D

Draftwise

Draftwise uses a firm's deal history to draft, review and negotiate agreements in Word. Its agent interprets redlines and comments, follows version history and applies precedent to new drafting tasks. Playbook Studio creates rules from example agreements and representation instructions, while Deal Table extracts terms, risks and obligations across the contract corpus. Ontonomi connects clients, matters, contractual relationships and positions into a structured model whose answers trace back to source material.

Knowledge Console controls the collections and guidance available to these workflows. The underlying document management system remains the firm's existing repository; Draftwise supplies the intelligence that turns that material into proposed legal work.

Ontonomi resolves questions through a structured map of the firm's legal relationships and shows the exact memo, clause or agreement behind each answer. This supplies an inspectable trail through the material used for the result. The drafting workflow also uses selected precedent from the document management system, and negotiation comparisons can draw on EDGAR filings. Playbook Studio lets a reviewer inspect citations while editing and exporting the marked agreement.

Accuracy and repeatability are asserted without a reproducible test set, error rate or account of unsupported questions. Those assertions should be distinguished from the source links, which establish where an answer came from rather than whether it is correct.

Playbook Studio turns uploaded example contracts and representation instructions into proposed rules that the user can refine and save. Running a review produces redlines, with a surface for inspecting citations, making manual edits and exporting the marked agreement. Knowledge Console lets administrators control collections, user access and approved playbooks across the organization. These functions give lawyers and knowledge teams specific ways to influence and inspect the work.

The drafting agent also performs work across deal history and whole agreements, but Draftwise does not describe its stop conditions or error escalation route. There is no complete account of which wider agent actions require separate approval.

Orrick, Gunderson Dettmer, Mishcon de Reya, Mayne Wetherell and Sekri Valentin Zerrouk provide named accounts of using Draftwise. Orrick partner Zac Padgett describes extracting a market percentage from comparable deal agreements during final negotiations, while Mayne Wetherell's Cameron Reeves describes quicker access to curated precedent. These examples identify practitioners and the work performed without a dated measurement method.

Playbook Studio separately claims first pass creation falls from more than six hours to five minutes and NDA review from an hour to two minutes. Those figures have no named customer, sample or evaluation method attached to the product page.

Customer data does not train public models, and Ontonomi's customer owned model is not used to train a tool sold to another firm. The data policy also prohibits sharing firm intellectual property, including trained intelligence or aggregates. Live DMS permissions govern access, while private cloud and on premises options can leave encryption keys with the firm's IT team. These commitments support confidentiality but do not explain every model provider's access or retention.

A customer subscription agreement is not available alongside the website terms. Privilege and work product protections are not expressly allocated, and private learning within the customer's own environment is distinct from the prohibition on shared training.

The product is aimed at transactional lawyers rather than a consumer seeking personal legal advice. It drafts agreements, applies precedent and analyzes negotiation positions, with lawyers able to inspect citations and revise proposed changes. Its ethical wall guidance discusses client restrictions, access control and material that should never reach AI. Draftwise makes no explicit statement separating software assistance from legal advice and sets out no competence or supervision requirements across the jurisdictions served.

The website terms disclaim accuracy in general commercial language. Neither those terms nor the professional audience amounts to a jurisdiction specific framework for responsibility when generated contract language is wrong.

Knowledge Console organizes access to precedent, users, licenses and approved playbooks, while usage analytics show adoption and engagement. The ethical wall guidance adds live permission checks and restrictions on material that may enter an AI workflow. These are controls over a firm's knowledge and access, not a release assurance framework for the vendor's models. Draftwise names no model risk owner, describes no evaluation procedure before deployment and gives no results across legal practices or populations.

Information security policies assign responsibilities to the executive team and require regular review, but do not explain how incorrect legal answers are investigated or how model behavior changes are approved.

Encryption uses AES 256 at rest and TLS 1.2 or 1.3 for transport. CloudWatch collects operational logs with alerting and anomaly detection, retaining them for up to two years. The separate retention policy sets a general maximum of five years, subject to legal requirements, and deletes data when its applicable period ends. Playbook Studio promises to delete trial uploads after the trial finishes. Information security rules restrict employee access by business need and require escalation of unusually sensitive material.

