Release Notes

Get instant answers about how to use Harvey by asking Harvey directly.

Upload documents alongside Ask LexisNexis® queries, allowing for more context while performing case law research and drafting abilities with context from documents.

Unlock password-protected, encrypted files directly in Harvey and work with them like any other file, without needing to decrypt files externally and remove passwords in advance.

Harvey can produce outputs better aligned with your jurisdiction and preferred language.

To simplify and clarify our product terminology, we’re renaming “Vault projects” to “vaults.”

GPT-5.1 is available in Harvey’s Model Selector across Assistant, Vault, and Workflow Builder.

Harvey now supports querying across two sources at once — giving you broader access to the context you need without switching tools or re-uploading files.

A redesigned sources panel will make it easier to navigate, search, and interpret citations — with clearer icons, a new search bar, and auto-updating sources that stay aligned with your current thread view.

Harvey just got smarter—refining its approach to find the right information and deliver more accurate answers from your documents and Vault projects.

Harvey’s Deep Research connects across multiple trusted sources—Vault, iManage, web, file uploads and Knowledge Sources —to deliver comprehensive, well-cited reports that help you understand the full picture faster.

Organize workspace members with public and private groups, making it easier to manage sharing, personalize collaboration, and control access across matters and departments.

Choose where to save your query to better organize projects and share work across your team.

Easily enable new features across your team with simplified admin controls and dedicated pages for each opt-in feature.

Harvey can now read and understand comment bubbles inside of Word documents.

Use web search within the Workflow Builder to incorporate up-to-date, real-world information directly into your workflows.

Run workflows that combine local uploads, DMS files, and Vault files in a single run.

Turn any document into a reusable template — Harvey will automatically detect names, addresses, and other variable fields, replacing them with placeholders.

Easily transfer project ownership when responsibilities change—keeping projects organized and collaboration seamless.

Work seamlessly between iManage and Harvey—select documents and ask questions without leaving iManage.

We've added citation-backed legal knowledge for Austria (RIS), Germany (Gesetze-im-Internet), and Canada (Justice Laws & Ontario e-Laws), enabling precise, jurisdiction-specific answers directly in Assistant.

UX Improvement that flags to customers that their query is going outside of Harvey, thus reminding them not to include any sensitive information.

Source details now appear directly in the source picklist and in filter chips, giving you more clarity and control when selecting or refining sources.

Quickly fill Word templates with uploaded information—Harvey populates standard templates automatically to save you time on document creation.

Answer questions with trusted, AI-powered insights from LexisNexis® primary law.

Quickly add, delete, and replace all of the embedded files in a custom workflow with a new file management UI.

Draft, revise, and summarize emails directly in Outlook.

Harvey Assistant just got smarter—GPT-5 is now the default model for all chat and draft responses, bringing major upgrades in reasoning, reliability, and writing quality.

Easily remove sensitive information from Word documents using the new Redact workflow.

Harvey now supports Claude Sonnet 4.5, Anthropic’s latest reasoning model—optimized for code, numbers, and complex legal work.

We've made several improvements to Harvey for Word, including faster playbooks, web search access, and saving directly to Vault.