C
Contracts 365

Contracts 365 is contract lifecycle management software for organizations that run on Microsoft 365. The Newburyport, Massachusetts company started as Corridor Company and took the name of its flagship product in 2022. The application handles contract requests, approvals, negotiation, signature and obligations, with SharePoint in the customer's own Microsoft 365 tenant as the contract repository. Legal, procurement and business users work from standard request forms, approved clauses and configured routing, and connections include Outlook, Word, Power Platform, Dynamics 365, Salesforce, DocuSign and Adobe Sign.

The AI Extraction Companion uses Azure OpenAI to summarize agreements, identify clauses and pull out data such as contract dates and payment terms. Each extracted value links to the language that supports it, and a reviewer approves the update before repository metadata changes. Contracts 365 puts extraction accuracy in the 90th percentile out of the box, varying by document and field. The AI Negotiation Companion works inside Word, compares counterparty language with approved positions, suggests revisions, flags watchlist issues and keeps a record of each negotiation round.

Fender chose the platform for retail and licensing agreements, Bell Partners runs its real estate contracts on it, and Chelan PUD says work that took weeks now takes days. Standard and Enterprise editions are quoted, with annual software pricing from $35,000 and implementation from $30,000.

Capability grades

All 15 axes, graded from public sources on the date shown. Hover a grade to see what the letter means on that axis.

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

AI Centrality

How much of the product is actually AI. Whether the machine learning is the mechanism the buyer is paying for or a feature layered onto conventional software, and whether the vendor is specific about which is which.

The platform provides a repository, request and approval workflows, electronic signature connections and obligation tracking, and its embedded AI companions handle tasks inside those workflows. The Extraction Companion uses a model to identify agreement details, summarize a contract and propose metadata updates. In Word, the Negotiation Companion compares clause language with a playbook and proposes replacement wording.

A buyer can run routine work through the contract workflow and SharePoint repository and add AI for ingestion or negotiation. AI lives inside the lifecycle system rather than in a separate drafting or research environment, and both companions are sold as add ons to either edition.

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

Citation Accuracy and Hallucination Disclosure

Whether the vendor publishes measured accuracy on citations and assertions, grounds output to primary sources, and says plainly what its system does when it does not know. Legal has a documented public record of fabricated citations reaching filed briefs, so an untested claim of accuracy is not evidence.

An extracted value can link to the text in the source agreement. The comparison screen shows the prior and proposed values so the reviewer can open the supporting language and validate a change. The negotiation tool identifies deviations from approved clauses and captures each draft and change in the record. Contracts 365 reports extraction accuracy in the 90th percentile out of the box and says quality varies by document and field.

Its product materials do not describe independent testing of legal citations or a process for establishing the current treatment of a statute or case.

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

Autonomy and Oversight Model

What the system decides on its own, what a lawyer must approve, and whether the vendor documents where the review point sits. A tool that drafts under review and a tool that files without one are different products and different risks.

The Extraction Companion shows proposed metadata beside the current values. Reviewers inspect the source language and approve the True Up step before any repository value changes. In Word, negotiation suggestions can be reviewed, applied or assigned to a colleague. Watchlists flag defined risks, guardrails hold positions that cannot be negotiated, and workflow rules route documents to the right staff. The organization decides which changes reach its repository and drafts. No agent accepts a contract on its own or skips the review chain a customer sets.

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

Operational and Outcome Evidence

Named, dated evidence that the product works in production at real firms or legal departments. Case studies with figures and identified customers count. Unattributed testimonials and launch announcements do not.

Fender selected Contracts 365 to improve its handling of retail and licensing contracts after weighing its Microsoft integration and generative AI. Bell Partners uses it as the contract management foundation for its real estate operations. Mark, a purchasing and contract administration supervisor at Chelan PUD, says the contracts team now handles more requests and that some work that used to take weeks takes a few days.

Contracts 365 also cites extraction accuracy in the 90th percentile under typical conditions, varying by document and configuration. No named customer measures how much the AI alone cut review time or errors.

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

Privilege and Confidentiality Posture

How client confidences are handled: attorney client privilege and work product treatment, segregation of one client matter from another, whether client data trains any model, and what the vendor commits to in writing rather than in marketing.

The terms of use describe subscriber data as stored in the customer's Microsoft 365 instance. The subscriber agreement must grant rights to use the data as necessary to provide the service. The extraction product page says customer data does not train its models, and the platform describes compatibility with Microsoft identity and security controls. Administrators can configure access and participation using existing systems and roles.

