Guillaume Laforge

🥑 Developer Advocate @GoogleCloud
🧠 Focusing on GenAI 🤖
⭐️ @ApacheGroovy co-founder
🏆 @java_champions
📣 @lescastcodeurs podcast
🦋 @glaforge.dev

[Guillaume Laforge @glaforge]

Before heading on vacation, I built an unofficial @Java SDK for #Google @antigravity 🚀

If you want to embed AI agents directly into enterprise Java applications, #GitHub Actions, or custom #CLI tools, here is how it works and what you can do with it 🧵 👇

[Guillaume Laforge @glaforge]

@danicat83 LOL, I remembered the fur color, so I knew where to search!

[Daniela Petruzalek @danicat83]

I’m happy that we have an official Gemini API CLI (not to be confused with the old Gemini CLI which has been superseded by Antigravity).

Thanks to this new CLI I can get rid of all the ad hoc scripts I was using to call nano banana, lyria and others in my skills.

The updated versions of my media generation skills are live on https://t.co/MuBTFaAFaN

[Richard Seroter @rseroter]

"@googlecloud should offer micro-VMs."

Ok.

Agent Compute Engine is a new service that gives agents their own hardware-isolated micro-VM. We're using it ourselves to power key services.

Coming soon ... https://t.co/Evf2TsPW21

[Alicia Williams @aliciaoncloud9]

You don't just have to use Gemini models in BigQuery SQL! 💡

With a few lines of SQL, you can prompt open models like Gemma, Llama, gpt-oss, and Hugging Face models across massive tables with zero data movement.

Read the walkthrough ➡️ https://t.co/4S2qWpksWl

[Rustam Mehmandarov @rmehmandarov]

A friendly reminder that #Java #HelloWorld looks like this since Java 24:

void main() {
println("Hello World");
}

No, it is not "public static void main..." anymore. 🫶

[Guillaume Laforge @glaforge]

@BriceDutheil @HardCoding What about just touching $JAVA_HOME/lib/security/blocked.certs?
https://t.co/zGXssY9KBu

[Google Cloud @googlecloud]

Today, we're bringing OpenAI models to Google Cloud's model garden.

We're now the only hyperscale cloud provider offering access to all three leading closed source LLMs—alongside 200+ other models—on a unified enterprise platform → https://t.co/OWExjjWBB7

[Guillaume Laforge @glaforge]

@Anh32920995 @myfear Made a less cheesy one, without the markers 😀

[Guillaume Laforge @glaforge]

@Anh32920995 @myfear Well, yeah, I could make AI tweak it to remove the useless markers and pencils 😅

[Guillaume Laforge @glaforge]

Fellow #java developers you are likely affected by the #eMudhras CA compromise.

Let's fix your @java and @graalvm installations and apps:
https://t.co/zGXssY9KBu

[genevieveh@ @genevieve__h]

This is my new favorite thing I've built with Argon: an iced coffee simulator, *completely* from scratch. No physics engine, fluid libraries or pre-baked animations, only three.js, WebGL2 math and custom 3D models - all running in Chrome 🤯

Approach, prompt & thoughts below! 🧵

[Laurent Picard @PicardParis]

🤿 I did my first deep-dive at a conference.
🎙️ Speaking for 3 hours is a challenging exercise, especially when doing almost everything live.
🙏 Thanks @Devoxx for the amazing organization.
🧵

[Philipp Schmid @_philschmid]

The easiest way to try Gemini 4 Argon in an agentic environment is Gemini Managed Agents. A single API call gets you

- Python, Node.js, Git, and Bash.
- Full network access and control.
- Dedicate Credentials API.
- Filesystem to persist work.
- Background Support.

https://t.co/V8U7xxDgkW

[Jack Wotherspoon @JackWoth98]

Not enough people know about Managed Agents 😀

In a single API call you get the Antigravity harness running in a cloud sandbox where it can write code, search the web, connect to MCP servers etc.

Build them into your products or teach an agent to do your repetitive daily tasks.

[Shubham Saboo @Saboo_Shubham_]

Google's Ambient quality agent runs 24/7 in LOOP to monitor and fix AI agents in production.

It reads live traces.
Catches silent failures.
Points to the exact line of code to fix.

And it's 100% open-source.

GitHub: https://t.co/Z4VBPTa8PM

[Daniela Petruzalek @danicat83]

Last week I deleted a custom SQLite RAG pipeline and replaced it with three Markdown files.

In the first Python version of AIDA (my OS diagnostic agent), I used a local SQLite RAG database to look up osquery table schemas. The data was small and static, so each chunk held a full table, but the setup was cumbersome and Gemini 2.5 Flash often made suboptimal RAG queries, pulling the wrong tables or missing related ones completely.

When I rebuilt AIDA in Go with Genkit, I replaced the RAG stack with Agent Skills middleware (`darwin`, `linux`, `windows`). Now the agent loads the OS schema catalog on demand without relying on vector search queries.

I also timed single-agent vs. multi-agent delegation on the exact same prompt ("what is my battery status?") with Gemini 3.8 Flash:

• Single-agent: 9.56s (3 LLM calls)
• Multi-agent (Coordinator + Inspector + Researcher): 17.02s (5 LLM calls)

Per-call latency stayed flat (~3.3s). The extra 7.5s is pure coordination overhead.

Full write-up and code:
https://t.co/bq7tJ9Xfqb

[Jack Wotherspoon @JackWoth98]

Gemini 4 Argon Developer Guide 🧑‍💻

Here are a few tips when using Argon:

🎯 - Align on goals & intent upfront
🧪 - Give it a way to verify & test its work
🤖 - Have Argon delegate to Flash subagents
🔄 - Update rules & skills

Read the full guide 👇
https://t.co/UJmmqBwVi5

[Mete Atamel @meteatamel]

How do MCP, ADK, and A2A fit together in practice? 🤔
Join me this Wednesday (Oct 21, 12pm BST / 1pm CEST) for a hands-on Google Cloud Build Hour workshop:

🔧 MCP server on Cloud Run
🤖 Agent logic with ADK
🤝 Interop via A2A

Free RSVP 👇 https://t.co/5b8mwnnipA

[Clement Farabet @clmt]

Creating and seamlessly deploying full-stack web apps in Google AI Studio has taken a massive leap forward—now powered end-to-end by Gemini 4 Argon (gemini-4-argon) and the Antigravity agent harness.

You can go from a single prompt, rough sketch, or repo import to a live production web app on Cloud Run in minutes. Here’s what changed under the hood

🧵 (1/6)

[Shengzhe @shengzheyao]

A few workflow tips if you're using Gemini 4 Argon in Antigravity CLI:

1. Right-size reasoning effort (/effort)
Argon thinks deeply—which is great for architecture & gnarly bugs, but overkill for mechanical edits. Keep it on medium by default, bump to high when planning/debugging, and drop to low for quick refactors.

2. One-shot model consults (/model <name> <prompt>)
You don't need to stay on your heaviest model all session. Run a single prompt on Argon to diagnose a tricky bug or review a design, then automatically drop back to your faster default model.

3. Delegate to subagents & follow up with @<subagent>
Offload repo exploration or test writing to subagents (coder / tester / reviewer) so your main Argon thread stays focused—type @<subagent> to message a subagent directly, or press Ctrl+K when a subagent surfaces a question (new in v1.3.6).

4. Side questions without polluting context (/btw)
Need a quick syntax check mid-task? /btw answers in a side overlay without adding a single token to your main trajectory.

5. Inspect changes in-terminal (/diff)
v1.3.5–1.3.6 adds a file tree, change stats, commit-message copy, and a highlighted commit tree view right in /diff.