Intro

A few weeks ago I ran a very simple test: I took TinyDB, opened a coding assistant, and asked it the most obvious thing in the world: convert this to Rust.

At first glance, the result did not even look that bad. The code looked plausible, it compiled, it passed a few tests, and it gave off that dangerous feeling of “I think we’re basically there.” But as soon as I started looking closely, the real problems surfaced: a deadlock in insert_multiple, silent integer-to-float corruption in update operations, a panic path on invalid regex, and roughly 40% of the original package features simply gone.

Intro

A few months ago I had to work on a complex application on AWS: a React frontend on Amplify, several Lambda functions, Bedrock with AgentCore, Knowledge Bases, and Prompt Management. I was in a hurry, and the temptation was overwhelming: open Claude Code, throw in a generic prompt, and hope it would “figure it out.” Instead, I did something different — I wrote specifications, reviewed them, spent an entire day on it — and that day it felt like I hadn’t accomplished anything. Two days later I had a working application. If I had improvised, I’d probably still be debugging.

Langchain 1.0

On October 22, 2025, LangChain finally reached version 1.0. After three years, this milestone represents something significantly different both from previous versions of the framework and from other competitors, which have become quite numerous in the meantime, creating some confusion and bewilderment for those who find themselves defining the software architecture for a new project.

To understand how volatile this market is, it’s worth noting that the framework developed by Microsoft called “AutoGen”, with 51k+ GitHub stars, recently entered maintenance mode, as Microsoft decided to focus its efforts on the Microsoft Agent Framework, which is obviously much more integrated with Microsoft’s GenAI services.

1. Introduction

1.1. Intro to the intro

I’m not quite sure what this article is—a mix of coding experiment, science communication, and maybe just a fun project for someone who in another life would have wanted to be a physicist.

I’ve had this in my drawer for a while, since I read this article by some CERN researchers that explains how you can simulate an experiment on Bell’s inequalities using the Qibo framework.

1. Introduction

The quantity of frameworks emerging for GenAI application development is incredible and, in my opinion, is becoming excessive. Every time a new framework appears, it seems to do more or less the same things as the previous one. Perhaps some have better modularization capabilities or more robust design against long-term obsolescence, but they all seem pretty much the same to me and, although I enjoy experimenting, the study of new miraculous and promising GenAI frameworks is becoming less and less appealing.

Introduction

During these scorching August days, I took the opportunity to thoroughly read Google’s A2A protocol specification and try to understand how to use its concepts to design an enterprise Agent architecture, possibly free from technological or platform constraints.

What is A2A?

The Agent2Agent (A2A) Protocol is an open standard designed and publicly shared by Google to facilitate communication and collaboration among AI agents. The standardization of AI interoperability model is a topic that has been discussed since the very first moments when we started talking about Agents, and there are several reasons for this: