Practitioner essays on building production software with AI agents.

You read Brooks. You read Fowler. You read The Phoenix Project and highlighted the good parts. Then you built something on Claude Code this weekend and realized your entire engineering organization is obsolete. Here is what building software actually looks like in 2026.

Every executive wants AI to magically modernize their 10 million line monolith. It won’t. Here’s what you actually need, and why you’ve been asking the wrong question for the last two years.

The old software heroes explain the last era. The loudest influencers explain the demo. The builders answering customers in public are the ones closest to the truth.

Your engineering team can now ship a feature a day. But your customers cannot absorb a feature a day. The new bottleneck is not building. It is receiving.

A synthetic user is an LLM agent calibrated to a real reader persona that can navigate your product, read your copy, and tell you what is wrong before a real customer does. Here is how to build them, where they break, and why your feedback loop is six weeks too long.