You can access the distribution details by navigating to My Print Books(POD) > Distribution
AI agents make dozens of model calls per task, and sending every one to a frontier model gets expensive fast. This practical guide shows how to move most of that work to small language models without giving up reliability. Using a network-operations agent as a running case study, you’ll learn to profile an agent’s workload, build an evaluation harness you can trust, enforce structured outputs, fine-tune with LoRA and QLoRA, distill reasoning, route between small and large models, quantize for cheap deployment, and add guardrails for agents that touch real infrastructure. Every chapter includes runnable code, exercises, and an honest account of where small models fail.
Currently there are no reviews available for this book.
Be the first one to write a review for the book Small Models, Real Agents.