Draftwise publishes no named processor register, exact AI prompt lifecycle or customer breach notification timetable, and the general privacy page's retention heading does not supply those periods.

The August 2025 website terms address access to the site and connected media rather than setting out a complete enterprise subscription agreement. They disclaim warranties of accuracy and completeness, exclude liability for direct and indirect damages arising from site use, and require the user to indemnify Draftwise for specified claims. They also disclaim responsibility for loss or corruption of transmitted data. No monetary cap appears in those clauses.

Those clauses contain no AI output warranty, customer indemnity or contractual remedy for a failed legal workflow. A cyber insurance certificate is available by request; its cover and exclusions cannot be determined from the resource title.

Word is the drafting surface, and the connected DMS supplies agreements, clauses, tags and version history. Deal Table brings together material from iManage, NetDocuments, Google Drive and SharePoint to analyze terms and obligations. Ontonomi exposes its structured knowledge through MCP and APIs. The access approach checks the DMS using the individual lawyer's identity and live permissions, with access events intended to remain visible in the source system's audit trail.

The product pages describe what those connections support, but do not provide an implementer's complete setup guide, synchronization schedule or field mapping. Customer cloud deployment also requires coordination with the firm's IT environment.

A firm can use a dedicated private cloud on AWS, Azure or Google Cloud, deploy into its existing cloud, or run Draftwise on premises. For the private cloud option, the firm's IT controls encryption keys and auditing, vendor access is limited to support, and network access can be restricted to firm subnets. Existing cloud installation can use containers, virtual machine images or Linux binaries, with administration by Draftwise or the customer.

These are concrete hosting and tenancy choices. The default statement that data stays inside the VPC does not separately identify the location of every language model inference service, so storage control is clearer than the complete AI processing geography.

Draftwise's trust center lists SOC 2 Type I, SOC 2 Type II and ISO 27001:2022, with an ISO certificate, a SOC 2 report and a penetration testing attestation dated January 22, 2026 among its resources. Access to the certificate and report requires a request, so their auditor, scope and coverage period are not visible from the listing alone. The FAQ additionally names Cyber Essentials Plus. These standards concern the company's security rather than the accuracy of generated legal work.

The portal also lists a 2026 cyber insurance certificate and disaster recovery testing material, with the underlying terms subject to access.

Ontonomi supplies a structured legal knowledge model over the firm's clients, matters, agreements and negotiated positions. It connects those relationships and traces answers back to their source clauses or memoranda, while the drafting system applies precedent and review rules to Word agreements. The knowledge architecture supporting the AI workflows is therefore described. Draftwise does not name its language model providers or versions, or say how individual tasks are allocated among models.

AWS, Azure and Google Cloud are hosting choices rather than an identification of inference suppliers. The promise against training public models leaves open where each provider processes a request and how substitutions are communicated.

Draftwise requires a sales discussion for product pricing. Neither the core product pages nor the FAQ give a rate, charging unit, tier structure, deployment fee or enterprise minimum. Playbook Studio has a free trial registration route and promises deletion of uploaded material when that trial ends, without stating an ongoing subscription price there. The website terms describe card, wire and ACH payments, recurring billing and cancellation at the end of the paid term.

Those payment mechanics say nothing about the cost of a firm deployment. Private cloud, existing infrastructure and on premises arrangements also lack a stated implementation charge.

Large and midsize law firms and corporate legal teams use Draftwise for transactional work. Its in house examples span advertising technology, defense contracting, investment funds, life sciences, real estate and software companies. Ontonomi adds concrete relationship models for funds and side letters, acquisitions, lending arrangements and corporate contract obligations. Named customers include Orrick, Gunderson Dettmer, Mishcon de Reya, Mayne Wetherell and Sekri Valentin Zerrouk, reflecting practice across several legal markets.

The depth of precedent available depends on the firm's own connected corpus. Draftwise does not list unsupported agreement types, set jurisdiction boundaries or say how far support extends beyond transactional practice.