Google Vault adds filtered exports for Gemini in Workspace
Google announced that Vault now supports filtered exports for Gemini in Workspace. The feature adds a new data source to AI compliance, letting admins filter and export Gemini conversations across Gmail, Drive, Docs, Sheets, Slides, Meet. Admins can define export scopes by custodian and date range, up to 5,000 users per OU, and choose time zone. The update aligns with Vault’s security controls…
Key points
- Google Vault now lets admins filter and export Gemini in Workspace conversations by custodian and date range, up to 5,000 users per OU.
- Exports are in JSON with Gemini‑app metadata, including prompts, AI responses, generated attachments and links to Workspace files.
- Available now for Business Plus, Enterprise and Education plans; Vault API export support will be added within 14 days.
Exports are delivered in JSON with metadata matching the Gemini app format, including prompts, AI responses, generated attachments, and links to referenced Workspace files. The UI lets admins choose the new “Gemini in Workspace” service from the alphabetized dropdown on the Search tab, set custodian, OU and date filters, then click Export. Exported JSON files retain the conversation context, such as user prompts, AI replies, any images generated by Gemini, and citations to Drive documents or Gmail threads. API support will be added within 14 days, and API users will gain the same capability after the 14‑day rollout. The capability is available now for Business Plus, Frontline Standard and Plus, Enterprise Essentials Plus, Enterprise Standard and Plus, Education Fundamentals, Standard and Plus. Future releases will add retention rules and litigation holds.
The story so far
4 episodes →- Google Vault adds filtered exports for Gemini in Workspacethis story
Google Vault now supports filtered exports for Gemini in Workspace
Google Workspace Updates · 22 October 2026
Loading the full article…
This text was published by Google Workspace Updates and written by Paul Jiménez Vela (noreply@blogger.com). It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Enterprise & Industry
All →- Anthropic adds continuous scanning and fix tracking to Claude Security beta · 3 src
- OpenAI adds models and Codex to Google Cloud for developers · 6 src
- EXL says enterprise AI success depends on serving harness, not model choice · 1 src
- Smartsheet launches MCP Server for AI agents to manage work data on AWS · 2 src
- Nvidia launches Minerva AIOps platform for AI factory observability · 4 src
Comments
via GitHub Discussions