Most AI tutorials show you a demo. Very few show you the setting that breaks in production three weeks later.
That gap is why I built the Anthropic Claude Field Guide, a ten-part video series on the parts of Claude Code and the Claude API that quietly fail. Every claim in every episode traces back to Anthropic’s official docs, and each one ends with a single change you can make the same day.
The full series is one playlist: https://www.youtube.com/playlist?list=PLHnN5yZzJYeI
Start here, with the one most people need first:
The ten guides
Why Claude Code Ignores Your CLAUDE.md Rules. CLAUDE.md is advice Claude reads. A hook is the one layer it can’t talk its way around. watch
Why Your Claude Prompt Cache Keeps Missing. One ordering mistake makes every call a cache miss, and the API never tells you. watch
Getting Guaranteed JSON From Claude. The old forced tool_choice trick now returns a 400 on the newest models. Here is what replaced it. watch
Running Claude Code Headless in CI. The flags that keep a CI run predictable, and why skipping permissions is the wrong shortcut. watch
Why Claude Ignores the Custom MCP Tools You Built. A one-line description loses to a built-in every time. Anthropic’s docs ask for three to four sentences. watch
Sharing Claude Code Config Without Leaking Secrets. Which settings file your team commits, and which one stays on your machine. watch
When the Batch API Cuts Your Claude Bill in Half. A three-question test for which workloads can wait, at half the token price. watch
Claude Orchestrator Patterns. When to fan out, when to loop, and the silent failure where a coordinator says it delegated and never did. watch
Why Your Claude Code Review Prompt Hides Real Bugs. A real run: the confidence line in your review prompt kept a 100x bug out of the findings. Split finding from filtering, with a demo repo you can run. watch
How to Secure a Claude Agent With Tool Access. Six layers, from retrieval ACL to per-user credentials, each with a real run and a public lab. watch
Also new: the OpenAI Codex Field Guide
Codex has one 32 KiB budget for every AGENTS.md file in your repo. The file that crosses it gets cut partway through, and the only warning is a single log line.
Why Codex Ignores Half Your AGENTS.md. Five suspects, real runs on Apache Airflow, and a free script that shows exactly what Codex loads. watch
Fail File #1: Codex Was Reading Half the Rules. The live run: same repo, same question, one setting changed. watch
In plain English
If your company is putting AI assistants to work, these videos cover the settings that decide whether the assistant follows your rules, costs what you expect, and keeps your data where it belongs. Each episode runs about six minutes. Pick the one that matches the problem your team hit this month.
How to use the series
Start with number one if you use Claude Code every day. Start with number two or number seven if your Claude bill is the conversation this quarter. Start with number ten if an agent of yours can touch real systems.
Which Claude feature should get its own Field Guide next?
#ClaudeCode #AIEngineering #AIAgents #DevOps #CloudArchitecture