Discover the Talks at PyCon Colombia 2026 ✨
Browse every accepted session—titles, tracks, levels, and speakers—before you plan your days in Medellín.
Future-proof Engineers with AI-DLC
AI is transforming not just what engineers build, but how they learn and grow. In this workshop, you'll discover AI-DLC (AI-Driven Learning Curriculum), a framework for creating personalized, adaptive learning paths for software engineers using AI tools. We'll explore how to design learning curricula that incorporate AI assistance, build skills that complement rather than compete with AI, and create development plans that keep engineers relevant and valuable for years to come.
Carlos Alberto Riveros Varela
Software Engineer @ EPAM Systems
Jesús Alfredo Reyes Vargas
Software Engineer @ EPAM Systems
High-Performance Video Ingestion with Async Python
Video is one of the most demanding data types to process. In this workshop, you'll learn how to build high-performance video ingestion pipelines using Python's async capabilities. We'll cover asyncio fundamentals for I/O-bound video processing, concurrent frame extraction and processing, async queue patterns for data pipelines, performance profiling and optimization, and real-world deployment considerations. Build a production-grade async video ingestion system from scratch.
How to Find Pearls on the Bottom of the Sea – Autoencoders as Anomaly Detection Models
Like finding pearls on the ocean floor, detecting rare anomalies in large datasets requires sophisticated techniques. In this workshop, you'll learn the theory and practice of autoencoder architectures, how to train them for anomaly detection, how to set decision boundaries, and how to evaluate their performance. We'll work with real-world datasets and build complete anomaly detection pipelines in Python.
Executable Skills: How to Teach an Agent How Your Company Works
How do you make an AI agent that truly understands how your company works? In this workshop, you'll learn to design and implement executable skills—reusable, structured pieces of organizational knowledge that agents can invoke. We'll cover skill architecture, knowledge representation in Python, integrating skills with popular agent frameworks, and testing skill reliability. By the end, you'll have a blueprint for building a company brain that your agents can tap into.
Create Your AI DJ: Agents in Python and Open Source
Create your own AI DJ using Python agents and open-source tools! In this beginner-friendly workshop, you'll learn the fundamentals of AI agents, build a music recommendation system powered by Python, and connect it to real music APIs. No prior AI experience required—just curiosity and a love for music. By the end, you'll have a working AI DJ that curates playlists based on mood, genre, and personal preferences.
From ETL to Agentic Workflows: The Evolution of Data Engineering in the Generative AI Era
Traditional ETL pipelines are deterministic and rigid. Agentic workflows powered by generative AI can adapt, reason, and handle the unexpected. In this workshop, you'll learn how to evolve your data engineering practices from classic ETL to intelligent agentic workflows. We'll cover designing agents for data extraction, transformation decisions, and loading strategies—as well as how to combine traditional orchestration tools with AI agents for hybrid architectures.
Building Your First AI Tool Server: Creating a Pokédex with FastMCP and Python
Build your first AI tool server from scratch using FastMCP and Python, with the Pokédex as your guide! In this hands-on workshop, you'll learn the Model Context Protocol (MCP), set up a FastMCP server, implement custom tools that AI agents can call, and connect everything into a working Pokédex AI assistant. No prior MCP experience needed—just Python knowledge and a love for Pokémon.
The Fellowship of Agentic Evaluations: How to Evaluate an Agent?
How do you know if your AI agent is actually doing the right thing? In this workshop, we'll explore practical evaluation frameworks for agentic systems. Forming a fellowship of evaluation techniques—from simple unit tests to complex behavioral evaluations—we'll apply them to real agent scenarios. You'll learn to define evaluation criteria, implement automated test suites, measure agent performance quantitatively, and track improvement over time.
