Hightower's AI Harness Engineering

Hightower's AI Harness Engineering

Home
Podcast
Notes
Chat
Archive
Leaderboard
About
Video: Claude Agent SDK Design Patterns: You Can Build Any Agent. The Harder Question Is Which One You Should.
Part 12: Anthropic's five agent design patterns are a vocabulary for design decisions. Here is how each maps onto the Claude Agent SDK constructs that…
1 hr ago • Rick Hightower
25:07
Claude Code: The Two Claude Code Schedulers That Run on Your Machine, and When to Use Each
Part 6: Cloud Routines stop at a one-hour floor. For recurring work tied to your local files, you have /loop and Desktop scheduled tasks. Here is how to…
6 hrs ago • Rick Hightower
Claude Code Routines: Running Your Agent on Anthropic's Clock, Not Yours
Part 5: Every other way to automate Claude Code needs your machine on. Routines run in Anthropic's cloud, which means the work finally happens at 3am…
13 hrs ago • Rick Hightower
Advanced Claude Code: Text a Task to Claude and Walk Away: A Practical Guide to Dispatch
Part 4: The most overlooked Claude Code feature is also the simplest: message a coding task from your phone, and a session spins up on your own machine…
15 hrs ago • Rick Hightower
Claude Code Advanced: Drive Your Local Claude Code Session From Your Phone, Your Browser, Anywhere
Part 3: The session runs on your machine the whole time. Remote Control just gives you a new pair of eyes and a new keyboard, on whatever device is in…
Jun 11 • Rick Hightower
Claude Code Advanced - Mastering Channels: Stop Walking Back to Your Laptop: Push the World into a Running Claude Session
Part 2: Claude Code channels turn CI failures, bug reports, and deploy alerts into messages that to the session that already knows your codebase…
Jun 11 • Rick Hightower
Claude Code - Routines, Remote Control, Scheduled Tasks and Channels: The Four Ways Claude Code Works Without You
Part 1: Most people learn Claude Code as a list of commands they type at a terminal. The developers who pull ahead learn the opposite skill: how to make…
Jun 11 • Rick Hightower
The Karpathy's AutoResearch: Automating Business Growth
Imagine improve your processes while you sleep
Jun 10 • Rick Hightower
4:17
Claude Agent SDK Debugging: The Ten Errors You Will Actually Hit With the Claude Agent SDK
Part 13: A field guide organized by symptom, not by feature. When something breaks in production, you do not know which subsystem failed. You only know…
Jun 10 • Rick Hightower
Claude Agent SDK Design Patterns: You Can Build Any Agent. The Harder Question Is Which One You Should.
Part 12: Anthropic's five agent design patterns are a vocabulary for design decisions. Here is how each maps onto the Claude Agent SDK constructs that…
Jun 9 • Rick Hightower
Claude Agent SDK Plugins: You Built a Test Tool, a Reviewer, and an Audit Hook. Stop Wiring Them by Hand.
Part 11: How Claude Agent SDK plugins bundle the custom tools, subagents, hooks, and MCP servers you have scattered across your code into one portable…
Jun 8 • Rick Hightower
Claude Agent SDK Deployment: You Cannot Deploy an AI Agent Like a Lambda
Part 10: It has a shell, a memory, and untrusted input pointed straight at it. Hosting the Claude Agent SDK is a question of architecture and isolation…
Jun 7 • Rick Hightower
© 2026 Rick Hightower · Privacy ∙ Terms ∙ Collection notice
Start your SubstackGet the app
Substack is the home for great culture