The public materials do not give a privilege waiver undertaking or describe whether the AI companions explicitly enforce an ethical wall that covers all of a law firm's document sources.

Source: Vendor Published
CC on UPL and Professional Responsibility PostureA boilerplate disclaimer sits in the terms while the marketing describes the product in advice terms, or the intended audience is left ambiguous.

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.

The negotiation tool compares text to the organization's approved language and lets the reviewer choose whether to accept a suggestion. Watchlists can surface issues for additional attention, and workflows can direct a contract to legal staff. The use cases involve internal legal, procurement, and business users working from different roles. The service materials do not describe how the system distinguishes a request for legal advice from an internal policy comparison.

They also do not map its workflow to bar rules or prescribe how a nonlawyer user should handle a question beyond their authorization.

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

AI Governance and Bias Disclosure

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

Organizations define approved clauses, risk indicators and negotiation strategies so suggestions follow their own playbooks. Guardrails mark positions that cannot be negotiated, and watchlists call attention to language outside a preferred position. The platform captures drafts, counterparty changes and AI assisted revisions, and extraction reviewers see the text behind each proposed value. These controls govern how the tools are used in a customer's contracting workflow.

There is no bias evaluation across agreement types or jurisdictions, and nothing explains how a model change is reassessed against contract review reliability.

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

AI Safety and Data Stewardship

Retention, deletion, access control, and what happens to prompts and documents after they are processed. Whether the vendor states its subprocessors and its incident practice, or leaves the buyer to assume.

Executed contracts and repository metadata are kept in the customer's Microsoft 365 tenant. Contracts 365 says the AI tools do not use prompts, completions, and customer contract data to train foundation models without permission. The public privacy policy separately covers service and account personal data and gives general retention criteria for that information. Contract retention can follow the organization's SharePoint policies, but those policies do not establish retention for every inference event.

The public materials do not specify a universal retention period or configurable deletion deadline for AI prompts and outputs outside the repository.

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

AI Liability and Recourse

What the vendor stands behind contractually when its output is wrong. Indemnities, caps, carve outs, insurance, and whether any of it is published or only reachable through a negotiated agreement.

The website terms of use separate the service users receive from any express warranties in a signed subscriber service agreement. They provide the service as is, exclude classes of indirect loss and, where a statutory warranty cannot be excluded, limit the remedy to supplying the service again or paying for it. Subscribers stay responsible for maintaining their data in Microsoft 365. No remedy addresses a missed negotiation issue or a wrong extraction, and the subscriber agreement that may change these terms is not public.

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

Practice Systems Integration Depth

How deeply the product reaches into the systems legal work already lives in: document management such as iManage and NetDocuments, Word and Outlook, contract lifecycle management, matter management, e-billing, and court filing systems.

The customer's SharePoint tenant is the working contract repository. The Negotiation Companion runs inside Microsoft Word, and Outlook and Power Platform support related workflows. Salesforce and Dynamics 365 connections link contracts to customer records, and Adobe Sign and DocuSign handle signatures. Repository values update only after a reviewer approves proposed extractions. Together these cover the contract file, the review environment, customer records and execution. APIs and workflow options handle requirements the standard integrations and configuration cannot meet.

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

Deployment Model and Data Residency

Where the software runs and where the data sits. Multi tenant cloud, single tenant, private deployment, on premises, and whether region of residence is a published option or an enterprise conversation.

A cloud application connects to the buyer's Microsoft 365 environment. The terms say subscriber data is kept in the customer's Microsoft tenant, while the privacy policy names Microsoft Azure as the host for the subscription service. The customer can manage its SharePoint repository within its tenant and retains responsibility for the integrity and security of stored data. The privacy policy also allows processing of personal information in the United States.

The public materials do not identify each inference processing location or describe a version of the application that customers can install entirely on their own premises.

Source: Vendor Published
CC on Security Certifications and Trust CenterBadges appear on the site with no scope, no date, and no report available.

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.

Microsoft identity and security controls underpin the platform, which adds role based permissions of its own. The privacy policy states participation in the applicable Data Privacy Framework programs and names major service providers, Azure among them, and enterprise buyers can review additional security documentation. These disclosures cover account controls and the named infrastructure. No SOC 2 report or ISO 27001 certificate covering the Contracts 365 application itself is identified, and Microsoft's certifications do not extend an audit to the vendor's software.

