Part IV
Deciding whether to adopt
What the cases support across them, and how to weigh a system against the simple alternative.
Chapters
- 4.1
Comparing decision systems
Across reviews, complaints and agent work, the choice between an endpoint and a trained classifier turns on how many labels a task needs and whether the probabilities are calibrated, and an agent's work improved most when a check it could not influence named what had failed.
DraftRecordsamazon-reviews-2023cfpb-complaintsswe-rebenchconstructed-patchesconstructed-agent-tasks