The 6 open challenges in context engineering
Harrison Chase (LangChain): agent architecture has converged, but proactive, always-on agents bring six new challenges.
An LLM is the engine; the agent is the whole car. This talk covers why agents need governance and the three challenges ahead (memory, robust planning and UX for agents), each with its ethical angle.
Download the slides as PDF The slides are in Spanish.
Harrison Chase (LangChain): agent architecture has converged, but proactive, always-on agents bring six new challenges.
I explain Anthropic's "Prompting Claude Opus 5.5" guide: effort, thinking, unattended agents, refusals, progress updates...
How to stop a retry from duplicating what a tool saves: a stable identity per operation, a ledger with states, and what ...
Let's talk.
maximofn@gmail.com
Machine Learning and AI specialist. I develop solutions with generative AI, intelligent agents and custom models.
Interactive 3D talk on what a software factory is: how agents are chained, how to delegate approval and where to start.
Interactive 3D talk on the Gymnasia agent: where data lives, from plate to data, tools, duplicates, health limits and how to test it all.
Hugging Face spaces allow us to run models with very simple demos, but what if the demo breaks? Or if the user deletes it? That's why I've created docker containers with some interesting spaces, to be able to use them locally, whatever happens. In fact, if you click on any project view button, it may take you to a space that doesn't work.
Let's talk.
maximofn@gmail.com
Machine Learning and AI specialist. I develop solutions with generative AI, intelligent agents and custom models.
Dataset with jokes in English
Use: Fine-tuning text generation models for humor
Dataset with translations from English to Spanish
Use: Training English-Spanish translation models
Dataset with Netflix movies and series
Use: Netflix catalog analysis and recommendation systems