GPT-Red boosts prompt injection resistance significantlyComplete entire workflows with one request using GPT-5.6You can move from conversation to documents fasterRun AI inference in the browser and cut wait timeReview how you use Claude and cut wasteLong tasks can move from draft to presentation more easilyTrack the latest safety rules for bigger modelsRun longer AI jobs with built-in external connectionsSee how Anthropic judges risky model misuseEasily automate multi-step daily tasks at lower costMake Claude easier to deploy through AWSKeep research tools and analysis in one placeDelegate more everyday coding work to ClaudeMeasure how well AI agents handle ambiguous biology research judgmentsClaude Sonnet 5 is built for heavier coding and work tasksHP partnership makes enterprise rollout easierTag Claude in Slack to delegate tasks with your whole teamHand Slack tasks to Claude more easilyConfidential AI gets stronger for sensitive workloadsGemini API key management is moving to safer auth keysGPT-Red boosts prompt injection resistance significantlyComplete entire workflows with one request using GPT-5.6You can move from conversation to documents fasterRun AI inference in the browser and cut wait timeReview how you use Claude and cut wasteLong tasks can move from draft to presentation more easilyTrack the latest safety rules for bigger modelsRun longer AI jobs with built-in external connectionsSee how Anthropic judges risky model misuseEasily automate multi-step daily tasks at lower costMake Claude easier to deploy through AWSKeep research tools and analysis in one placeDelegate more everyday coding work to ClaudeMeasure how well AI agents handle ambiguous biology research judgmentsClaude Sonnet 5 is built for heavier coding and work tasksHP partnership makes enterprise rollout easierTag Claude in Slack to delegate tasks with your whole teamHand Slack tasks to Claude more easilyConfidential AI gets stronger for sensitive workloadsGemini API key management is moving to safer auth keys
Official sources only. Rumors, leaks, and get-rich schemes are excluded.
← Back to top
AI BriefingGoogleFeature Updates00:00

AI summarized from verified sources

Run longer AI jobs with built-in external connections

Build more reliable, production-ready agents.

SOURCE CHECK

50 sources

VERIFIED

Sources

Primary / ai.google.dev

Official Docs

Supporting / ai.google.dev

Official Docs

Supporting / blog.google

Official Blog

Supporting / ai.google.dev

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / ai.google.dev

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / developers.googleblog.com

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / developers.googleblog.com

Official Docs

Supporting / developers.googleblog.com

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / x.com

Official Docs

Supporting / ai.google.dev

Official Docs

Supporting / ai.google.dev

Official Docs

Supporting / blog.google

Official Docs

Supporting / deepmind.google

Official Docs

Supporting / ai.google.dev

Official Docs

Supporting / ai.google.dev

Official Docs

Supporting / blog.google

Official Docs

Supporting / x.com

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / blog.google

Official Docs

Supporting / ai.google.dev

Official Docs

Key Points

  • 1Background execution support
  • 2Connects to remote MCP servers
  • 3Adds custom function calling

Google expanded Managed Agents in the Gemini API with background execution, remote MCP server integration, and custom function calling. Developers can now build more reliable agents that keep running and connect more easily to internal or external systems.

What changed

Google added background execution, remote MCP server integration, custom function calling, and credential refreshing to Managed Agents in the Gemini API. This makes it easier to run long tasks through a single endpoint.

Why it matters

Agent development often requires extra glue code for long-running jobs and internal system access. This update shifts more of that complexity into Google’s platform.

Impact for users

It can reduce rework when building internal tool integrations, data lookups, and scheduled automation. It is especially useful for developers embedding AI into real workflows.

h
hayami

Stay on top of OpenAI, Google & Anthropic updates. An AI digest for business professionals.

Source Policy

We use only official sources. Each article links to the original announcement so you can verify it yourself.

© 2026 hayami. All rights reserved.