Each build here records who did what, and in the builds where agents wrote the code, the answer so far has been consistent: the making gets cheap, and the time moves to framing, deciding, accounts and checking. This thread runs from pair programming with ChatGPT and Cursor in 2025 to a team of agents with written rules and reviewers in 2026.
Building with agents
Where do a builder's time and judgement go when agents do the typing?
agentic engineering · multi-agent workflows · coding agents
Builds
- EXP-007Building · Pilot
This lab, rebuilt
Nothing goes live unread: building a public site with AI agents, without losing control
This lab, rebuilt in three days by Claude Code from briefs I worked out with Claude. The setup that keeps an agent-built site honest, and the rules that came from mistakes.
- EXP-004Live
emilysas.com
The bottleneck moved: where the time goes when an AI agent writes the code
A Claude agent wrote my professional site in about 42 hours, from first commit to the last launch change. The time went on accounts, decisions only I could make, and testing in production.
Notes
- A recipe for honest pictures: how to avoid AI image slop without copyright troubleinference cost · unit economics · token budgetsNote
- How I Used AI Pair Programming to Build a Robust Evaluation System (Without Vibe Coding)agentic engineering · multi-agent workflows · coding agents2025 post
- TinyLaunch Update: From Framer MVP to Full React Build — Lessons, Challenges & Next Stepsagentic engineering · multi-agent workflows · coding agents2025 post
- TinyLaunch Is ‘Launched’: From Framer to Fully-Coded Productproduct discovery · problem framing · build vs buy2025 post
- Trying (and Failing) to Send Emails from My Domainagentic engineering · multi-agent workflows · coding agents2025 post