Where the Saved Hour Goes
AI can create a real time dividend for engineers, and history says unallocated capacity gets absorbed before anyone notices. The case for deciding where the saved hour goes.
★tag · 28 essays
#agentic-sdlc
All essays tagged agentic-sdlc.
Don't Automate the Apprenticeship Out of Engineering
Entry-level work was never just cheap execution. It was the training system that produced the people capable of judging what the machines build.
★The Modernization Backlog Just Got Repriced
The rewrite taboo broke for systems that can grade their own replacement. At enterprise scale, the first modernization dollar should fund the answer key, not the port.
★Everyone Knows You Never Rewrite
For twenty-six years, the full rewrite was the cardinal sin of software engineering. Then one engineer ported half a million lines of Bun from Zig to Rust in eleven days. The taboo was never about code. It was a price tag, and for systems whose intent lives in an executable oracle, the price just collapsed.
★Paying for Intelligence Twice
Satya Nadella named a real problem: AI workflows generate valuable learning exhaust from proprietary context and corrections. He is right about the asset. My practitioner's edit is simple: own the learning loop, not necessarily the model.
★Two Gates and a Night Shift
My personal delivery pipeline runs on three Claude agents, three nested loops, and two explicit human approval gates. The gates sit where judgment is cheapest and most consequential, and the real bottleneck moved upstream to the clarity of the ask.
★Barometer: I Chased a New Primitive. I Was Standing on It.
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.
★Still in the Code
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.
★Native Was the Long Way Around. The Stack Wasn't the Point.
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.
★The Subsidy, Itemized
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.
★Trust the Gate, Not the Actor
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.
The Kill Switch Was Always There
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.
★The AI Operating Ledger
Enterprise AI is entering its accounting phase. The winners will measure verified outcomes, not just tokens, subscriptions, or generated output.
★Your First AI Reorg Should Be the Work, Not the People
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.
The Subsidy and the Severance
AI's free-lunch phase is ending, and that makes AI-driven layoff math harder to defend. Two repricings, one ledger.
The Agent Team Tax: When AI Agents Need to Argue
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.
Workflow.ts: When the Code Runs the Agent, Not the Other Way Around
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.
★The Frame Is the Bottleneck
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.
★Code Review Your Prompts
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.
Stunning UIs Aren't Just Designed. They're Enforced.
A field report on building Inkwell, a pure-CSS design system that turns taste into repeatable constraints for people, teams, and coding agents.
The Bottleneck Is Never the Stack
A year of writing, one argument, and a working theory of where software is going
★Spec, Standards, Specialists: How I Actually Build with AI
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.
★The Agentic SDLC: Uniting the AI Tool Sprawl
Every tool in your product development life cycle is now an AI agent trying to do everything. Here is how to stop the chaos, draw the right boundaries, and build an orchestrated pipeline that actually works.
★The Dark Factory Model for AI-Driven Software Development
Most engineers treat AI-generated code like work from a junior developer they don't trust. Simon Willison gave me a better mental model: the dark factory. Here is what it means, why experience is the raw material, and how to build a system that runs.
Meet Roci: My Always-On Personal AI Agent, One Month In
Back in January I wrote about OpenClaw as a concept. That post was the theory. This one is the implementation. One month running a dedicated EC2 instance, a name, and an agent I genuinely rely on.
The Rise of MCP Servers: Why Every Developer Will Have a Personal AI Toolchain
From AWS to GitHub to Podman, MCP servers are quietly becoming the new plug-in ecosystem for developers—and it’s changing how we work.
From Procrastination to Privacy-First Productivity (Part 2)
After building two open-source task managers to battle procrastination, I took it further — secure cloud sync, end-to-end encryption, and now an MCP server that connects your tasks to AI.
From AI to Agents: Building Smarter Systems that think, decide and act
Exploring the evolution from AI to AI Agents with a hands-on FinOps example. Learn how AWS Strands enables autonomous agents to monitor cloud spend, notify on overages, and free humans to focus on higher-judgment work.