7 stages · 27 episodes
The learning path
Go from "why is the far server slow?" to running agents safely in production. Each stage starts with the big picture, then zooms into the failure modes and fixes. Mark episodes as done and your progress is saved in this browser.
- 1 Foundations Edge & Caching Why far servers feel fast, where edge rendering backfires, and how one cache expiry can take down an AI app. 0 of 2 done
- 2 Core Decision Models When a typed decision beats generated text, and how to route between a decision model and an LLM. 0 of 3 done
- 3 Advanced Agents in Production Context, memory, cost guardrails and the workspace an autonomous coding agent needs. 0 of 9 done
- 4 Hands-on Hands-On: Coding Agents from Your Phone Step-by-step tutorials: build and ship real apps from the Claude app, with the prompts and the code for every step. 0 of 3 done
- 5 Hands-on AI Coding Agent Tips One practical tip per Short for Claude Code and the other coding agents, each one tested in a real run. 0 of 2 done
- 6 Extra Code Stories Picture-led stories from the history of programming, and what they say about where coding goes next. 0 of 3 done
- 7 Advanced AI Security Stolen tokens, poisoned tools and the other ways an AI system gets turned against its users. 0 of 5 done
How to use it
- Go in order. Stages build on each other: caching and latency first, then LLM apps, decision models, agents and security.
- Watch, then read. Every episode page has the video and the full written design: architecture, request flow, the failure mode, the fix and the trade-offs.
- Check the numbers. "Numbers worth knowing" and the sources tell you which figures are measured and which are illustrative.
- Mark it done. Your progress stays in this browser. No account needed.
1. Edge & Caching Foundations
Open stage
2. Decision Models Core
Open stage
3. Agents in Production Advanced
Open stage
7 min
Step 1
Context Engineering for AI Agents
Brilliant at step one. By step forty, your agent forgot the task.
52 sec
Step 2
The Runaway Agent
Your agent looped all night. $10k gone.
4 min
Step 3
Autonomous Coding Agents
The hard part is not writing code. It is proving the change is safe.
6 min
Step 4
Building Memory for AI Agents
Your agent remembered the wrong version of you.
9 min
Step 5
Inside the AI Agent Harness
Same model. Different agent. The harness decides.
10 min
Step 6
Remote Control vs Cloud Agents
Your agent needs you. You are not at your desk.
7 min
Step 7
Build Web Apps From a Phone
A whole web app, built from a phone.
55 sec
Step 8
Your Laptop Is Your Cloud
Your laptop can be your own cloud dev box.
166 sec
Step 9
Scion Replaced Git
Claude's code flood broke Git. So Anthropic built Scion.
4. Hands-On: Coding Agents from Your Phone Hands-on
Open stage
5. AI Coding Agent Tips Hands-on
Open stage
6. Code Stories Extra
Open stage
7. AI Security Advanced
Open stage
47 sec
Step 1
Approval Fatigue
You tapped Allow 41 times. One was rm -rf.
9 min
Step 2
Grok Bot: Agents on One Computer
Five bots. One computer. Your logins.
60 sec
Step 3
Five Bots, One Computer
Five bots. One computer. All signed in as you.
60 sec
Step 4
The Rule Was Only a Wish
Your agent fixed the deck overnight. Nobody asked it to.
60 sec
Step 5
Put Your Agent in a Box
Your agent runs every command as you.