62 posts on engineering, architecture, and technical craft.
An AI with shell access and no guardrails will eventually destroy something you care about. This post dissects how a production harness implements layered permissions, hooks, dangerous pattern detection, and trust boundaries — balancing safety with usability.
10 min readThe orchestration loop is the heart of an AI harness — a state machine that coordinates API calls, streaming responses, concurrent tool execution, error recovery, and token budgets. This post traces the complete data flow from user input to final response.
9 min readAd-hoc prompting is fine for one-off questions. Repeatable workflows deserve structure. This post dissects how a production harness defines, discovers, loads, and executes skills — reusable AI workflows that turn tribal knowledge into executable automation.
8 min readThe invisible foundation beneath every AI harness layer: centralized state management, per-model cost tracking, rate limit handling, a custom React-to-terminal renderer, and multiple entry points. This post covers what makes 'works in a demo' become 'works in production.'
9 min readA production AI harness is not single-threaded. Background agents explore codebases, shell commands execute, remote agents run on cloud infrastructure — all while the main conversation continues. This post dissects the task system that manages this concurrency.
8 min readThe model is only as good as the context it receives. This post dissects how a production AI harness constructs system prompts, loads project instructions, manages persistent memory, and compresses context when the window fills — all to give the model the right information at the right time.
9 min readA chatbot answers. An agent finishes the job. The gap between them is not one feature — it's a stack of seven capabilities, built one rung at a time. This series walks that stack in plain English, for engineers and curious non-engineers alike.
9 min readFastAPI's Depends() handles per-request wiring. dependency-injector handles everything else — configuration, singletons, factories, and a declarative container that makes your entire object graph visible in one file.
15 min readYou have been typing instructions into AI assistants one conversation at a time. Skills flip that model — they turn your best prompts into reusable, structured workflows that any team member can run. This post explains the shift from ad-hoc prompting to skill-driven development.
7 min readEvery AI assistant starts each conversation knowing nothing about your project. Context files change that — they encode your stack, conventions, and constraints so the AI works with your codebase instead of against it. This post shows how to build the foundation layer that makes every skill smarter.
9 min read