Operating the AI-Native Stack

What happens when you stop using AI tools and start operating AI infrastructure. State management, routing, trust boundaries, and the architecture that emerges when serious work forces system decomposition.

16 stops

The Missing Layer Is a Memory Substrate

Bigger context windows are not the answer to serious AI workflows. Once multiple systems need the same durable truth about the user, the projects, and the working context, memory stops being a feature and becomes infrastructure.

A Perfectionist's Permission to Ship

AI made drafting cheap and left editing exactly as expensive. For a perfectionist that barely helps. The fix wasn't more discipline, it was a published quality gate that decides how much editing a piece is allowed to get.

The Architect and the Coder

Most talk about AI agents treats 'the agent' as one worker. In practice it's two roles, and keeping them apart, with a written contract between them, is most of why the setup works.

Compile-Time Came Back

Agentic coding reintroduced the dead time long compiles used to have. The part that reorganized my day isn't that the agents write code, it's that I turned into the scheduler.

Who Wrote This?

When an agent writes the code and you direct and approve it, 'who's the author' feels like a deep question. Operationally it isn't a question about authorship at all. It's a logging problem.

Stop Feeding Your Agent Everything

We argue about what a prompt should say. The variable that actually changed the behavior was where the instruction lives and when it arrives. Context is something you route.

When the Bug Is in the Instruction

A bug in agent-written code is often not a bug in the code. Because the build prompt lives on the issue, you can debug the instruction the same way you debug the program.

GitHub Issues Is a Bad Message Bus, and That's the Point

By every metric a distributed-systems engineer cares about, a GitHub issue tracker is a terrible message bus. The properties that make it terrible are exactly the ones agentic workflows need.

The Money Problem

Treating AI cost as a money problem misses where it actually bites: a deadline, an exhausted usage allowance, all your eggs in one provider's basket. That's not a spending problem, it's a routing problem.

The Groundhog Day Problem

Every AI session starts from zero. People treat that as a prompting problem and get good at re-explaining themselves. It's a state problem, and the fix is completely different.

Your CLAUDE.md Is a Junk Drawer

It starts small and focused, then sprawls into a file you're afraid to delete from. It isn't too long. It's holding four different jobs that want four different homes.

What's a Message Bus?

A plain-language primer: when two programs need to coordinate, they need a channel in the middle. Queues, broadcasts, logs, signals: the shapes that matter before the brand names.

Privacy Is an Architecture Problem

The single-assistant fantasy breaks down as soon as AI touches real work. Different tasks have different trust boundaries, which means privacy has to be expressed in the architecture, not buried in settings.

Inside the AI Control Plane

The useful shift in agentic work is not one smarter agent. It is role separation: one layer scopes and governs the work, another executes against a contract, and a reviewer decides whether the result stands.

From AI Disclosure to Process Transparency

Most AI acknowledgments are too vague to be useful. Process transparency gives teams a practical, auditable way to describe human-AI work without pretending the model is an author.

GitHub Issues as Ephemeral Prompt Storage

Prompts are ephemeral — one issue, one prompt, one fix. Here's why I stopped treating them like durable artifacts and started putting them where they belong: on the issue itself.

What else belongs on this trail?

If there's a missing connection this path should include, or something new you'd like to see explored here, let me know.

Get in touch →