A back-end engineer set out to redesign a React app with an AI agent and came out actually knowing React. The unlock wasn't the prompting, it was understanding the code well enough to steer it. As the cost of entry collapses, knowing the technology matters more, not less.
Analytics only shows the events you remembered to add, never the ones you forgot. Let Claude instrument features as it builds them, then run a skill that audits your tracking against your own docs and live data, flagging what's missing, noisy, or quietly broken.
17 lock-wait timeouts in two hours. The SELECT was doing exactly what it was supposed to. The problem was what InnoDB did silently in addition: a gap lock on the write path, invisible in logs, invisible in EXPLAIN, visible only in production.
Writing code by hand used to be the job. Soon it will be a hobby, like woodworking or growing your own veg. What a company pays for now is judgment: knowing what to build, catching the answer that looks right and isn't, deciding when it's good enough to ship.
A written style guide is a museum piece nobody enforces. An LLM changes that: it reads rules in plain prose and applies them on every pull request, reaching judgment calls no linter could express. The style guide stops being a document and becomes a runtime.
An autonomous email agent hit a missing script, spiralled through 25 pointless shell calls, then fabricated email content including a prompt injection, and acted on it. The fix is not more warnings. It is structural validation before the model ever sees the data.
Most architecture methods try to predict which failures will hit. Residuality Theory does the opposite: it throws random stressors at a design and keeps whatever survives. The randomness is the point, because resilience that depends on predicting the future is not resilience at all.
Hand two developers the same tool and you get opposite verdicts. 'Useless' is rarely a fact about the thing. It's a fact about the person holding it. The rare skill was never operating the tool. It's imagining the door a tool opens before the use is obvious.
AI is now a reader of your documentation. When context lives outside the repository, gaps appear and assumptions creep in. Moving documentation closer to the code makes the system easier to reason about, for people and for machines.
Senior engineers carry the front of every decision, every code review, every on-call shift. The peloton runs best when roles rotate. When the star eventually leaves, someone else needs to know what wind feels like.
Using Claude Code as the orchestrator and Codex as the engine gives you the best of both tools: Claude's UI, Codex's depth, and minimal Claude token spend. The economics only work when the task is big enough to justify two layers.
The bottleneck in software engineering has shifted from typing to understanding. As AI handles implementation, engineers who thrive will be those who recognise patterns, curate guardrails, and connect technical decisions to business outcomes.
Five types of documentation, five different AI leverage stories. The question isn’t whether to involve AI in your docs; it’s where each type belongs and how much maintenance you can hand off.
Pairing with an AI feels like pair programming. It isn't. There's one prior in the room, and it's trained to agree. This post makes the case for mob programming and spec-driven development as the structural fix.
Errors don't just happen; they land somewhere. Validation, generic, idempotent ignore, warning log, or Sentry: each routes failure to a different audience. Get the routing wrong and either engineers go blind to real bugs, or state corrupts silently.