From S3 to AI Agent: Your First Queryable Lakehouse
AI agents are only as good as the data they can query. Most agents built today connect to outdated CSVs, unstructured databases, or nothing at all. What if your agent could query a real lakehouse—with versioning, schema evolution, and time travel—using natural language? In this workshop we build exactly that from scratch using only open-source tools that run on your laptop. Starting from a local Docker Compose stack, we stand up a functional lakehouse with MinIO as S3-compatible storage, Apache Iceberg as the table format, Project Nessie as a Git-like versioned catalog, and Trino as the SQL query engine. On top of that, we build a Python MCP server that exposes Iceberg tables as tools for an AI agent, and connect Claude so it can query the lakehouse in natural language.
hls4ml: From Python Models to Hardware Acceleration
Bridge the gap between Python machine learning and hardware implementation using hls4ml. In this workshop, you'll learn how to take ML models trained in Python (TensorFlow, PyTorch, scikit-learn) and deploy them to FPGAs using the hls4ml library. We'll cover model quantization, hardware-aware training, the HLS synthesis workflow, performance profiling, and practical considerations for deploying ML at the edge. No prior FPGA experience required.
Jerónimo López Gómez
Researcher @ Universidad de Antioquia
Natalia Echeverri Durán
Researcher @ Universidad de Antioquia
LangGraph and Strands Agents: Core Concepts, Patterns, and Tradeoffs
Dive deep into two powerful agentic frameworks—LangGraph and Strands Agents—and learn when to use each. This advanced workshop covers the core concepts behind both frameworks: state machines, graph-based orchestration, tool use, and memory management. We'll build the same agentic application in both frameworks, compare their strengths and limitations, and discuss the architectural trade-offs to help you choose the right tool for your production AI systems.
Your LLM Is Bleeding Money and Python Can Stop It
Every token your LLM processes costs money, and without proper observability, costs can spiral out of control. In this workshop, you'll learn how to instrument your Python LLM applications to track token usage, latency, and cost per request. We'll build a complete observability stack using open-source tools, set up alerts for cost anomalies, and implement strategies to cut your LLM bill without sacrificing quality.
LLMs in Depth: How an LLM Works Mathematically (and Its Implementation with PyTorch)
Demystify the mathematics behind Large Language Models and implement them from scratch in PyTorch. This advanced workshop takes you through the complete mathematical foundations: attention mechanisms, transformer architecture, positional encodings, layer normalization, and training dynamics. For each mathematical concept, we'll write the corresponding PyTorch implementation—giving you a deep, hands-on understanding of how LLMs actually work under the hood.
From Notebook to Production: End-to-End MLOps on Databricks
Move beyond Jupyter notebooks and deploy machine learning models to production using MLOps best practices on Databricks. In this intermediate workshop, you'll learn to structure ML projects for production, implement CI/CD pipelines for models, manage experiments with MLflow, deploy models as REST APIs, and monitor them in production. We'll walk through a complete end-to-end example from data preparation to automated retraining.
Patterns, Protocols and Tactics for Multi-Agent Systems
Master the essential patterns, protocols, and tactics for building robust multi-agent systems in Python. In this workshop, you'll learn proven architectural patterns for multi-agent collaboration, communication protocols between agents, error handling and recovery strategies, and practical implementation tactics. Drawing from real-world experience, we'll build multiple agent architectures and analyze their trade-offs—giving you a reusable toolkit for designing multi-agent systems.
Multi-Agent Teams in AI-Assisted Development: A Glimpse Into the Future of Programming
Get a glimpse into the future of programming, where teams of AI agents collaborate with human developers. In this workshop, you'll explore cutting-edge patterns for multi-agent collaboration in AI-assisted development: code generation agents, review agents, testing agents, and orchestration strategies. We'll build a mini multi-agent development team using Python and the Claude SDK, and discuss where this technology is heading and how developers can prepare.
