Making Agent Evals Isn’t As Hard As You Think!
Discussing the theory behind creating and using agent evals Resources: Evals Field Guide - https://lucek.ai/blogs/agent-evaluations Evaluation Concepts - https://docs.langchain.com/langsmith/... Demystifying Evals - https://www.anthropic.com/engineering... Chapters: 00:00 - Introduction 00:33 - Context 02:37 - What get’s measured 05:08 - How its measured 08:20 - Unit Test Evals 11:14 - Agent Integration Evals 14:49 - Online Evals 18:32 - Benchmark Evals 23:51 - Agent Eval Loop #ai #programming #datascience
▶︎
From Retrieval to Navigation: The New RAG Paradigm
▶︎
I Trained an LLM to Think Deeper (Here's How)
▶︎
Why The Best Software Engineers Are Solving Code Review Bottlenecks Now
▶︎
Reinventing Entropy | Compression is Intelligence Part 1
▶︎
How Agents Quietly Break Architecture
▶︎
Do Reranking Models Actually Improve RAG?
▶︎
How AI Engineers Improve Agentic Products
▶︎
The Most Famous AI Company Isn't Winning. Here's Who Is.
▶︎
Reinforcement Learning with Verifiable Rewards - Teaching LLMs to Solve Problems
▶︎
What is happening at Meta?
▶︎
Everything you need to know about Loops
▶︎
Full Walkthrough: Workflow for AI Coding — Matt Pocock
▶︎
How I Made An AI EMPLOYEE with Deep Agents
▶︎
The most rational take on AI you’ll hear this year
▶︎
How AI agents & Claude skills work (Clearly Explained)
▶︎
How To Think SO CLEARLY People Assume You're A Genius
▶︎
WTF Is an "AI Agent Loop"? Genius or Hype?
▶︎
Finally. Agent Loops Clearly Explained.
▶︎
the true reason C++ always wins
▶︎