Engineering Agent Feedback Loops

View at publisher Summarise with VIRAT
Authors: Dhivya Nagasubramanian
Cited by: 0
References: 6

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

We have come a long way in this book on AI techniques, introduction to transformer that gave birth to different large language models, prompting, building agents with different design patterns through different frameworks. Now that we are comfortable building agents, in the upcoming chapters, we will get to know how to make an agentic solution deployable and reliable in a production environment. Here’s the thing that AI agents and humans have in common: if they don’t have feedback, they don’t really grow—they just repeat themselves. You can get away with that in a polished demo where the world is neat and predictable. But outside the demo? Life is messy. Customers phrase things in ways you didn’t anticipate, markets swing, and policies shift with little warning. An agent that can’t listen, adjust, and learn from those changes will eventually crack. It might not happen on day one, but the brittleness shows up when it matters most.

Fields of Study & Subjects

Artificial Intelligence Applications AI-based Problem Solving and Planning Topic Modeling

Publication details

Journal / source
Apress eBooks
Pages
305–333
Publication date
1 April 2026
Language
EN
Document type
Book chapter