Agents
Agents need an undo button before they need more autonomy
An agent that is right 97% of the time still makes dozens of wrong moves a day. Reversibility, not accuracy, makes that tolerable. An argument, with a pattern.
Independent · Applied AI · Since 2024
Plain notes on building with AI, one feature at a time
Warm Start publishes slow, careful writing for engineers, PMs and designers who ship AI features. Fewer predictions, more worked examples you can check on a Tuesday afternoon.
Latest from the desk
Browse by topic
- Cost and latency4Token math, caching, time to first token and the budgets that decide whether a feature survives its first invoice.Browse
- Evals3Test suites, graders and regression checks for model-backed features, and what each kind of check can and cannot catch.Browse
- Agents3Tool-using systems that take actions, and the guardrails, undo paths and review steps they need.Browse
- Product and design3Interfaces, expectations and feedback loops for AI features people use every day.Browse
- Field reports3Hands-on tests and postmortems from real setups, with the numbers we measured and the mistakes we made.Browse
- Retrieval and RAG2Chunking, embeddings, indexes and the quiet ways retrieval-augmented answers change over time.Browse
Get the next issue before your next sprint
One essay every other Thursday on evals, retrieval, agents, latency or cost, with the arithmetic shown and the code attached.
Free · No sponsored posts · 18,400 readers