Most developers build #RAG for semantic similarity. But similar ≠ relevant!
Your coding agent can retrieve documents that match the prompt word-for-word - without actually getting the context it needs to solve the problem.
🔗 Watch the #InfoQ presentation to learn why standard vector retrieval fails and how #ContextEngineering bridges the gap ⇨ https://www.infoq.com/presentations/architecture-context-engineering/
Baruch Sadogursky and Patrick Debois discuss why coding agents fail due to bloated context windows and stuffed prompts. They explain practical context engineering fixes, including lazy-loaded skills, versioned context artifacts, externalized memory banks, and LLM-as-a-judge evals. Software architects & engineering leaders will learn how to turn raw markdown files into reliable agentic workflows.
www.infoq.com
Comments (0)
Sign in to comment or create an account