Tag
This article describes a reference RAG agent implementation using Mastra and Elasticsearch vector store, demonstrated on a corpus of 500 sci-fi movies, with the agent built in approximately 60 lines of TypeScript.
A detailed demonstration of using Google's Agents CLI eval skill to detect and fix 'vibe coding' vulnerabilities in RAG agents, illustrated with a real example where Claude Code helped create a custom rubric and improved test scores from 19/33 to 30/33.