JUL 13Past
Evals Without Fooling Yourself
Online🎬 Recording
Learn how to build reliable evaluation pipelines for LLM applications. We'll cover common pitfalls and practical approaches used in production.
Live deep-dives with practitioners — online sessions, always recorded.
Learn how to build reliable evaluation pipelines for LLM applications. We'll cover common pitfalls and practical approaches used in production.
A practical walkthrough of the full fine-tuning workflow — from dataset preparation and training to deploying a custom model endpoint.
Everything you need to build a production-grade Retrieval Augmented Generation system. Indexing strategies, retrieval quality, and latency optimisation.
How do agents remember? Explore short-term, long-term, and episodic memory strategies for building context-aware AI agents.