Philipp Schmid

Excited to introduce the Gemini Interactions API, a unified interface for Gemini models and agents. Starting today with Gemini Deep Research Agent. - Unifies access to models and agents via a single RESTful endpoint. - Access Gemini Deep Research agent via API. - Optional server side context management. - background execution for long-running inference. - Remote Model Context Protocol (MCP) servers support. Spent the last six months building this with an amazing team! I couldn’t be more proud and excited. Models evolve into systems and we want to give you the best developer experience. Give it a try and share your feedback. We will listen and want to build this with you in public.

Turn prompts into production-ready apps with @GoogleAIStudio newly upgraded vibe coding experience! - Powered by the new Google @antigravity coding agent. - Integrates @Firebase for secure sign-in and Cloud Firestore. - Supports @nextjs, React, and Angular out of the box. - Stores API keys safely in the new Secrets Manager.

@OfficialLoganK LFG! Great effort by the team! Step by step.

Lots of great Gemini API updates shipping today 🛠️ 1. Built-in tools (search, maps, file search) now work with function calling 2. We now do context circulation with built-in tools for better model performance 3. Grounding with Google Maps now works with Gemini 3!!

Blog: blog.google/innovation-and… Example: #combining_built-in_tools_and_function_calling" target="_blank" rel="nofollow noopener">ai.google.dev/gemini-api/doc… Docs: ai.google.dev/gemini-api/doc…

We shipped one of the most requested Gemini API features! 🥳 You can now combine built-in tools (Google Search, URL Context,…) with your own functions custom in a single API call. Gemini orchestrates everything: 🔧 Combine Google Search, Google Maps, File Search or Url Context with custom tools in one API call 🔄 Built-in tool context is circulated with signatures. 🤖 Gemini decides tool order and chains results. 🆕 Google Maps is now available for Gemini 3 models. Available natively in the Interactions API and opt-in via generate_content. Learn More below 🔽

Google Colab now has an open-source MCP server that lets you use Colab runtimes with GPUs from any local AI agent. 🔧 Tools to execute_code, connect, notebook editing ☁️ Run Python on cloud GPUs directly from agents 📝 Can create .ipynb files and add code/markdown 🔌 Works with Gemini CLI, Antigravity or any MCP-compatible client

@ammaar @GoogleDeepMind Congrats! Glad you're with us.

Today marks 1 year @GoogleDeepMind 🎉 We redesigned AI Studio, helped millions of developers go from idea to app with Gemini, and got to cover launches live that I would’ve been watching from my couch a year before. None of it happens without this team. Back to pushing.

Build AI agents that think, plan, and act using Gemini + Vercel’s agent stack. Pure ideation → high-level agent.

Wrote a developer guide for Nano Banana 2 with the Gemini Interactions API. The guide walks you through 4 use cases. 📝 Text → Image: Generate a photorealistic Kyoto travel poster. 🔍 + Web Search: Ground images with real landmark facts. 🆕 + Image Search: Retrieve real photos for visual accuracy. 🧑 + Reference Photo: Composite a real person into scenes.

@OfficialLoganK Great work by the Team!

Spend caps in the Gemini API, available starting today!! This is another step forward of many to give developers more control and peace of mind when building with Gemini. Please go set a cap and send us any feedback as you use them!

Set a spend cap: aistudio.google.com/spend

Big QoL! Spend caps are rolling out for the Gemini API!! Please go set a cap and send us any feedback as you use them! - Spend caps can have up to a 10 minute delay before taking effect - We are working to bring this latency down over time - We are shortly rolling out email notifications when you hit caps - Spend caps are experimental so pls send us feedback on things you want here

Nano Banana Pro vs Nano Banana 2 blog: fofr.ai/nano-banana-2-…

Docs: ai.google.dev/gemini-api/doc… Blog: blog.google/innovation-and…

What if one embedding model could understand text, images, video, audio, and PDFs all at once? Excited to share Gemini Embedding 2 our first fully multimodal embedding model. 🖼️ 5 modalities in a single unified embedding space 🌍 Supports up to 8,192 input tokens, 100+ languages 🎧 Embeds audio natively, no transcription step needed 📐 Flexible output dimensions: 3,072 / 1,536 / 768 via MRL 📎 Up to 6 images, 120s video, and 6-page PDFs per request Now in Public Preview via Gemini API & Vertex AI.

What if you could optimize a model overnight without any ML experience? What if an AI agent runs hundreds of training experiments autonomously, keeping only the improvements? That is the idea behind autoresearch. Yes, the early results are small scale, GPT-2 speedups, a 0.8B model beating a 1.6B. But the unlock is real: You have a domain task (search ranking, fraud scoring, clinical NER). You have labeled data and an eval metric. You hand it to an agent loop. You go home. By morning you have a small, fine-tuned model that's measurably better. All will depend on "how good is our eval."

👀

@iwebst Congrats!

Promptfoo will be joining OpenAI. We’re staying open source and we’re going to keep supporting customers and users. We built Promptfoo to help devs test and secure AI apps. The results have been phenomenal: 350k+ developers, 25%+ of the Fortune 500, 23 people, ~2 years. AI agents are eating the world, and joining OpenAI will supercharge our technology as we connect it deeply into the model and inference layers. We will be able to find & fix AI security issues in a way that no one else has done before. Grateful to our team, to a16z and Insight Partners, and to the community who helped turn this into something huge. You built this with us. Much more to come ❤️