Skip to content
CodeStoa

One lesson a day · Free

Understand how software really works.

Each lesson is an animated video, a written deep dive with code that runs, and a quick quiz. Starting with System Design and AI Engineering, with more stacks on the way.

today's lesson

AI Engineering Beginner 5:05 video

LLM Evals: Why "It Looks Good" Isn't Enough

§ 01

The syllabus

Each domain is split into subdomains, from fundamentals to the internals senior engineers know. Pick one and go deep.

  1. System Design

    Coming soon

    Design systems that are fast, scalable and reliable.

    • Latency
    • Performance
  2. AI Engineering

    1 of 1 published

    Build real applications with LLMs, agents and tools.

    • LLM Application Evaluation
    • LangChain
    • LangGraph
    • Prompt Engineering
    • MCP
    • Claude
  3. More on the way

    Languages, frameworks and more, taught the same way.

§ 02

Watch it. Read it. Prove it.

Every lesson gives you three ways into the same idea, because understanding sticks when you see it, read it and use it.

  1. 01 · Watch

    A short animated explainer, narrated, with Vora as your guide: diagrams move, data flows, code runs.

  2. 02 · Read

    What are LLM evals?

    LLM evals are systematic, repeatable tests that judge an LLM, or a system built on one such as an agent, against clear criteria. They're how you know an AI app works, instead of hoping it does.

    A written deep dive at your own pace, with code that has been run before it was published.

  3. 03 · Practice

    A teammate tries a new prompt on the same five questions they always use and says it's better. What's the main problem?

    A short quiz that explains every answer, right or wrong.

See the whole lesson: LLM Evals: Why "It Looks Good" Isn't Enough

§ 03

Latest lessons

A new topic lands every day.

  • 5:05

    AI Engineering Beginner 4 min read

    LLM Evals: Why "It Looks Good" Isn't Enough

    LLM evals are systematic, repeatable tests that judge an LLM app against clear criteria. Learn why spot checks fail, how evals differ from classic tests, and the workflow to run them.

    Oct 19, 2026

Subscribe via RSS