Part 2 — For the Developer

Ch. 13 — Securing the Model Layer

Prompt injection, hallucination, and non-determinism — compliance risks unique to LLM-based agents and how to mitigate them.

The model layer introduces risks that do not exist in traditional software. No compliance framework has a clause about prompt injection — but every framework cares about the consequences.

A rule-based system fails in ways you can enumerate. A conditional branch either executes or it doesn't. An API call either succeeds or returns an error code. The failure space is finite, and testing can cover most of it.

An LLM-based agent fails differently. It can be manipulated into taking actions you never intended. It can invent facts and act on them. It can produce different outputs from identical inputs on different days. These are not edge cases. They are properties of the system.

Platform Agentic

Compliance, governance, and accountability for teams building agentic AI systems.

Access the book — sign in with Google·LinkedIn