Tag
The essence of Loop Engineering is not having agents run more iterations, but systematizing the second-order management operations of humans managing AI—through evaluation, observability, SOP/skills, maker/checker, and real data feedback—so that the system manages itself.
At the Anthropic conference, Fiona Fung shared insights on managing engineering teams in the age of AI. She pointed out that as the cost of code generation decreases, the bottleneck has shifted to verification and collaboration, recommending the reduction of legacy processes and the strengthening of automated quality assurance.