Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
miia: Agentes Inteligentes en Software
Learn how a three‑agent system—writer, estimator, programmer—automates user story refinement, effort estimation, and code generation to streamline software development workflows.
Presentaremos el concepto del desarrollador aumentado por miia: un sistema inteligente basado en una arquitectura multiagentes, diseñado para automatizar y optimizar etapas clave del ciclo de desarrollo de software.
Este sistema se construyó bajo la premisa de que la inteligencia artificial puede integrarse como una herramienta estratégica para potenciar las capacidades humanas, no para reemplazarlas. Con miia, diseñamos una arquitectura compuesta por tres agentes especializados que colaboran de forma orquestada para mejorar la eficiencia, la claridad del flujo de trabajo y la calidad del producto.
Fases del sistema multiagente:
Agente escritor: organiza y depura historias de usuario usando contexto del código, documentación y aprendizajes previos.
Agente estimador: calcula el esfuerzo técnico necesario por historia, mejorando la comunicación con los stakeholders.
Agente programador: genera código adaptado al entorno técnico, asegurando coherencia arquitectónica y buenas prácticas.
En esta charla compartiremos cómo diseñamos la arquitectura de miia basada en múltiples agentes colaborativos, un caso de uso real, los aprendizajes obtenidos y cómo esta solución está evolucionando en Ceiba.
- GPT-4GPT-4 is OpenAI’s large multimodal model: it processes both text and image inputs, delivering human-level performance on complex professional and academic benchmarks.This is OpenAI’s latest milestone in scaling deep learning: a large multimodal model accepting both text and image inputs. It demonstrates a significant capability leap over its predecessor, scoring in the top 10% on a simulated bar exam (GPT-3.5 scored in the bottom 10%). The model handles nuanced instructions and long-form content, supporting context windows up to 32,768 tokens (32K model). This capacity allows processing up to 25,000 words in a single, complex prompt. GPT-4 is engineered for enhanced reliability, steerability, and advanced reasoning across diverse tasks.
- LangChainThe open-source framework for building and deploying reliable, data-aware Large Language Model (LLM) applications.LangChain is the essential framework for engineering LLM-powered applications: it simplifies connecting models (like GPT-4 or Claude) to external data, computation, and APIs. The platform provides a modular set of components—Chains, Agents, Tools, and Memory—allowing developers to quickly build complex workflows like Retrieval-Augmented Generation (RAG) pipelines and sophisticated conversational agents. Its Python and JavaScript libraries, combined with LangChain Expression Language (LCEL), offer a standardized interface for rapid prototyping and moving applications to production with confidence.
- TransformersThe deep learning architecture that revolutionized sequence modeling (NLP, vision) by replacing recurrent units with a parallelizable multi-head self-attention mechanism.The Transformer: a neural network architecture introduced in the landmark 2017 paper, "Attention Is All You Need." It eliminated the sequential processing bottleneck of prior Recurrent Neural Networks (RNNs) by relying solely on self-attention, enabling massive parallelization and significantly faster training (up to 10x faster) on modern hardware. This efficiency allowed for the creation of large-scale pre-trained models: BERT (encoder-only) and the generative GPT series (decoder-only). The architecture is now foundational to all modern Large Language Models (LLMs) and drives the current state-of-the-art in AI.
- PyTorchPyTorch is the open-source machine learning framework: it provides a Python-first tensor library with strong GPU acceleration and a dynamic computation graph for building deep neural networks.PyTorch, developed by Meta AI, is a premier open-source deep learning framework favored in both research and production environments. Its core is a powerful tensor library (like NumPy) optimized for GPU acceleration, delivering 50x or greater speedups for complex computations. The key differentiator is its 'Pythonic' design and dynamic computation graph (eager execution), which allows for rapid prototyping and simplified debugging compared to static-graph frameworks. Leveraging its Autograd system for automatic differentiation, practitioners build and train models for computer vision and NLP; major companies like Tesla (Autopilot) and Microsoft utilize PyTorch for critical AI applications.
- OpenAI APIOpenAI API: Your direct gateway to cutting-edge AI models (GPT-4o, DALL-E 3, Whisper), enabling scalable, multimodal intelligence integration into any application.The OpenAI API provides authenticated, programmatic access to a powerful suite of generative AI models. Developers leverage REST endpoints and official libraries (Python, Node.js) to integrate capabilities like advanced text generation (GPT-4o), image creation (DALL-E 3), and speech-to-text transcription (Whisper). This platform is engineered for scale, supporting millions of daily requests for tasks from complex reasoning to real-time customer support agents, ensuring your application gets reliable, state-of-the-art intelligence.
Related projects
Agentes AI - Puesta en marcha
Bogotá
Learn how AI agents work and how to enhance language model functionality using open‑source tools and Google Vertex…
Facilitando el proceso de selección y pruebas técnicas.
Medellín
Learn how to automate CV parsing, scoring, and sentiment analysis of interview videos using LLMs, Google Sheets, and…
Agent interaction experiments
Bogotá
This talk explores how autonomous AI agents interact to perform complex tasks independently, addressing challenges and applications across…
Orquestación y especialización de agentes código
Medellín
Learn practical steps to orchestrate and specialize coding agents, enabling them to collaborate efficiently and boost developer productivity…
Objetos de aprendizaje conducidos por IA
Medellín
This talk covers developing interactive virtual learning objects using a ReactJS library enhanced with AI to create dynamic…
Agentic Process Automation (Even a CTO Can Understand)
Medellín
A live demo shows how autonomous AI agents convert messy everyday workflows into intelligent, scalable processes, handling complex…