Engineering-Management

A Hacker News thread with 400+ comments captured what my senior engineer said quietly in our 1-on-1: AI coding agents are eating the creative, enjoyable parts of software engineering and leaving humans with the tedious review work. As a tech lead, I’m watching engagement scores drop while velocity metrics climb. Here’s what that tension actually looks like from the inside, and the three structural changes I’m trying to keep my team from checking out.

Simon Willison coined ‘agentic engineering’ to describe professional software engineers using AI coding agents like Claude Code and Codex. I ran my team through two sprints of structured agentic workflows. The productivity numbers look great — until you check the bug tracker three weeks later.

Ad-hoc AI usage creates inconsistency and hidden risk. Here’s how to build a practical standard: AGENTS.md, .cursorrules, prompt libraries, and review checklists — with real templates.

AI can help you prep for 1:1s by surfacing action items, recent PRs, and discussion topics. But there’s a line you shouldn’t cross: never let AI write your actual feedback.

Automating standup notes with AI seemed like a small quality-of-life win. It turned out to surface real questions about surveillance, trust, and what standup is actually for.

AI can write tests in seconds, but coverage numbers are lying to you. Here’s how tautological, implementation-coupled tests let a real bug survive for three weeks.

An AI-generated migration ran perfectly in dev. In production, it would have locked a large production table during business hours. What I learned the hard way about AI and database changes.

AI coding tools quietly moved from flat subscriptions to credit-based pricing. I tracked my small team’s actual spending for a quarter and found we were paying well over $300/month per developer instead of the advertised $20. Here’s the breakdown, the traps, and how we cut costs by 40% without losing productivity.

In 3 months my team evaluated 6 AI coding tools, switched primary tools twice, and lost an estimated over 100 engineer-hours to setup, configuration, and relearning. I finally enforced a 90-day moratorium on tool changes. Here’s what I learned about the real cost of chasing the next shiny AI tool.

I added CodeRabbit to our GitHub org on a Tuesday. By Friday, it had flagged 23 issues across 7 PRs — and my team thought I had secretly reviewed everything myself. After 30 days running four different AI PR review bots in parallel, here’s what actually caught real bugs versus what generated noise.