BlackBoiler vs Pactly: how they compare in 2026
Repeatable Word markup is BlackBoiler's central job: prior redlines, approved clauses and fallback guidance become rules that propose the next edit. Pactly combines Word review with intake, approval, signing and a contract repository, then adds Projects for questions across many agreements. For the actual editing step, AI Legal Index identifies a shared human decision point: BlackBoiler returns tracked changes for lawyer review, while Pactly requires acceptance of Assist proposals. The difference is what surrounds that step. BlackBoiler fits into an existing contract process and concentrates on translating negotiation standards into changes. Pactly also maintains the agreement workflow and a table of extracted answers, with source passages and recorded corrections. BlackBoiler's Veris helps refine playbooks conversationally; Pactly's published playbook versions preserve the positions used in a review round.
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.
The product is an automated contract editing engine. It converts an organization's prior redlines, approved language and written guidance into executable playbook rules, applies them to a new agreement, and returns tracked changes and comments in Microsoft Word. There is no repository, workflow or signature product underneath that would work without the models. The June 2026 Veris release adds a generative, conversational layer for building playbooks and questioning clauses on top of the patented rules based editing engine, and both parts make up the product. The company says eleven United States patents cover document revision, playbook driven markup and clause handling.
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.
The vendor describes a four stage chain: evidence (the customer's prior redlines, approved language and guidance), logic (how those become executable rules), checking (a judge validator that assesses whether a proposed change fits the intended outcome, plus statistical similarity checks), and output (tracked edits and comments for lawyer review). The earlier ContextAI feature shows, for each redline, the playbook rule that prompted it and earlier examples of the same edit in the organization, a trail a reviewer can open for every proposed change. The vendor names failure modes: playbook coverage may be incomplete, contract language may depart from earlier examples, and unusual provisions may need a lawyer's fresh decision. The product cites no legal authority and has no citator; its output rests on the customer's own approved language, which is shown to the reviewer. No measured accuracy figure or test set is published.
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.
The system runs the first pass markup alone, producing tracked changes and comments. It is constrained by the customer's approved playbook positions, which the customer reviews and approves before use. The review surface is Microsoft Word track changes in the document the reviewer already has open. The reviewer decides what to accept, change, reject, escalate or negotiate, and the vendor says new risks, exceptions and negotiation decisions are left to the right reviewer. Nothing is applied to the agreement unless the reviewer accepts it, because the output is a proposal in tracked changes. Clause 3(b) of the Access Services Agreement says the same in contract terms: use of the Services is not a substitute for, and shall not replace, review and analysis by a lawyer. No marketing claims the system handles review on its own.
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.
Four testimonials are published, each attributed only to a first name and surname initial or to a verified user, in the style of review site content, and none gives an organization or a figure. The customer base is described in categories (AmLaw 25 law firms, Fortune 1000 organizations and several construction customers), but no customer is named anywhere and no case study, deployment figure or before and after measure is published. A 2021 AI Breakthrough award, a National Science Foundation SBIR award and Virginia Innovation Partnership Corporation portfolio status are recognition and funding rather than production use. Clause 12(c) of the Access Services Agreement bars either party from any public statement mentioning the other without written approval, so naming customers would need a waiver from each.
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.
Under clause 7(b) the customer owns all contract data, training of third party foundation models is barred without customer authorization, and use of customer data is limited to configuring, improving, supporting and operating that customer's own use of the service. The vendor also says customer data is not used to train models shared with other customers. Data is isolated per customer, with dedicated instances available for enterprise deployments, access is limited to authorized staff with controls and logging, and data is encrypted in transit and at rest. Mutual confidentiality runs five years, with trade secret protection lasting indefinitely. Privilege and work product are not addressed anywhere. No model provider is named, so whose model touches contract text, and what that provider keeps, is not stated.
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.
Clause 3(b) of the Access Services Agreement, headed Review of Outputs and No Legal Advice, says use of the Services is not a substitute for, and shall not replace, review and analysis by a lawyer. Supervision and competence are addressed. The vendor sells to contract managers and procurement staff who are not lawyers, and says directly that a lawyer reviews the redline before anything moves forward and handles exceptions, new risks and negotiation decisions. The marketing never describes the product as giving advice; it consistently describes a first pass returned to a lawyer. Jurisdiction limits are not named anywhere. The only geographic limit is a website terms clause limiting site use to United States residents, which covers the website, not the service.
