Erik Schluntz and Barry Zhang, Anthropic,
agentsllm evaluationai engineeringproduct engineering
This is one of the cleanest public pieces on agent design because it separates workflows from agents and keeps repeating the uncomfortable production lesson: start simple, add autonomy only when the task needs it, and make the tool interface inspectable.
Worth keeping next to any agent architecture work because it gives language for the tradeoff. Agents can improve task performance, but they buy that with latency, cost, and new failure modes.