A month ago I resubscribed to Codex because Anthropic's limits kept stopping me. Then came three 5.5 models in fifteen days, a Sonnet cache cut, and $200 of API credit tucked inside my Max plan.

Why homemade beats off-the-shelf, what actually makes an agent learn, and a job finder built for friends.

The quiet ways the agent you already run falls apart in use, and how to make fewer of them.

Ten months of running my agent from a black window, eight interfaces that almost worked, and the open source agentic IDE that ended the hunt this week.

It reads their CV, searches every morning across many sources, explains why each role fits, and gets sharper when they reply to the email. Here is the whole thing, written down.

Why the fallback layer is the cheapest resilience you can ship, what the $20 actually buys you, and the capabilities I deliberately keep off the primary stack.

What happens when capability masks debt, and why the human read is the check nothing automates away.

A working playbook: effort by task, model routing, agentic runs, and vibe coding without the surprise bill.

From a Lego castle on the living room carpet to a kanban board I shipped on three platforms and killed in six months.

Six months of mistakes, a real walk-through, and everything I wish someone had told me before I started.

The corrections loop. Six months in. Here is what actually made my agent learn.

No real AI hardware yet, agents still break, and trust is the bottleneck. Where I think the next few years actually go, from someone who lives with one.

Three weeks of building instead of writing. Here is everything that piled up in the meantime, including a few days with Anthropic’s new top model.

What an AI agent and an ADHD brain actually do to each other, good and bad, and what to do about it.

Three AI graphic novels, one research question: where does the line between slop and quality actually live? What changed across 255 agents, 16M tokens, and three complete pipelines.

The checkpoint system that makes building with AI agents actually survivable.

What minimal knowledge and a vague direction get you now, and why vibe coding quietly became my default.

It reads their CV, searches every morning across many sources, explains why each role fits, and gets sharper when they reply to the email. Here is the whole thing, written down.