D

DraftPilot

DraftPilot's main product is model driven review and drafting inside Word. A selected playbook supplies preferred positions and fallbacks; the AI identifies departures, proposes language, and explains changes to the reviewer. The same models generate playbooks from past work and support conversational drafting, comparison, and research. Mass Review uses AI to answer questions across agreements and connect findings with source language.

Conventional functions such as workspaces, permissions, and file conversion support that workflow, but they are not an independent contract management system. Removing the models would remove the review, analysis, and drafting service that customers buy.

AI Chat uses a curated legal network containing legislation, secondary sources, and commentary, with general web access excluded from legal research. Its research guide instructs users to specify the jurisdiction and inspect the list of source links used in an answer. Research can then become proposed changes to the contract, subject to reviewer acceptance. Mass Review separately lets users inspect the contract language underlying a table result.

Published totals for the research network differ between the FAQ, guide, and trust center. No reproducible accuracy test, source freshness method, or systematic citation treatment results accompany those totals.

The enterprise workflow divides authority between legal and approved business reviewers. Legal owns playbooks, permissions, acceptable positions, and escalation rules; procurement or contract managers perform a bounded first review on agreed contract types. Issues outside the approved route return to legal or the appropriate specialist with the clause and business context. The product proposes tracked edits and comments in Word, which authorized reviewers can edit, accept, or reject.

DraftPilot expressly describes this arrangement as something other than autonomous contracting. Its control boundary is organizational approval and exception routing, rather than a published numeric model confidence threshold.

Axiom's 2025 white paper describes an eight week pilot in which 18 volunteer attorneys used DraftPilot on client work after an evaluation of eight suppliers. Evidence came from surveys, product analytics, participant calls, and feedback sessions. Forty four percent of participants reported time savings in the 40 to 60 percent band, while 16 of 18 reported moderate or significant improvement in work quality. The vendor's case study also separates tasks such as drafting, issue spotting, and summaries.

These are reported observations from motivated volunteers, not a randomized benchmark. Raising Cane's provides another named deployment involving real estate positions and lease review.

DraftPilot states that customer material does not train its models or public models, and its security guide says original contracts are not stored after analysis. Playbooks remain in the customer's workspace, with permissions controlling their use and editing. OpenAI inputs and outputs receive the stated zero retention arrangement. The broader trust center also names Anthropic and lists 30 days for generated redlines and comments, which narrows the general no retention headline.

No accessible commitment directly addresses attorney client privilege or work product. The linked customer terms require sign in, and the trust center requests access before releasing the service agreement or DPA.

The enterprise operating model keeps legal judgment with lawyers and approved specialists. Procurement and contract managers may conduct an initial review only within legal's chosen contract types, positions, and escalation rules. Suggested language remains subject to acceptance, and exceptional issues return to the legal team. This division keeps assistance separate from professional judgment and reserves consequential advice for legal.

The research guide also asks the user to state a jurisdiction and intended use. Public pages do not define professional eligibility by jurisdiction or connect those controls to specific competence and supervision duties.

DraftPilot's trust center publishes principles covering privacy in product design, human empowerment, and transparency through security certification. It also describes output protection, operational guardrails, and grounding of AI Chat in a verified source network. Those statements give a direction for responsible use but do not identify an accountable model owner, a release evaluation procedure, or results across languages and contract types.

An AI Governance Policy is listed among resources that require access approval, so its contents cannot establish additional public controls. Customer playbooks and escalation rules govern a customer's review process; they do not disclose the vendor's own model testing.

Public resources distinguish contract analysis from stored customer configuration. The security guide says playbooks normally reside on AWS in Ireland and describes immediate deletion of OpenAI API inputs and outputs. The AI posture page separately lists 30 days for generated redlines and comments. Administrators use SSO, SCIM, workspaces, and permissions to control access. Twelve subprocessors are named with service roles, including hosting, model, email, analytics, and business operations providers.

Encryption is specified for transit and storage. However, a complete deletion process for retained playbooks, a binding incident notification period, and the DPA terms are not available in the readable public material.

DraftPilot links to customer terms on SharePoint, but the linked document leads to a Microsoft sign in page. Its public trust center lists a Master Services Agreement and DPA behind an access request. As a result, no readable contract establishes liability caps, indemnity scope, an AI output warranty, or remedies for an incorrect clause or research answer. This is an access limitation, not evidence that the negotiated agreement lacks those provisions.

The published review workflow allocates final decisions to authorized people, but that operational allocation does not reveal what financial responsibility DraftPilot accepts when its service makes an error.

The Microsoft Word connection has a described installation and editing path. Users install the add in through AppSource or central IT deployment, open it from the Word ribbon, and work with the agreement already being negotiated. Proposed language becomes native tracked changes, while explanatory comments accompany the edits. Reviewers can accept, reject, or alter individual suggestions and handle later rounds by focusing on counterparty changes.

AI Chat can insert drafting or tables into the same file. Workspaces and identity controls manage product access. No comparable public sync specification describes a connection to a legal document management repository.

DraftPilot is delivered through a Word add in and a browser interface, with hosted services handling analysis and team configuration. Its security guide places default playbook storage on AWS in Ireland and offers United States only hosting on Enterprise. The subprocessor list separately identifies Heroku in Ireland and OpenAI and Anthropic in the United States. Those provider locations do not establish where every model request is processed.

The guide's OpenAI zero retention statement addresses persistence, not processing geography. Public materials therefore identify hosting choices and part of the provider chain without a complete regional account for all AI tasks.

The public trust center names SOC 2 Type II and ISO 27001, with an ISO 27001:2022 certificate and a SOC 2 report listed as resources. Both require access approval, so their audit periods, organizational scope, and qualifications are not visible in the accessible pages. GDPR and UK GDPR are presented as compliance frameworks rather than independent security certifications. Additional resources include a network diagram and CAIQ Lite questionnaire, also behind requests.

Product pages specify AES 256 encryption at rest and TLS 1.2 in transit. These published controls support the security description but do not replace examination of the underlying reports.

The main FAQ identifies OpenAI as the provider behind the contract workflow. The trust center supplies a broader inventory: GPT 4 Turbo with an April 2024 version identifier, and Anthropic Claude 3.5 Sonnet with an October 2024 identifier, both accessed through APIs. The subprocessor list confirms both companies and associates them with AI services. The security guide explains OpenAI's zero retention arrangement, but does not extend that provider specific statement expressly to Anthropic.

Public material does not map every feature to its active model or commit to customer notification when a model changes. The inventory therefore discloses providers without a complete change framework.

DraftPilot Pro starts at £7,200 per year for a minimum of three users, equivalent to £2,400 per user annually. A separate Customer Success Advisory Fee applies without a published amount. Everyday review and chat are unlimited under the package, while Mass Review includes an allowance and optional additional capacity. Pro includes playbooks, workspaces, identity controls, onboarding, and optimization support. Enterprise uses a negotiated organization package with tailored deployment and ongoing support.

The posted subscription amount is therefore a real entry point, but it is not the complete first year cost because advisory charges and additional portfolio analysis remain unspecified.

DraftPilot primarily addresses corporate legal departments handling repeatable commercial agreements. Its enterprise workflow also supports procurement teams and contract managers operating within legal's approved boundaries. The playbook materials cover agreements such as NDAs, services contracts, statements of work, data processing terms, and reseller arrangements. Axiom's deployment extends the audience to lawyers delivering client services, while Raising Cane's demonstrates lease and real estate work.

The FAQ describes review across more than 58 languages, including applying a playbook in a different language from the agreement. That breadth is not accompanied by a jurisdiction by jurisdiction account of supported law or tested performance.