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

Model Supply Chain Disclosure

Which models sit underneath, whose they are, where they run, and whether the vendor commits to telling customers when that changes. A legal buyer inherits every dependency it cannot see.

Microsoft Azure OpenAI supports the Extraction Companion. The vendor adds its own prompts and lets administrators refine those prompts and extraction rules for their organization's documents. Contracts 365 says the module does not require a separate Microsoft Copilot license. It also describes safeguards for customer prompts, completions, embeddings, and training data. The public product materials identify the provider and distinguish the company software from a separate Copilot tool.

They do not give a complete version and routing policy for models behind every negotiation, extraction, and summarization feature available in the platform.

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

Commercial Transparency

Whether a buyer can learn what this costs without entering a sales process: published rates, the unit being charged, what sits behind an enterprise tier, and what implementation adds.

The pricing page describes Standard Edition for smaller and midsize teams and Enterprise Edition for large organizations, priced by quote, with AI companions, integrations and business modules as add ons. The company's 2026 new customer form states that pricing starts at $35,000 a year and implementation services at $30,000, and that user numbers, scope and configuration can raise both. FastTrack, an implementation package listed on Microsoft AppSource, launches Standard Edition in weeks.

Neither companion carries a separate price, and there is no seat schedule. The two figures are floors for software and implementation rather than the cost of a particular setup.

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

Firm and Practice Coverage

Who the product is actually built for. AmLaw, midlaw, small firm and solo, in house departments, government and courts, and which practice areas are supported rather than merely claimed.

In house legal, procurement, operations and business teams managing many contract types in a Microsoft environment are the buyers. Examples include retail and licensing agreements, lease administration, supplier agreements and transactions in financial services, life sciences and public utilities such as Chelan PUD. Standard Edition serves smaller and midsize teams, and Enterprise adds options for large organizations.

Users configure risk positions and clause lists for different contracting processes. The work runs from request through negotiation and approval to obligations after signature, and it stays with organizations' own contracts rather than litigation, consumer legal advice or case law research.

Source: Vendor Published
Sources on file

5 public documents

The public pages on file for Contracts 365, with the recorded signals each one supports and the date it was last read. Open any of them and check the reading against the record.

Pricing

From $35,000 annually

USD, as published, never converted
  • Contracts 365 offers Standard and Enterprise editions by quote.
  • Annual software pricing starts at $35,000.
  • Implementation starts at $30,000. User counts, scope and configuration affect the quote.
  • The AI companions are add ons with no separate listed price.

Quoted annual software subscription. The entry figure is the platform minimum stated on the vendor's 2026 new customer form.

Implementation: Implementation services start at $30,000. The FastTrack package launches Standard Edition, and advanced AI configuration and training can be scoped separately.

Note: The 2026 new customer form states the $35,000 software and $30,000 implementation floors and that actual pricing can be higher. Editions and add ons are otherwise priced by personalized quote.

Legal Signals

What each signal means

A signal records what public sources say on the date shown. It is not a grade and it is not a recommendation. Where a signal reads Not addressed, it means the index did not locate the material in public sources on that date, which is a statement about disclosure rather than about the product.

Confidentiality and Privilege

Client Data in Training

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

Never, in policy only

A public policy or trust page states no training on customer content, with no matching term located in the published agreement.

The AI Extraction Companion page states that Contracts 365 never uses customer data to train the models, and the negotiation material says foundation models are trained on customer prompts, completions or data only with permission or instruction. The public terms of use carry no matching clause.

Source: Vendor PublishedContracts 365 never uses customer data to train the modelsAs of Nov 19, 2026Evidence

Prompt and Output Retention

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

Not addressed

No located public material states how long prompts and outputs are retained.

Subscriber contracts stay in Microsoft 365 under the organization's own SharePoint retention policies, and the privacy policy gives general criteria for personal information. No retention period covers AI prompts and outputs outside the repository.

Source: Operator VerifiedAs of Nov 19, 2026Evidence

Ethical Walls and Matter Segregation

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

Claimed, not documented

Segregation is asserted in public materials with no published detail on how it is enforced.

The platform uses existing Microsoft identity, permissions and compliance controls, and contracts sit in the customer's own SharePoint. How those permissions carry into what the AI companions read is not described.

