Workflow tuning, tips & tricks, in-depth guides and deep dives: harness engineering, agents & orchestration, AgentKit and other AI tools. Teardowns of repos worth reading, AI and software terms and patterns explained, system design and architecture.
Deploy Cloud Harness MCP to a VPS, gate the hostname with Cloudflare Access, turn on Managed OAuth, then wire up the ChatGPT connector. With 21 real screenshots, identifying data blurred.
Install, validate, choose modes, write prompts, and operate UI Craft end to end.
A practical guide to using Archify with an AI agent for code-grounded diagrams or proposed flows, using one bakery example throughout.
Seven content areas. Pick the one closest to your work and read its two suggested pieces first.
Habits and workflows for working with agents faster, with less rework.
The runtime layer around the model: hooks, guards, routing, control plane.
Running agents in parallel, advisors, subagents, and how to coordinate them.
Installing, configuring, and running AgentKit and other AI tools.
Close reads of repos worth learning from: structure, design choices, reuse.
AI and software terms and patterns, explained with examples that run.
System architecture, and using AI to design, draw, and check it.
The Advisor is a supervisory control loop running alongside the main agent in the same session, not a stronger model called in to give an opinion.
OMP /plan locks the runtime read-only, AgentKit ak:plan produces a durable file-backed roadmap. When to use which, and why not to nest the two workflows.
OMP roles are routing aliases, not agents. Assign models by workload, inspect effective state, and retry through fallbacks.
Every piece has a machine-readable edition over REST and MCP, versioned with the web one. Subscriber pieces need a key from an account with access.
Create an API key$ content.read slug=cloud-harness-mcp-chatgpt-setup