How to use LLM context to upgrade your project

 Posted on January 25, 2026  |  Diego J. Romero-López

How to use LLM context to upgrade your project In this post we pick up a Python 2.0 project and show how to use a LLM to upgrade a software project. This time we will be using contexts. Introduction I will upgrade the Djanban project as it should be done. Not only making it work with the latest versions of the software packages, but improving its quality and making sure there are guardrails that make impossible for the developers [Read More]
llm  ai  guide  showcase 

How to minimize tech debt from the start

 Posted on January 24, 2026  |  Diego J. Romero-López

How to minimize tech debt from the start In this post we are going to lay some guidelines about how to prevent your project of accumulating tech debt. Introduction Tech debt has been a constant in all my work. All projects I have started working with had an amount of tech debt. Why does this happen? And better yet, what can we do to avoid falling on this tech debt trap? [Read More]
software  tech-debt 

How to use a LLM to upgrade your project

 Posted on January 12, 2026  |  Diego J. Romero-López

How to use a LLM to upgrade your project In this post we pick up a Python 2.0 project and show how to use a LLM to upgrade a software project. Introduction I will upgrade the Djanban project as it should be done. Not only making it work with the latest versions of the software packages, but improving its quality and making sure there are guardrails that make impossible for the developers [Read More]
llm  ai  guide  showcase 

How NOT to use a LLM to upgrade your project

 Posted on January 11, 2026  |  Diego J. Romero-López

How NOT to use a LLM to upgrade your project In this post we pick up a Python 2 project and show how NOT to use a LLM to upgrade an outdated software project. This is a two-series go to the next post if you are only interested in how to do it correctly. Introduction We tend to only focus on positive outcomes, following active (positive) advice, etc. But what about negative one? [Read More]
llm  ai  guide  showcase 

When are full software rewrites needed?

 Posted on January 3, 2026  |  Diego J. Romero-López

When are full software rewrites needed? Having dealt with a full rewrite of a software application recently, it left me wondering if it was needed at all, if there was any way to salvage the project or some parts of the project. Could we have avoided the rewrite? Introduction I have encountered the necessity of rewriting full software projects several times in my career but in my last years I have had to do it twice. [Read More]
software  practices  tech-debt  war-story 

Using LLMs to create a python library

 Posted on December 5, 2025  |  Diego J. Romero-López

Using LLMs to create a python library I have used Gemini and Claude LLM models to create a mypy plugin to mark a function as pure: mypy-pure. Introduction I think that static analysis in Python is a great opportunity to catch a lot of issues before running the program. I do not even remember when, but I saw a thread in the Python official forum where a user was suggesting this @pure decorator idea to the Steering Council of Python. [Read More]
llm  ai  war-story 

Use LLMs to handle tedious tasks

 Posted on November 24, 2025  |  Diego J. Romero-López

Use LLMs to handle tedious tasks There are some times where there are tedious tasks that need to be done in our software projects. We know how to do it but usually delay them because they are boring, not challenging and painfully long. The LLMs (Large Language Models) promise faster and better software development. Could we use a LLM to do them? Could we leverage the LLMs to free them from these chores? [Read More]
llm  ai  war-story 

Use Static Single-Assignment when possible

 Posted on November 3, 2025  |  Diego J. Romero-López

Use Static Single-Assignment when possible This post discuss a way of coding assignments in code where all variables are treated as constants. Introduction There are simple ways to improve our source code that are simple but effective. Static Single-Assignment (SSA) is one of them. By changing the way variable assignments are done, we can achieve some benefits in maintainability that cannot be overlooked. What is Static Single-Assignment? Just treating the variables as constants, i. [Read More]
programming  quality 

Otelize, add OpenTelemetry to your Python project easily

 Posted on September 15, 2025  |  Diego J. Romero-López

Otelize, add OpenTelemetry to your Python project easily OpenTelemetry (sometimes abbreviated as OTEL) is a standard for telemetry and monitorization of software applications that has gain a lot of traction in these last years. We will learn here how to use the Python package otelize to add this telemetry to our Python applications without having to rely on much boilerplate. How did I use to add OTEL telemetry to my Python code? [Read More]
python  package  software  monitorization  telemetry 

How to work in a toxic environment

 Posted on September 14, 2025  |  Diego J. Romero-López

How to work in a toxic environment There are many posts about growing a good culture of empathy in teams. But how could you deal with a toxic culture? In this post we are going to delve into this question. Toxic behaviors What is a toxic environment? A toxic environment is one where the bad behaviors are not corrected or they are ignored. As simple as that. There are people doing things that affect negatively to others, and nobody is correcting them. [Read More]
teams  culture