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.
No AI governance position is published. Nobody is named as accountable for AI governance, no testing before release is described, no evaluation results are disclosed, and nothing addresses uneven output across contract types, counterparties or drafting styles. There is no responsible AI page, principles statement, model card, AI policy, ISO 42001 certification or outside governance assessment. The vendor does describe validation tools: a judge validator that checks alignment with the intended outcome, and statistical similarity checks. Those check individual outputs; nothing describes how the vendor builds, tests and answers for its models.
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.
Customer data is kept for the length of the customer relationship unless agreed otherwise, and can be deleted at contract end or earlier on request. Access control is described in two documents. Access is limited to authorized staff who need it, with access controls and logging, and infrastructure access is secured by VPN, secure tokens and IP allowlists issued only to approved employees. Encryption is AES256 at rest and TLS in transit, backups are encrypted, and clause 7(b) confirms the customer owns its data and the vendor will not sell it. No subprocessor list is published, with only Amazon Web Services for hosting and Stripe for payments named, and no incident or breach notification practice appears anywhere. The vendor also discloses that individual client files may sometimes be downloaded temporarily onto an employee's encrypted hard drive for testing. No retention period is stated.
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.
Clause 9(a) of the Access Services Agreement covers third party claims that the Services infringe or misappropriate United States intellectual property, with the vendor controlling the defense and able to modify, replace or terminate. Clause 9(a)(iii) carves out unauthorized combinations, customer changes, Customer Data and Third Party Products. Clause 10 caps total liability at amounts paid or payable in the twelve months before the claim, with exceptions for breach of confidentiality, IP infringement, customer payment obligations and breach of the use restrictions. The agreement is explicit that output errors are the customer's risk. The IP indemnity does not reach output quality, clause 8 disclaims all warranties, and clause 3(b) defines the risk of relying on any edit, redline, comment, summary, suggestion or analysis as Customer's Assumed Risks. Clause 9(b)(ii) requires the customer to indemnify the vendor against third party claims arising from those risks. No insurance is mentioned.
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.
The Microsoft Word add-in is the delivery surface. Review runs inside Word without moving to a separate tool, the playbook is chosen in the document, and output comes back as native tracked changes and comments for the reviewer to accept, change or reject. Single sign on and API access are listed as enterprise features, with nothing on what the API exposes or what a firm must configure. No document management, contract lifecycle or electronic signature platform is named as an integration partner. The vendor positions itself as sitting alongside a CLM where the CLM leaves a gap, and as handing back to the customer's existing process, but names no connection.
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.
The vendor says it uses isolation measures specific to each customer to keep customer data separate, that enterprise deployments may include dedicated customer instances and data separation controls, and that data is held in a silo open only to the client and necessary vendor staff. The service runs on Amazon Web Services, with production, staging and development all in AWS. No region is named, no choice of region is offered, no European or other non United States option is described, and processing location is not distinguished from storage. The vendor says expressly that it does not publish detailed architecture or infrastructure information.
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.
The vendor says on two pages that it is SOC 2 Type II certified. No auditor, audit period, report date or scope is published, and no other certification is claimed: no ISO 27001, HIPAA attestation or public penetration test summary. The report is available to prospective customers on request through the sales or security review process. Further security materials and completed questionnaires are kept for enterprise evaluations, while team and individual subscribers are pointed to the public page. That public Security and Trust page has a seventeen question FAQ covering hosting, encryption, isolation, access, retention, deletion, backups and authentication, and carries no reports, dates or covered standards.
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 vendor refers to generative AI throughout, and no model, provider or architecture is described beyond the four stage evidence, logic, checking and output framing. Clause 7(b) of the agreement allows Customer Data to be processed using third party infrastructure, technology and AI services, and separately bars training third party foundation models without customer authorization. So third party models are in the supply chain under the contract, and nothing identifies them. The Third Party Products definition gives only a generic example. Amazon Web Services is named, but as infrastructure, which says where a model runs, not whose it is. Stripe is a payment processor that never touches contract content and is routed outside the Word add-in and the conversational interface. No commitment to notify customers of a model change is published.
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.
