Gmail's Gemini Flows adds AI-powered email filtering with 2,000 message monthly limit on Pro tier
Google's Workspace Studio Flows is now available to Google AI Pro ($20/month) and Ultra ($100/month) subscribers, bringing AI-powered email filtering to Gmail. The service processes up to 2,000 emails monthly on Pro tier and 10,000 on Ultra, potentially limiting utility for high-volume users receiving thousands of messages weekly.
Google has expanded access to Workspace Studio Flows, its AI-powered email automation tool, to subscribers of its paid Gemini tiers. The feature, previously limited to full Workspace accounts, is now available to Google AI Pro ($20/month) and Ultra ($100/month) users as of late May and June 2026.
How Gemini Flows works
Flows enables users to create AI-powered scripts that automatically process incoming Gmail messages. The system uses Gemini to analyze email content and apply actions based on custom prompts, addressing a long-standing limitation of Gmail's traditional rule-based filtering.
Users define a trigger (such as "when I get an email") and specify an action. One key capability is "Add labels with Gemini," which allows the AI to categorize messages based on semantic understanding rather than keyword matching. For example, a user can create a prompt instructing Gemini to identify and label all press releases and promotional emails with journalistic intent, regardless of variations in sender structure or wording.
The interface includes pre-built templates and a testing function that allows users to validate their flows against existing emails before deployment.
Monthly processing limits
Google AI Pro tier subscribers are limited to 2,000 flow executions per month—meaning the AI can process a maximum of 2,000 incoming messages. The Ultra tier increases this limit to 10,000 executions monthly.
According to testing by ZDNET's David Gewirtz, these limits may restrict the feature's usefulness for high-volume email users. Gewirtz reported receiving 7,724 messages in a single week during a busy news cycle, with monthly volumes regularly exceeding 10,000 messages during periods of major AI announcements or holiday seasons.
Additional limitations
Flows can generate email drafts but cannot automatically send them—users must manually review and click to send any AI-generated responses. The feature works across multiple Google Workspace applications including Chat, Docs, and Meet, not just Gmail.
AI-powered labeling requires users to enable Google's default set of six AI labels, though custom labels can be added.
What this means
Gemini Flows represents Google's first significant update to Gmail's filtering capabilities in over 20 years, addressing the semantic understanding gap that rule-based filters cannot solve. However, the monthly execution limits create a narrow "Goldilocks zone" where the feature is most useful: users must receive enough email to benefit from AI assistance but not so much that they exceed the monthly quota within days. For enterprise users or journalists managing thousands of weekly messages, the Pro tier's 2,000-message limit may prove insufficient, while the Ultra tier's $100/month cost for 10,000 executions represents a significant premium for email management alone.
Related Articles
Google Expands Gemini-Powered Ask Maps Globally With Personal Intelligence, Real-Time Transit, Agentic Ordering
Google Maps' Gemini-powered Ask Maps chat is rolling out globally to English speakers in Australia, Brazil, Canada, Indonesia, Japan, Mexico, and over 150 other countries and territories. The update adds Gmail-based Personal Intelligence, real-time transit data, conversation memory, and agentic capabilities for ordering food and booking hotels.
Anthropic Makes Auto Mode Default in Claude Code for Pro, Max, and Team Plans Starting August 14
Anthropic will make auto mode the default setting for new Claude Code sessions on Pro, Max, and Team plans starting August 14, 2026. The company cites a 1,053-person study showing auto mode blocked 89% of harmful actions compared to 13.6% for human reviewers, plus a third-party test claiming zero successful prompt injections out of 720 attempts.
Anthropic Makes Claude Code's Auto Mode Default, Cutting Dangerous Command Approvals by 75 Percentage Points
Anthropic will enable Auto Mode by default in Claude Code for Pro, Max, and Team plans starting August 14, 2026. Internal testing with 1,053 paid users found the classifier-based system caught 89% of dangerous commands compared to 13.6% caught by human reviewers, while producing 25% more pull requests.
Anthropic Adds Cross-Session Messaging to Claude Code, Letting Terminal Instances Communicate Directly
Claude Code sessions running on macOS and Linux can now send messages to one another instead of requiring users to manually copy context between terminals. Anthropic says the feature supports both local and cross-machine communication, though it's not yet available on major cloud platforms.
Comments
Loading...