tag · 16 essays
All essays tagged agentic-sdlc.
I built a serverless internet health monitor because I wanted an excuse to learn Lambda MicroVMs. The better lesson was that Barometer did not need the newest primitive. It needed the boring, correct fit between the tool and the job.
★I lead engineering at a Fortune 100 company, and I still ship my own software. Not because leaders need to prove they can code, but because AI is changing the work faster than secondhand models can keep up.
★I rebuilt a working web app as native iOS and Mac software, not because native was magic, but because the discipline required to make it correct is the same discipline AI agents need to be useful.
★Twenty-six days of Claude Code showed $2,556 of API-priced work against a $200 subscription. The lesson was not the total. It was cache behavior, model routing, and a government kill switch that landed in my usage chart. Value lives in verified outcomes, not tokens, and the work has to survive the stop.
★AI has made generation cheap. The durable advantage now belongs to teams that can encode judgment into gates that verify whether the work should ship.
A government order took Anthropic's Fable 5 and Mythos 5 offline. The lesson for enterprise AI is architecture: portability gets you out, verification gets you out safely.
★Enterprise AI is entering its accounting phase. The winners will measure verified outcomes, not just tokens, subscriptions, or generated output.
★Most AI reorgs open with a headcount model. The better sequence redesigns workflows, decision rights, ownership, and evaluation loops first, then lets the org chart follow the work it is meant to describe.
AI's free-lunch phase is ending, and that makes AI-driven layoff math harder to defend. Two repricings, one ledger.
Claude Code agent teams are powerful, but they are not faster subagents. They earn their cost only when the work needs real peer challenge, not polite parallel execution.
Agent loops let the model pick the next step. Workflows invert that. Code owns the control flow; the model owns the judgment inside each step. Here is the TypeScript file I am running today, type-checked against the live SDK, and the honest answer to whether you should build this now or wait for the official tool.
★My thesis is that as agents get better at execution, the primary constraint for organizations shifts from technical production to the human-led framing of problems.
★Viral prompt threads borrow the language of science without the rigor. Here's a four-question code review for any prompt, plus a worked example that shows the gap between sounding authoritative and being right.
A field report on building Inkwell, a pure-CSS design system that turns taste into repeatable constraints for people, teams, and coding agents.
A year of writing, one argument, and a working theory of where software is going
★The strategy posts say AI software development is a system. Here is the working loop I run inside that system: a refined specification, a layer of standards, and a coordinated set of specialists doing the work.
★browse other tags