BlackBoiler charges $125 per user per month for Starter or $1,250 per user per year with annual billing. Starter includes two playbooks and 25 monthly contract uploads. Pro costs $300 per user per month or $3,000 per year and adds five playbooks per user, 100 monthly uploads, analytics, administration and multifactor authentication. Enterprise has custom pricing for unlimited contract volume, single sign on, API access, playbook help, onboarding and negotiated service terms. A seven day trial requires a payment card and converts to the chosen subscription unless canceled. Setup charges for the larger deployment remain part of the enterprise quote.
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.
Three buyer segments each have their own stated position: in house legal teams reviewing the same agreement types at volume, law firms applying set positions across client matters, and contract managers applying standards the legal team has already set. One industry has a dedicated page, construction and AEC contracting, supported by a claim of several construction customers. NDAs, service agreements and subcontracts are the recurring types the product is built for, with more complex contracts in scope subject to playbook coverage. The vendor states the product's limit: how useful it is depends on playbook coverage, the language and context of the agreement, and lawyer review. Practice areas are not addressed, since coverage is by agreement type and industry, and government use is not described; a United States Government Rights clause in the agreement concerns license rights, not coverage.
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 Access Services Agreement permits customer content to configure, improve, support and operate that customer's own use of BlackBoiler. Training third party foundation models requires separate authorization, and the security position excludes models shared with other customers. The own customer improvement permission is broader than that foundation model restriction. It does not require a separate opt in for every improvement use, and should not be read as a blanket prohibition on learning from contract content.
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 security page says data is kept for the length of the customer relationship unless agreed otherwise, with no period stated, and may be deleted at contract end or earlier on request. Deletion requests are handled subject to legal, security, backup and operational requirements. Clause 7(b) of the agreement also lets the vendor use and keep customer data to configure, improve, support and operate that customer's own use of the service, again with no period.
Deletion is a request the vendor processes under its own practices, not a setting the customer controls. The legal, security, backup and operational conditions on deletion have no stated limit, and nothing says how long backup copies last after a deletion request. Termination duties run one way: clause 11(c) requires the customer to delete or destroy the vendor's property and certify it in writing, with no matching duty on the vendor to delete customer data.
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?
BlackBoiler separates customer data and offers dedicated instances and additional separation controls in enterprise deployments. Necessary vendor staff may access a customer's environment under authorization and logging controls. These protections distinguish one customer from another. They do not describe ethical walls among client matters within the same law firm or a retrieval connection that inherits a document management system's individual user permissions.
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?
Section 6 of the Access Services Agreement allows disclosure of confidential information only as far as needed to comply with a court or government order or applicable law. It conditions that on the disclosing party first giving written notice and the chance to obtain a protective order. The commitment is mutual and is a condition on the right to disclose, not a statement of practice. No transparency report or count of requests is published, and no separate data processing addendum is published.
The commitment covers confidential information as defined in section 6, and the agreement does not separately address requests aimed at customer data, though customer data submitted under the agreement would normally fall within that definition.
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?
The editing engine uses the customer's earlier redlines, approved language and written guidance to build executable playbooks. ContextAI links a proposed edit to its playbook rule and examples from the organization's prior work. These are identified sources for a contract review rather than a licensed case law collection. The service does not give a separate inventory of foundational training corpora or the license terms of any underlying model provider.
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?
The product cites no authority. It proposes contract language against the customer's own approved positions and returns tracked changes in Microsoft Word; it does not retrieve cases or statutes, show citations or include a citator. What the product does check is different: the vendor describes a judge validator that assesses whether a proposed edit fits the intended outcome, plus statistical similarity checks against the customer's earlier examples, before the edit reaches the lawyer. That checks a proposed edit against the customer's standards, not legal authority against later history.
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?
BlackBoiler warns that incomplete playbooks, unfamiliar language and unusual provisions can require a lawyer's fresh decision. Its first pass produces proposed Word changes and comments that a reviewer can accept, change, reject or escalate. Those review choices do not establish an automatic refusal when support is insufficient. A defined no answer response or a confidence threshold that forces escalation is not specified for the editing engine.
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 contains no tool entry naming BlackBoiler or Veris as of October 15, 2026. BlackBoiler's output is a proposed contract redline supported by customer playbooks and prior edits, rather than a brief prepared for filing. That narrower workflow does not establish an error rate. The database result concerns named court matters and does not certify the correctness of proposed edits.
