Learn

Learn testing: by watching and doing.

Video walkthroughs, a podcast, and a path that picks up where the last lesson left off.

Video lessons are coming

First video is in the works, walking through the regression harness from the featured article. Videos will live on YouTube.

Follow the channel

The podcast hasn’t launched yet

Conversations on testing and AI, recorded, not scripted. Episode one is being planned.

What’s coming

A public roadmap, not a progress bar

Catching LLM Hallucinations With a Regression Harness

Published: read it.

Write Your First LLM Eval

Published: read it.

Building a Golden Dataset for LLM Evals

Published: read it.

The LLM Test Pyramid

Published: read it.

Testing LangGraph Agents

Published: read it.

Building an LLM-as-Judge Eval Pipeline

Published: read it.

Red-Teaming Your Own Guardrails

Published: read it.

Precision, Recall, and Vibes: Evaluating RAG Pipelines

Published: read it.

Can Your LLM Catch Its Own Bugs? Mutation Testing Meets AI

Published: read it.

Chaos Monkey for Agents

Published: read it.

The Tokens Are the Budget

Published: read it.

Schema or It Didn’t Happen: Testing MCP Tool Definitions

Published: read it.

AI Wrote the Test Cases: Now Who Tests the Test Cases?

Published: read it.

Turn It Loose: Building an Exploratory Testing Agent

Published: read it.

Teaching Your Test Suite to Heal Itself

Published: read it.

The Flakiness Score: Finding Your Worst Tests With Statistics

Published: read it.

Semantic Flaky-Test Clustering: When Text Similarity Isn’t Enough

Planned.

Timeouts and Zombies: Testing Agents Against Hung Tool Calls

Planned.