Google just shifted the agent workflow from the cloud to the desktop
Google has transitioned its agent workflow from cloud-based systems to a local desktop environment. This shift is marked by the introduction of Gemini 3.5 Flash and Antigravity 2.0, which enhance the speed and efficiency of agent development. The new tools allow developers to manage multiple agents and tasks more effectively, transforming the approach to building AI agents.
- ▪Google has released Gemini 3.5 Flash, a faster model for agentic workflows.
- ▪Antigravity 2.0 is a standalone desktop application that serves as a hub for agent interaction.
- ▪The new local-first approach allows for parallel task execution and integration with existing tools.
Opening excerpt (first ~120 words) tap to expand
try { if(localStorage) { let currentUser = localStorage.getItem('current_user'); if (currentUser) { currentUser = JSON.parse(currentUser); if (currentUser.id === 3928059) { document.getElementById('article-show-container').classList.add('current-user-is-article-author'); } } } } catch (e) { console.error(e); } albe_sf Posted on May 20 Google just shifted the agent workflow from the cloud to the desktop #ai #agents #devtools #machinelearning Google's latest announcements for agentic AI are more than just a new model. The release of Gemini 3.5 Flash and the Antigravity 2.0 development platform signals a shift from prompt-driven exploration to a more grounded, local-first engineering workflow for building agents.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at DEV.to (Top).