ANAlpesh Nakrani
SolutionsBlogBooksPraiseAboutWork with me
All books
Human in the Loop Is Not a Plan cover
Cover preview Page 1 of 87
Free PDF/The AI-Native Canon

Human in the Loop Is Not a Plan

Designing evaluation that scales with autonomy

A book by Alpesh Nakrani

Subscribe to get the complete book. Your PDF downloads immediately.

Pages
87
Chapters
8
Format
PDF · 18.9 MB
01/Overview

What's in the book

Putting a human in the loop feels safe and scales terribly. The reviewer becomes the bottleneck, then a rubber stamp, then a liability. This book is about building evaluation that keeps pace with autonomy: sampling, escalation, and the small set of decisions a person should never delegate.

'A human reviews it' is where most AI systems quietly fail. What real evaluation looks like when the machine outpaces the reviewer.

EvalsAgents
02/Inside the PDF

Table of contents

PDF page
  1. FMFront Matter: Human in the Loop Is Not a Plan
  2. 01The Review Queue Collapse13
  3. 02Human in the Loop Is an Incomplete Sentence20
  4. 03The LOOP-SAFE Framework28
  5. 04Risk-Tiered Review and the Capacity Math35
  6. 05Rubrics, Calibration, and Disagreement44
  7. 06Sampling, Evals, and Continuous Learning52
  8. 07Autonomy Boundaries and Evaluation Strength60
  9. 08The Operating System for Scalable Oversight68
  10. ENDConclusion: Design the Loop or Remove the Claim76
  11. AAppendix A: Source Index79
  12. BAppendix B: Glossary82

The full chapters, illustrations, and reference material are included in the downloadable PDF.

Read it at your own pace

Your next read, ready to download.

87 pages. The complete edition. Free with your subscription.

Download free PDF

Ask AI about Human in the Loop Is Not a Plan — Free PDF