Paul Couvert

Home
Paul Couvert

🐦 200k+ Readers on 𝕏
🤖 Technology & AI Educator
⚒️ Build better and Faster w/ AI and No-Code

10/04/2025

Wow Google has just released Firebase Studio

You can build any app in natural language, modify it and deploy it all in one place 🔥

Basically a free alternative to Cursor, Bolt or v0, directly in the browser.

1️⃣ Access Firebase Studio

With a free Google account, go to the official Firebase Studio page:
firebase.studio

2️⃣ Type your prompt

Simply describe the app you want to create.
It may even involve the use of AI. E.g:

Transform a topic into a complete mindmap.

3️⃣ Modify or validate the plan

Firebase Studio will propose a plan.
You can ask it to modify or approve it!

4️⃣ Enjoy!

You're already done!

The app builds itself automatically, and once it's finished, you can request any changes you like.

5️⃣ Publish

You can also publish your app to share it.

Once it's finished, just click on the "Publish" button and follow the simple steps.

💡 You can also easily view and modify the code!

Just click on the icon next to the "Publish" button
And Gemini is also integrated into the editor... for free!

27/03/2025

OK it's a game changer

You can run an AI agent locally on your laptop:

No need to connect or pay a provider like OpenAI or Anthropic.

Combine the open source Google Gemma 3 model, Smolagents and LM Studio and you're ready:

Here are the steps:

1️⃣ Host a Local LLM

Download and install LM Studio to host an AI model locally.
Download a suitable LLM (like Gemma 3 12B).

2️⃣ Set up development environment

Install Python and Visual Studio Code.

3️⃣ Use Smolagent library

Utilize the Smolagent Python library for building AI agents easily.

4️⃣ Generate Agent Code with Local LLM

Use the hosted LLM in LM Studio to generate the Python code for your desired AI agent.

Provide a detailed prompt with instructions, an example, and relevant documentation (like Lite-LLM).

5️⃣ Configure Connection to Local LLM

In the generated Python code, configure it to connect to the locally running LLM in LM Studio by specifying the API base URL (found in LM Studio's developer tab) and the correct model ID.

6️⃣ Run the AI Agent

Execute the Python script in VS Code.

The agent will then interact with the local LLM in LM Studio to perform the defined tasks.

Thanks to Qualcomm for helping me on this video!

Address

Website

http://paulcouvert.com/

Alerts

Be the first to know and let us send you an email when Paul Couvert posts news and promotions. Your email address will not be used for any other purpose, and you can unsubscribe at any time.

Shortcuts