Skip to content

In progress

Generative AI in Production

Not another prompt-engineering guide. The book about the part that starts after the demo works — retrieval that drifts, agents that cannot be resumed, costs nobody budgeted, and the outage at 3am.

Coming to Amazon Kindle and paperback. Subscribers get the sample chapter first.

Get the sample chapter Read the articles it grew from

Chetan Karnatakam

Generative
AI in
Production

What happens after the demo works.

Draft cover

Contents

Eight chapters

  1. 01 Why the demo works and production does not
  2. 02 Retrieval: chunking, metadata and the quality metric nobody tracks
  3. 03 Agents that can be resumed, replayed and paid for
  4. 04 Evaluation you can run in CI
  5. 05 Cost, latency and the budgets that enforce themselves
  6. 06 Failure: providers, drift, and the fallback chain
  7. 07 Security and the permission boundary
  8. 08 Shipping it: MLOps, observability and the on-call story

Newsletter

The week in production AI

One email a week: what actually shipped, what broke, and what it means if you have an LLM system in production. No hype, no reposts, unsubscribe in one click.