Gemini 3.5 AI automates multi-step workflows in apps, enabling seamless action-taking for complex tasks and productivity boos

Editorial illustration for Gemini 3.5 adds action‑taking to run complex multi‑step workflows in apps

Gemini 3.5 adds action‑taking to run complex multi‑step...

Gemini 3.5 adds action‑taking to run complex multi‑step workflows in apps

By AI Daily Post Edited by Brian Petersen, Editor-in-Chief

June 5, 2026 • 2 min read

May 2026 marked a busy week for Google’s AI roadmap. At I/O the company rolled out Gemini 3.5, a model built for “agentic” tasks that can not only reason but also take actions across apps. While Gemini 3.5 focuses on multi‑step workflows, the same event introduced Gemini Omni, a system that blends images, audio, video and text to generate high‑quality video content grounded in real‑world knowledge.

The Android Show followed with hardware designed for these models, including a new “Googlebook” from partner manufacturers. Meanwhile, Google’s consumer health push landed a refreshed Google Health app and the Fitbit Air wearable. On the research side, an initiative was announced to apply advanced quantum science and AI to life‑science problems.

All of these moves point to a single goal: make AI more proactive, helpful and woven into daily routines. The Gemini line, especially the action‑taking capabilities of 3.5, is the centerpiece of that effort, promising developers a tool that can execute complex, multi‑step processes without manual intervention.

With powerful new action-taking capabilities, Gemini 3.5 is built to help you reliably execute complex, multi-step agentic workflows across your apps. The Gemini app is becoming a more helpful AI assistant, featuring an intuitive new UI, personalized daily briefs and Gemini Spark. Instead of just answering questions, it acts as a proactive helper -- managing your inbox, scheduling appointments and anticipating your daily needs in the background.

Get more done with our advanced AI models in Search. Our next era for Search introduces new features that bring together the best of the web with the best of AI.

The latest AI news we announced in May 2026 - Google AI Blog

Why this matters

Gemini 3.5’s new action‑taking layer lets developers stitch together multi‑step workflows without writing bespoke glue code. For founders, the promise of an “intuitive new UI” and “personalized daily briefs” suggests a faster path from prototype to product, especially when the same model can act across different apps. Researchers will note Google’s two‑decade investment claim and its push to embed AI in healthcare, crisis response and education, yet the announcement stops short of detailing how Gemini 3.5 handles safety or error recovery in complex sequences.

Is the “reliable execution” of agentic tasks truly dependable, or will edge cases surface once real‑world data flows through? Our teams can experiment with the Gemini app’s “Spark” feature, but we should remain cautious about assuming seamless integration across all platforms. Ultimately, the update adds a useful tool to our AI toolbox, but its impact will hinge on transparent performance metrics and clear guidance for developers navigating these new capabilities.