Philipp Schmid

Agents & Gemini API, MTS @GoogleDeepMind | prev: Tech Lead at @huggingface, AWS ML Hero 🤗 Sharing my own views and AI News 🧑🏻‍💻

[Philipp Schmid @_philschmid]

The Interactions API is now generally available. 🎉 The Interactions API is the simplest way to build with Gemini for humans and agents.

- One API for Gemini models and agents.
- Antigravity Agent with a isolated remote Linux sandbox.
- Image gen with Nano Banana; music with Lyria 3, soon video with Omni.
- `background=True` for async, long-running interactions.
- Multimodal Tool Use & Combination.
- Dedicated skills for coding agent.

Building something new inside Google isn't easy, but it's possible. We spent almost a year on this because we think developers and agents deserve an API that is intuitive, familiar and easy to learn and use and evolves with improving capabilities and new behaviors.

Give it a try. Feature requests, bugs, complaints all to me. 👇🏻

[Philipp Schmid @_philschmid]

@vercel_dev @GoogleAI Nice!

[Philipp Schmid @_philschmid]

@Google @GoogleAIStudio Lets go!

[Philipp Schmid @_philschmid]

@ModelsOnOR @GoogleAIStudio Lets go!

[Philipp Schmid @_philschmid]

@OfficialLoganK @GoogleAIStudio Lets go! Big Kudos to the team! Gemini Decision started organically inside Google DeepMind. We built a prototype and opened it up for internal testing, and teams across Google picked it up fast. 6 weeks later we're shipping a new model and a new API together.

[Philipp Schmid @_philschmid]

@sundarpichai @GoogleAIStudio Super excited! 🚀

[Philipp Schmid @_philschmid]

Gemini Decision started organically inside Google DeepMind. We built a prototype and opened it up for internal testing, and teams across Google picked it up fast. 6 weeks later we're shipping a new model and a new API together. All done by a small team of research, engineering, and product. I helped design, build, and evaluate the API and Gemini Decision 1. Big kudos to the team! 🚀

Give it a try and let us know what you think.

Docs: https://t.co/fElhhaY76x
Blog: https://t.co/wWxq2cbMue
Playground: https://t.co/ub12585i17

[Philipp Schmid @_philschmid]

Excited to announce the Gemini Decisions API, a new API for yes/no, multiple choice, and rubric questions, powered by our new Gemini Decision 1 model.

🖼️ Text, images, audio, video, PDFs input support
❓ Up to 1,000 questions per request, 256k context
⚡ 150-250 ms end-to-end
💰 $0.10 per 1M input tokens, $0 output
📊 Confidence score on every answer

https://t.co/wWxq2cbMue

[Philipp Schmid @_philschmid]

👀

[Logan Kilpatrick @OfficialLoganK]

Gemini

[Philipp Schmid @_philschmid]

@ArtificialAnlys @GoogleDeepMind Exciting!

[Philipp Schmid @_philschmid]

Evaluations are the backbone of any frontier progress. Today we're launching MKA (Multimodal Knowledge Agent) with @ArtificialAnlys, a benchmark for agents doing knowledge work on visually complex files.

- 200 tasks across 10 verticals and 83 occupations, written by domain experts
- Each task takes a seasoned professional 3 to 8 hours
- ~70 yes/no rubric checks per task, weighted 75% factual accuracy and 25% visual design
- Every model runs in the same harness (Stirrup) with the same tools, sandbox and turn budget
- 200 tasks stay private with Artificial Analysis, so they can't leak into training data
- 10 public tasks on @huggingface 🤗

Gemini 4 Carbon is #2 on quality, 3 points behind Claude Fable 5.2, at $6.29 per task vs $31.97.

Blog: https://t.co/n6WZLdmc8D
Results: https://t.co/sib7sPjoO6

[Philipp Schmid @_philschmid]

@Flandermaxx Security and review tasks mostly

[Philipp Schmid @_philschmid]

We wrote a practical Developer Guide for Gemini 4 Carbon covering API changes, long decode up to 1M tokens, and multi-agent patterns: https://t.co/VkUdKe4iPi

Upgrading from Argon means just changing the id to gemini-4-carbon. I use medium thinking_level for almost everything. For bigger multi-file tasks, the new /swarm preview in @Antigravity creates a multi-agent team that can communicate via a message board. You can put Carbon on architecture and code review while 3.8 Flash works on parallel edits.

[Philipp Schmid @_philschmid]

@Fanfulladev @ericzakariasson do you know?

[Philipp Schmid @_philschmid]

Gemini 4 Carbon is #1 on CursorBench and available in Cursor. Give it a try!

[Cursor @cursor_ai]

Gemini 4 Carbon is now available in Cursor!

At high effort, it's the top model on CursorBench at 60.4%

[Philipp Schmid @_philschmid]

@cursor_ai 🚀

[Philipp Schmid @_philschmid]

@rafaelobitten @GoogleAIStudio @antigravity @_mohansolo

[Philipp Schmid @_philschmid]

Gemini 4 Carbon is now available in the Gemini API, @GoogleAIStudio, and @Antigravity (Google AI Ultra subscribers). At Google, teams have already improved open-source vulnerability recall by 25%+ over Argon and found 40x more remote protein homologs for AlphaFold 3.

I've been using it for past weeks for all my tasks (default is medium effort for me). My tasks already got 10x more ambitious, but it still feels that i need to at least 100x more ambitious.

Here is an example of that using /swarm in @Antigravity: turning 7 public planning PDFs (206 engineering drawings) into an interactive 3D reconstruction of our London Platform 37 office overnight from a single prompt.

[Philipp Schmid @_philschmid]

@REVOLVO_OCELOTS @GoogleAIStudio @antigravity All carbon for this case but you can define and it can be both

[Philipp Schmid @_philschmid]

Demo by @cobley_ben

[Philipp Schmid @_philschmid]

Learn more: https://t.co/LM2vHndRmT

[Philipp Schmid @_philschmid]

@OfficialLoganK Lets go!