Blogs on

"Hello world" version of an AI-data-analyst

Gonçalo Leiria — Mon, 10 Aug 2026 18:36:58 +0100

I am developing an LLM-powered data analyst for a fictional SaaS company. The idea is that a user can ask questions about the business in natural language, and the agent can use the database to answer them if needed. I am using Pydantic-AI to connect the agent to Google’s Gemini models and Django to handle the application and data layer.

The SaaS Company

I created a fictional SaaS company and generated synthetic data for it. The goal is not to create a perfect simulation of a real business but to create a small coherent world that I can use to explore the AI-agent architecture and that the agent can reason about. As the project evolves, I will gradually add more data and relationships. This is literally just me putting the pieces together.

Django + Data Pipeline Deployment

Gonçalo Leiria — Wed, 22 Jul 2026 14:39:50 +0100

Goal of the project

In my previous article I described how I built and deployed a Dockerised data pipeline to Microsoft Azure. Every day, Azure Data Factory orchestrates the execution of a container that collects weather data from the OpenWeather API and stores it as a Parquet file in Azure Blob Storage.

The next step was to build a lightweight Django application that reads the latest dataset directly from Blob Storage and presents it through an interactive Plotly dashboard.

Blob Storage vs Azure Data Lake Storage Gen2

Gonçalo Leiria — Mon, 20 Jul 2026 07:03:06 +0100

Recently, while deploying a data engineering project to Azure, I found myself asking a question: when should I use Blob Storage and when should I use Azure Data Lake Storage Gen2 (ADLS Gen2)? Here I share how things clicked for me.

Blob Storage

Blob stands for Binary Large Object. A blob is simply a sequence of bytes. From the perspective of Azure Blob Storage, a JPEG image, a PDF, an MP4 video, a Parquet dataset, a CSV, or JSON file are all treated exactly the same: they are just blobs. Blob Storage is therefore Microsoft’s object storage service. It provides a highly scalable and inexpensive way of storing files in the cloud without caring about their internal structure.

A Simple Azure Deployment

Gonçalo Leiria — Thu, 16 Jul 2026 14:30:53 +0100

This project started as a take-home assignment for a data engineering role. After, as part of my learning journey into cloud computing, and after completing Azure AZ-900 and DP-900 certifications, I wanted to get hands-on practice so I deployed the pipeline to Microsoft Azure. Here, I share the main steps I took to make that happen.

A hypothetical team of data scientists asks me, as part of the data engineering team, to a build Dockerised data pipeline in Python to collect daily meteorological data from the publicly available OpenWeather API (https://openweathermap.org/). The GitHub repository for the project can be found here. There you can find a detailed README describing the project’s architecture, design decisions, implementation, and instructions on how to run it locally. This post focuses exclusively on the deployment to Microsoft Azure.

Microsimulations - Digital Twins

Gonçalo Leiria — Sat, 01 Nov 2025 11:43:42 +0000

The idea of using computers to simulate real-world systems has been around for many decades. However, in recent years, with the democratisation and significant cost reductions of computational power, increased data availability, and advancements in artificial inteligence, computational simulations have reached new levels of sophistication and their applications, particularly in the healthcare care domain, are expanding very rapidly. This blog post provides a very brief overview on microsimulations and how integrating machine learning and multi-objective optimisation into these systems can help us to tackle a concrete healthcare challenge: optimising type 1 diabetes screening strategies while minimizing costs associated.