Five engineers and their AI coding agents rebuilt the x.com web app in under six months. “Never rewrite from scratch” used to be gospel, but when writing code gets cheap, the hard part moves to the plan and the rollout. Here’s how that played out when I chose to build the Calendrz mobile apps natively, twice.
Ben Congdon splits software into interpolative (agents nail it from a few sentences) and novel (fighting uphill). Building Calendrz showed me exactly where that line runs, and why the bits you have to explain are the ones worth building.
A founder rebuilt his whole platform alone with Claude Code, and his tests stayed green for weeks around a pigeon that never existed. When the agent writes the code and the tests, green proves less than you think: here’s what I’d check on Monday morning.
Sentry’s David Cramer argues prompts are rarely the way to make AI agents behave. I agree: the rules that matter belong in code, as I learnt building Calendrz.
A malicious AGENTS.md file in a Downloads folder tricked coding agents into installing a rogue package. Why instruction files are code now, what I’d ask engineering teams to change this week, and how Calendrz treats the emails its own agent reads.
Engineering leaders say AI agents write code much faster, yet their release cycles are no faster than before. Typing was never the bottleneck: here’s where the time really goes, and what I’d change about review and verification.
This will close in 30 seconds