Each hallucination fix solves one problem and leaves four others open. AI agents hallucinate in five distinct ways: fabricating data when retrieval returns nothing, selecting wrong tools when descriptions overlap, ignoring business rules, failing on soft constraints, and bypassing hard requirements. Five layered defenses: Graph-based retrieval computes from structured data instead of guessing (zero fabrication). Semantic tool routing via protocol discovery replaces brittle keyword matching (correct selection without vector indexes). Database-driven rules updated in seconds without redeployment. STEER messages guide self-correction instead of hard failure (15 guests requested → agent adjusts to 10, informs user). Framework hooks block operations LLMs must never bypass. Walk away with layered defense covering all five failure modes, STEER pattern for self-correction, database-driven rules without redeployment, when to use hard hooks vs soft steering, and complete open-source demo with serverless infrastructure. Demonstrates 8 test scenarios covering fabrication, rule violations, edge cases - zero hallucinations.

Outline: • Your AI Agent Hallucinates in 5 Different Ways • Grounded Retrieval with Graph Queries • Semantic Tool Routing • Steering Rules + STEER Messages • Hard Hooks That Cannot Be Bypassed • Full Layered Defense Test • Resources + Q&A