Subscribe

Stage 3 · Advanced

Agents in Production

Context, memory, cost guardrails and the workspace an autonomous coding agent needs.

You'll be able to: Run agents that stay sharp over long tasks, stay on budget and hand back reviewable work.

0 of 9 done
  1. 1 Cinematic deep dive 7 min Failure mode + fix Context Engineering for AI Agents An agent is only as smart as its context window: treat the window as a budget, and write, select, compress and isolate what goes into it at every step.
  2. 2 Cinematic Short 52 sec Failure mode + fix The Runaway Agent An agent loop with no step cap and no budget can retry a failing tool all night, and because every call resends a growing context, the bill grows faster than the number of steps.
  3. 3 Deep dive 4 min Failure mode + fix Autonomous Coding Agents An autonomous coding agent is a controlled loop: it reads a bounded task, observes a real repository, makes small changes, proves them with tests, and hands a reviewable pull request back to a human.
  4. 4 Cinematic deep dive 6 min Failure mode + fix Building Memory for AI Agents Useful agent memory is a small, scoped, revisable set of evidence: capture what matters, retrieve it when relevant, and retire it when the world changes.
  5. 5 Cinematic deep dive 9 min Failure mode + fix Inside the AI Agent Harness The model only predicts the next tokens; the harness is everything else (the loop, tools, permissions, sandbox, context management, hooks and subagents), which is why the same model can be great in one product and useless in another.
  6. 6 Cinematic deep dive 10 min Failure mode + fix Remote Control vs Cloud Agents Every coding agent now answers two separate questions, where the agent runs (your machine or a cloud VM) and where you steer it from (terminal, browser or phone): Remote Control keeps the agent at home and hands you the remote, cloud sessions send it to a disposable VM, and both reach your machine without opening a single inbound port.
  7. 7 Cinematic deep dive 7 min Failure mode + fix Build Web Apps From a Phone You can build, fine-tune, test and ship a web app entirely from the Claude app on a phone, because the phone is only the remote: a Claude Code cloud session does the work in a VM, every push gets a preview link you open and test in the phone's own browser, and specific prompts (plan first, one change at a time, ask for proof, ask why before fixing) make the replies you get back easy to check on a small screen.
  8. 8 Cinematic Short 55 sec Why use it Your Laptop Is Your Cloud Run `claude remote-control` on your own laptop or desktop and it acts like a private cloud dev box: your phone starts and steers sessions on it, with your files, GPU, databases and MCP servers, and the machine never opens an inbound port.
  9. 9 Cinematic Short 166 sec How it works Scion Replaced Git When Claude pushed Anthropic from 2,500 to 30,000+ merges a day, the bottleneck moved into Git; Scion fixes it by dropping Git's offline, full-clone assumption: thin always-online clients, a smart server, and three cache tiers.
  10. Coming soonPrompt Injection in AI AgentsAnnounced at the end of an episode in this track. Subscribe to catch it.
  11. Coming soonLLM GatewaysAnnounced at the end of an episode in this track. Subscribe to catch it.
  12. Coming soonPrompt Injection Through ToolsAnnounced at the end of an episode in this track. Subscribe to catch it.
  13. Coming soonWhen RAG Leaks Private DocumentsAnnounced at the end of an episode in this track. Subscribe to catch it.
  14. Coming soonAgent sandboxing: how isolation really worksAnnounced at the end of an episode in this track. Subscribe to catch it.
Next stage Hands-On: Coding Agents from Your Phone