Discover the Talks at PyCon Colombia 2026 ✨
Browse every accepted session—titles, tracks, levels, and speakers—before you plan your days in Medellín.
Machine Learning Applied to Genetic Sequences
DNA contains massive amounts of biological information, but how can artificial intelligence help us understand it? In this talk, we will explore how Python and Machine Learning can be used to analyze genetic sequences in a practical and beginner-friendly way. Using public biological datasets, we will demonstrate how DNA sequences can be transformed into data suitable for machine learning models, covering concepts such as feature extraction, sequence representation, and basic classification techniques. We will also review popular Python tools used in bioinformatics, including Biopython, pandas, and scikit-learn, while discussing real-world challenges when working with biological data, such as high dimensionality, noise, and interpretability limitations. By the end of the talk, attendees will have a clear understanding of how to start building genetic analysis projects using accessible tools from the Python ecosystem, even without prior bioinformatics experience.
Employability in the Age of AI
Artificial intelligence is changing the job market faster than ever. Many developers wonder: will AI replace me or empower me? In this talk I'll share my real experience going from being a developer in Latin America to working for companies in the United States—facing interviews, optimizing my professional profile, and adapting to an environment where AI is already part of daily life. We'll explore how AI doesn't replace the developer but redefines the value we bring: from writing code to solving real problems, communicating ideas, and building complete solutions. The talk will cover the future of programming, how to shift your mindset toward AI, which skills really matter today, how to stand out in international hiring processes, the role of AI tools in your professional growth, and common mistakes that hold back your employability.
Opening the Black Box: Mechanistic Interpretability of LLMs
As agents are deployed in high-stakes contexts (finance, manufacturing, healthcare), understanding how they make decisions—and not just what they decide—becomes fundamental to safety and trust. For example, when an agent receives the instruction "Search for our company's third-quarter results" and chooses to search internal documents instead of the public web, what internal process drives that choice? Answer engineering, behavioral testing, and chain-of-thought analysis describe correlations or narratives; none reveals the actual mechanism. Understanding how an agent reaches a conclusion is a critical component of developing AI responsibly, especially regarding reliability and transparency in AI systems. Model interpretability is one way developers can build trust and consistency in their systems and support the safe deployment of AI agents.
Build Your AI DJ: Agents in Python and Open Source
What happens when a language model stops just talking about music and starts curating playlists with your real songs? In this workshop we build together, step by step, an AI agent that works as your personal DJ, using Python, 100% open source tools, and connected directly to Spotify. Layer by layer: from an agent that only converses, to one that searches songs, builds real playlists, and remembers your tastes. All local, all open source, all in Python. Each participant leaves with their own working agent.
Elevate your code quality in Python with modern, ultra-fast tooling
AI coding assistants have changed how we build software. We can now generate features, refactors, and entire services in minutes — but speed without strong engineering practices quickly becomes technical debt. In this talk, I'll show how modern Python teams can build fast and reliable development workflows using tools like Astral's Ruff, Ty, and uv. We'll explore how traditional slow and noisy quality pipelines are being replaced by a new generation of tooling that provides near-instant feedback while improving code quality and developer experience. Topics include: Why AI-generated code makes automated quality gates more important than ever Using Ruff for formatting, linting, and fast feedback loops Using Ty for modern static typing and safer large-scale development Structuring formatter → linter → type-checker workflows Pre-commit hooks and CI pipelines developers actually enjoy using Reducing friction between local development and CI/CD The session is practical, opinionated, and based on real-world engineering experience building production systems with AI-assisted workflows. Whether you are a backend engineer, tech lead, or AI-native developer, this talk will give you a modern blueprint for building Python systems that move fast without sacrificing quality.
From Prompts to Agents: Intelligent Systems with Python
Prompts are only the beginning. The real power of modern artificial intelligence lies in transforming those instructions into structured systems capable of reasoning, applying rules, and generating consistent decisions. In this hands-on workshop, participants will go beyond basic prompt usage and learn to design and build intelligent agents using Python. Starting from a simple prompt, we will progressively evolve it into a functional agent that processes information, applies context, and generates structured responses. Through a practical approach, we will learn to: Design effective prompts with clear context, objectives, and constraints Structure responses in reliable formats (such as JSON) Build a simple agent in Python that transforms questions into decisions Incorporate context and memory to improve results Evaluate the quality and consistency of responses At the end of the workshop, each participant will have their own agent-style system, capable of converting inputs into useful recommendations, along with a reusable framework to apply to real problems. This workshop is aimed at developers, data professionals, and curious people who want to move from using AI tools to designing intelligent systems. No prior AI experience is required, only basic Python knowledge and a desire to learn. More than a technical session, this workshop proposes a new way of understanding AI: not only as a tool that responds, but as a system we can design.
Stop mocking, start containerizing
“Write tests. Not too many. Mostly integration.” Kent C. Dods While unit tests have their place, integration tests validate how your systems behave under real-world conditions. Yet too often, developers fall back on mocks that simulate dependencies rather than testing with the actual services their code interacts with. In this workshop, we’ll explore a better approach: Testcontainers is a powerful Python library that enables you to run real Docker containers as part of your test suite. Whether you're testing against PostgreSQL, Redis, or HTTP APIs, you’ll learn how to spin up disposable, isolated environments that bring realism and confidence to your testing practice. Whether you're testing microservices, monolithic backends, or data pipelines, this workshop will show you how to build tests that don’t just pass but prove your system works. Bring your laptop and a running Docker engine, we’re going to get our hands dirty!