Daniel Sabogal
Data & ML Intern @ Loka
Isabel Mora
Junior ML Engineer @ Loka
José Hernán Ortiz Ocampo
Senior ML Engineer @ Loka
NLP in Practice: From Corpus Linguistics to RAG with Python
Bridge the gap between traditional corpus linguistics and modern Retrieval-Augmented Generation (RAG) systems. In this workshop, researchers and developers will learn how classical NLP techniques—corpus analysis, tokenization, and annotation—can inform and improve RAG implementations. We'll use Python to build a pipeline that takes a text corpus from raw collection through linguistic analysis to a queryable RAG system, demonstrating how academic NLP foundations enhance practical AI applications.
Biviana Marcela Suárez Sierra
Researcher @ Universidad EAFIT
Dora Cecilia Alzate Gallo
Researcher @ Universidad EAFIT
NORTH: Claude as a Real Copilot
Learn how NORTH uses Claude as a genuine coding copilot—not just a code completer, but a true engineering partner. In this workshop, you'll explore the architecture of NORTH and learn how to build similar AI copilot integrations using Claude's API and Python. We'll cover prompt engineering for coding assistance, maintaining context across long sessions, integrating with development workflows, and building the feedback loops that make AI copilots genuinely useful.
Build an OpenClaw-style Coding Assistant on WhatsApp with Claude Agent SDK
Build a fully functional AI coding assistant that lives in WhatsApp, inspired by OpenClaw, using Claude's Agent SDK and Python. In this hands-on workshop, you'll learn to integrate the Claude Agent SDK with the WhatsApp Business API, design conversational flows for code assistance, handle multi-turn conversations with memory, and deploy your assistant to the cloud. Walk away with a working AI coding companion accessible from any device.
From Prompts to Agents: Intelligent Systems with Python
Take your first steps from writing simple prompts to building intelligent multi-agent systems with Python. In this beginner-friendly workshop, you'll learn the foundations of AI agents, how they differ from simple LLM calls, how to chain agents together for complex tasks, and how to give them tools and memory. Using popular Python frameworks, you'll build a working multi-agent system by the end of the session—no prior AI experience needed.
PyBlend: Towards an AI Food Scientist for Nutritional Product Design
Discover how Python and AI are transforming nutritional product design. In this workshop, you'll be introduced to PyBlend, a framework that models the complex optimization problem of designing nutritional formulations. We'll explore how machine learning algorithms can navigate vast ingredient spaces, balance nutritional constraints, and generate novel product formulations. Attendees will gain hands-on experience with AI-driven product design and learn how Python makes interdisciplinary AI applications possible.
Dashboards That Think: Build Agentic Analytics with Sigma
Learn how to build dashboards that don't just display data—they think. In this workshop, you'll combine Sigma's business intelligence capabilities with Python-based AI agents to create agentic analytics dashboards. We'll cover integrating LLMs with Sigma, building agent-driven data narratives, automating insight discovery, and creating dashboards that can answer follow-up questions and adapt dynamically to user context.
Beyond Vibe Coding: Spec Driven Development with Code Graphs
Go beyond vibe coding and learn how to use specifications and code graphs to guide AI-assisted development. In this workshop, you'll discover how structured specs and dependency graphs give AI coding tools the context they need to produce coherent, maintainable code. We'll work with real Python projects to define specs, generate code graphs, and wire them into your AI-assisted workflow—resulting in code that actually makes sense architecturally.
Esneider Bravo Benítez
Software Engineer @ Lendingfront
Jonathan Vallejo Muñoz
Software Engineer @ Lendingfront
Stop Mocking, Start Containerizing
Tired of maintaining brittle mock objects that don't reflect production behavior? In this workshop, you'll learn how to replace mocks with real containerized services using Testcontainers for Python. Bring your laptop and a running Docker engine—we're going to get our hands dirty!
Now or Never! Token Diet with TOON to Save Money and Help AI Understand More
Tokens cost money, and every unnecessary token you send to an LLM is money wasted. In this workshop, you'll learn how to put your AI applications on a token diet using TOON, a Python tool for creating compact, semantically rich data representations. We'll cover TOON's architecture, how to serialize complex data structures efficiently, measure token reduction, and integrate TOON into existing AI pipelines—without losing the information your models need.
