Mete Atamel

At the heart of Google Antigravity is its ability to effortlessly gather your feedback at every stage of the experience. In this blog post, I will show you all the different ways you can provide feedback to Antigravity.

As the agent works on a task, it creates different artifacts along the way:

• An implementation plan and a task list (before coding)
• Code diffs (as it generates code)
• A walkthrough to verify the results (after coding)

These artifacts are a way for Antigravity to communicate its plans and progress. More importantly, they’re also a way for you to provide feedback to the agent in Google docs style comments. This is very useful to effectively steer the agent in the direction you want.

Google Antigravity is an agentic development platform where you have your familiar code editor along with a powerful agent on the side. In today’s post, I want to show you some tips and tricks for the code editor.

Setup and Extensions

In a typical setup, you’d have the editor, the terminal, and the agent visible:

If this is not the case, you can toggle terminal and agent panels as follows:

Google Antigravity was announced last week as the next generation agentic IDE. I’m very impressed with it so far. It already helped me to upgrade my blog to the latest Hugo (that I’ve been putting off for a long time). It even recognized that some of the shortcodes (eg. Twitter) from the old version changed in the new version and automatically updated my blog posts with the new version of the shortcodes. Nice!

The Gemini team at Google recently announced the File Search Tool, a fully managed RAG system built directly into the Gemini API as a simple, integrated, and scalable way to ground Gemini. I gave it a try and I’m impressed how easy it is to use to ground Gemini with your own data.

In this blog post, I’ll introduce the File Search Tool and show you a concrete example.

I’ve been exploring the Agent Developer Kit (ADK) and its powerful callbacks feature. In this blog post, I want to outline what callbacks are and provide a sample agent with all the callbacks implemented for a quick reference and testing.

At its core, an agent framework like ADK gives you a sequence of steps:

receive input → invoke model → invoke tools → return output

In real-world systems, we often need to hook into these steps for logging, guarding, caching, altering prompts or results, or dynamically changing behaviour based on session state. That’s exactly where callbacks come in. Think of callbacks as “checkpoints” in the agent’s lifecycle. The ADK framework automatically calls your functions at these key stages, giving you a chance to intervene.

A few days ago, I saw Logan Kilpatrick’s Tweet about the new AI-first vibe coding experience in AI Studio:

Last time I tried AI Studio for vibe coding, it was mostly a single-page web application with all the code in a single file (which wasn’t ideal).

Last year, we announced the Google Gen AI SDK as the new unified library for Gemini on Google AI (via the Gemini Developer API) and Vertex AI (via the Vertex AI API). At the time, it was only a Python SDK. Since then, the team has been busy adding support for Go, Node.js, and Java but my favorite language, C#, was missing until now.

Today, I’m happy to announce that we now have a Google Gen AI .NET SDK! This SDK enables C#/.NET developers use Gemini from Google AI or Vertex AI with a single unified library.

Earlier this month, the Gemini 2.5 Computer Use model was announced. This model is specialized in interacting with graphical user interfaces (UI). This is useful in scenarios where a structured API does not exist for the model to interact with (via function calling). Instead, you can use the Computer Use model to directly interact with user interfaces such as filling and submitting forms.

It’s important to note that the model does not interact with the UI directly. As input, the model receives the user request, a screenshot of the environment, and a history of recent actions. As output, it generates a function call representing a UI action such as clicking or typing (see the full list of supported UI actions). It’s the client-side code’s responsibility to execute the received action and the process continues in a loop:

It’s crucial to secure inputs and outputs to and from your Large Language Model (LLM). Failure to do so can result in prompt injections, jailbreaking, sensitive information exposure, and more (as detailed in OWASP Top 10 for Large Language Model Applications).

I previously talked about LLM Guard and Vertex AI and showed how to use LLM Guard to secure LLMs. Google Cloud has its own service to secure LLMs: Model Armor. In this post, we’ll explore Model Armor and see how it can help to safeguard your LLM applications.

This is the sixth and final post in my Vertex AI Gen AI Evaluation Service blog post series. In the previous posts, we covered computation-based, model-based, tool-use, and agent metrics. These metrics measure different aspects of an LLM response in different ways but one thing they all had in common: they are all for text-based outputs.

LLMs nowadays also produce multimodal (images, videos) outputs. How do you evaluate multimodal outputs? That’s the topic of this blog post.