting of billable legal time. Law firm fee treatment is not part of the described workflow.
Outside Counsel Guideline Readiness
Can a firm get this vendor through a client’s AI clause without a bespoke negotiation?
The service agreement, Privacy Notice, and security statements provide general information about confidentiality, retention, and permitted data. They do not include a current named model provider chain, a complete subprocessor register, or a client disclosure package for outside counsel use. Lists of supported applications describe integrations rather than organizations processing data on eBrevia's behalf. A firm can use the public contract material in diligence, but it does not resolve a client's AI specific notification requirements.
A public provider register identifies data categories, functions and regions, including core Bedrock inference, fallback Anthropic and OpenAI services, and AI monitoring. Customers can subscribe to change notices and object before a new supplier is engaged. The trust page offers security reports and a certificate on request, while service terms and the law enforcement policy provide additional diligence material. No dedicated client consent pack or outside counsel AI disclosure form is supplied. Counsel would still need to distinguish the contractual improvement permissions from the marketing training promise.
Court Disclosure Support
If a judge’s standing order requires an AI disclosure, can the product produce one?
Contract Analyzer retains extracted terms beside source language and supports review status, annotations, and exported reports. DraftPro leaves selected revisions visible as Word redlines, while Command records contract activity and status changes. Those elements can help reconstruct what was reviewed. No public export combines the generating model, the full set of material used for an answer, and a named person's verification in one certificate. Contract analysis records therefore cover only part of a filing disclosure.
Projects can export values, reasoning and source references to Excel, and produce a PDF preserving the table's visual labels. Human corrections and verifications record who acted and when inside the application, but the help guide expressly says the Excel export omits that sign off marker. Word review retains tracked edits and written justifications for deviations, while account activity is available through logs. These records preserve parts of the process without a combined export of model version, exact prompts, source context and human approval for a court filing.
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.
- AI Governance and Bias Disclosure
- Primary Law Corpus Provenance
- Good Law Verification
- Bar Guidance Alignment
Which one fits
Choose eBrevia if
- The main task is extracting and organizing provisions across agreements.
- Contract intelligence is the central purchase rather than signature routing.
- Review teams need a dedicated environment for an existing contract collection.
Choose Pactly if
- Portfolio questions should coexist with drafting and approvals.
- A standalone analysis plan with explicit allowances fits the project.
- Corrected result cells should remain stable during repeated analysis.
In summary
eBrevia
eBrevia organizes contractual provisions and data for review across an agreement collection. Its extraction and contract intelligence workflow supports teams that need to understand existing obligations and terms at scale.
Pactly
Pactly Projects presents portfolio answers in a table with reasoning and excerpts. The wider Pactly system adds negotiation playbooks, tracked changes, intake and signature workflows around that analysis.
Questions buyers ask
How does Pactly organize repeated questions across files?
Each Projects column applies a question or structured task to the selected agreements. Results can include text, dates, numbers, lists or other supported formats, with reasoning and a quoted passage for inspection. From the AI Legal Index, based on each vendor's own published materials as of October 16, 2026. No vendor pays for placement.
Can either platform serve a review of existing contracts?
Yes. eBrevia is built around contract intelligence and extraction. Pactly Projects supplies a table for repeated portfolio questions, while its CLM also handles the negotiation and execution of new agreements. From the AI Legal Index, based on each vendor's own published materials as of October 16, 2026. No vendor pays for placement.
What does Pactly preserve when a reviewer corrects an answer?
For an analysis that will run more than once, AI Legal Index identifies Pactly's retained original AI value and protected human correction as concrete controls. The reviewer can restore the original result, and later reruns do not silently replace the correction.
Does exporting Pactly's result table include verification signoff?
The spreadsheet carries values, reasoning and supporting text, but not the verification signoff. It can support further analysis without serving as a complete record of who approved each answer. From the AI Legal Index, based on each vendor's own published materials as of October 16, 2026. No vendor pays for placement.
Neither vendor paid for inclusion, placement or a grade, and neither reviewed this page before it published. Everything on it comes from public material on the dates shown. How the index grades.
Pactly's described verification controls concern Projects; they should not be generalized to every AI output in its CLM.