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?
Clause 3(b) of the customer agreement says use of the service is not a substitute for, and shall not replace, review and analysis by a lawyer. The public FAQ addresses competence and supervision directly. It says nonlawyers can apply standards the organization has set, but a lawyer reviews the redline before anything moves forward and handles exceptions, new risks and negotiation decisions. No named authority is engaged.
No bar ethics opinion is cited, no bar guidance is discussed, no regulator is named, and nothing maps the product to the conduct rules its buyers follow.
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?
The vendor invites a buyer to weigh its subscription against how review is done today, citing internal reviewer time, repeated manual markup, outside counsel spend and available capacity. Its wider material says the software takes on the repeatable first pass to save time. That is a claim about the buyer's own costs. There is no record of AI assisted work by matter, nothing a firm could show a client, and no guidance on fee or disclosure treatment where AI has compressed billable time.
The buyer may be an in house team, a law firm or a contract manager. For an in house team the saving stays with the organization rather than passing through an invoice. For a law firm applying set positions across client matters, fee treatment is not addressed.
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?
No subprocessor list is published, and nothing says which model providers see client content. Clause 7(b) of the vendor's own agreement allows customer data to be processed using third party AI services and separately restricts training of third party foundation models, so third parties are in the chain and none is named. The named AWS hosting arrangement does not identify the language model suppliers handling a client's content.
Stripe is a payment processor that never touches contract content. No data processing addendum, AI disclosure pack, consent or notice template, or commitment to notify customers of subprocessor changes is published, and nothing says a subprocessor list or model provider statement is available on request. The security review process offers security materials and questionnaire answers.
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?
Nothing published addresses court disclosure or verification certification. Nothing discusses court standing orders on AI use, no disclosure template or guidance is published, and no export gives the kind of record such an order would require. The product is transactional: it applies negotiation standards to commercial agreements before signature, and its output is a contract redline, not a court filing, so the question does not normally arise.
One element of such a record does exist. The vendor says each proposed edit can be traced to the playbook rule that produced it and to earlier examples of the same edit in the organization. That trail is a review aid inside the document, not an exportable record of model, sources and human verification, and nothing published presents it for 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
- Good Law Verification
Which one fits
Choose BlackBoiler if
- You want tracked changes based on past redlines and approved language.
- The organization already has intake, approvals and signature systems.
- Your lawyers want Veris to refine negotiating rules within Word.
Choose Pactly if
- Contract requests and approvals should sit alongside the review.
- A repeatable table of questions must cover a contract portfolio.
- Published playbook versions should preserve the rules behind each review.
In summary
BlackBoiler
BlackBoiler applies established negotiation positions to recurring agreements inside Word. Its proposed changes undergo alignment checks before a lawyer accepts, revises or rejects the markup. Veris adds conversational playbook construction and clause work.
Pactly
Pactly combines controlled redlining with a broader contract workflow. Its Projects tables organize repeated questions across agreements, preserve human corrections and attach reasoning and source excerpts to results.
Questions buyers ask
Does BlackBoiler replace Pactly's wider contract workflow?
BlackBoiler concentrates on review and markup, handing the agreement back to the existing process after lawyer review. Pactly also handles generation, routing, signatures and repository management. From the AI Legal Index, based on each vendor's own published materials as of October 16, 2026. No vendor pays for placement.
How do the two products build repeatable negotiating positions?
For recurring agreements with established fallback language, AI Legal Index highlights BlackBoiler's conversion of previous edits into executable rules and Pactly's versioned positions with examples, rationale and suggested drafting.
Can Pactly change an agreement without accepting Assist's proposal?
Assist cannot apply its own edits or send a counterparty response. A user can apply, edit, copy or reject a proposal. BlackBoiler likewise returns a first pass that the lawyer decides how to use. From the AI Legal Index, based on each vendor's own published materials as of October 16, 2026. No vendor pays for placement.
Which product has a standalone portfolio analysis plan?
Pactly Projects starts at $69 monthly for one user, 50 documents and 250 runs. That package analyzes agreements in a table and is separate from the full CLM subscription. 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.
BlackBoiler's trial converts to a paid plan unless canceled; Pactly Projects and its CLM have separate allowances.