Source: Vendor PublishedAs of Nov 19, 2026Evidence

Third Party Request and Subpoena Notice

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

Disclosure addressed, notice absent

Published terms or policy address disclosure to authorities or in response to legal process, and no commitment or reservation regarding customer notice is located anywhere. The vendor has told the customer that data can leave and has said nothing about whether the customer hears of it.

The privacy policy allows disclosure of personal or usage information by court order, subpoena or other legal process, with no promise of advance notice to the affected customer. Contracts themselves sit in the customer's own tenant.

Source: Vendor Publishedby court order, subpoena or other legal processAs of Nov 19, 2026Evidence
Accuracy and Authority

Primary Law Corpus Provenance

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

Not addressed

No located public material identifies the corpus behind the product’s answers.

The companions work from the organization's own contracts, clause library and approved positions, with prompts the vendor supplies and administrators can refine. No licensed collection of legal authority stands behind them.

Source: Operator VerifiedAs of Nov 19, 2026Evidence

Good Law Verification

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

Not addressed

No located public material addresses whether authority is checked for subsequent history.

The companions compare contract clauses against approved language and link extracted values to the source text. Neither checks a cited statute or case, and no citator is attached.

Source: Operator VerifiedAs of Nov 19, 2026Evidence

Refusal and Uncertainty Behavior

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

Not addressed

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

Watchlists flag predefined risk patterns and guardrails hold fixed positions for a reviewer. Nothing makes a companion withhold a recommendation it is unsure of.

Source: Operator VerifiedAs of Nov 19, 2026Evidence

Fabricated Citation Record

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

None located

No court order, opinion or disciplinary record addressing fabricated or hallucinated legal citations produced by this product has been located as of the date shown. This is a statement about the public record on that one subject, not a finding about the product, and this signal is not a litigation history.

No court order or disciplinary decision in the AI Hallucination Cases database attributes a fabricated citation to Contracts 365 or its former name, Corridor Company. The companions work on contract language rather than legal citations.

Source: Operator VerifiedAs of Nov 19, 2026Evidence
Professional Responsibility

Bar Guidance Alignment

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

Not addressed

No located public material engages with bar or ethics guidance.

Organizations configure their own playbooks, guardrails and review routing for the AI companions, and reviewers approve every extracted value and suggested edit. No bar guidance on lawyers' use of AI is mapped to the product.

Source: Operator VerifiedAs of Nov 19, 2026Evidence

Billing and Fee Posture

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

Savings claims only

Public materials claim time savings without addressing billing or disclosure, and the product sits inside a fee relationship between a lawyer and a client where those savings would change the bill.

Contracts 365 promotes faster contract work and less manual review, and Chelan PUD reports weeks of work reduced to days. Nothing records AI use for fee purposes or helps disclose it to legal clients.

Source: Vendor PublishedAs of Nov 19, 2026Evidence

Outside Counsel Guideline Readiness

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

Subprocessors listed

A current subprocessor or model provider list is published.

The privacy policy lists service providers and their roles, including Microsoft Azure for hosting and Adobe Sign and DocuSign for signatures, and the Extraction Companion runs on Azure OpenAI. Enterprise buyers can request further security documentation.

Source: Vendor PublishedAs of Nov 19, 2026Evidence

Court Disclosure Support

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

Partial record

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

The Negotiation Companion records drafts, counterparty changes and AI assisted revisions for each negotiation round, and extraction updates pass through an approval step. That history is not packaged as a court disclosure naming the model, its prompts and the reviewer.

Source: Vendor PublishedAs of Nov 19, 2026Evidence
Contact

Correct a record, or ask how something was graded

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

AI Legal Index

The AI Legal Index is an independent index that tracks changes to AI vendors in legal. It holds 535 vendors across 9 categories, each graded on the same 15 capability axes and recorded against 12 legal signals, from public sources. No vendor pays for inclusion, placement, or rating.

Index Status
Last index update
November 19, 2026
The AI Legal Index is an editorial reference. It is not a regulatory body, not a law firm, and nothing published here is legal advice or a recommendation to retain or avoid a vendor. Records are verified against published sources, bar guidance and public court records. Where a record reads not addressed, the material was not located in public sources on the date shown. See the Methodology page for evaluation standards and limitations.
© 2026 AI Legal Index
3801 N Capital of Texas Hwy, Ste E240 · Austin, TX 78746