AI agents are moving from novelty to necessity — but building them safely, predictably, and observably requires more than clever prompts. This workshop gives developers a practical introduction to AI agent engineering using Embabel, with an emphasis on the habits, patterns, and mental models needed to design trustworthy agents in real systems.

Across two focused sessions, you’ll learn how to ground agents in strong domain models (DICE), design goal-driven behaviours (GOAP) and other planning approaches, enforce safety through invariants and preconditions, and make every action explainable through observability.

You’ll run and inspect a fully working reference agent, extend its domain, add new actions, and validate behaviour through explainable planning logs. You'll explore how to select and deploy models tuned to provide the best and most cost-effective agent behaviour for your users.

• By the end of this full day workshop, you’ll know how to:

• Build agents anchored in typed domain models

• Design composable, goal-oriented behaviours

• Use preconditions and invariants as safety guardrails

• Debug agents through explainability, not guesswork

• Extend an agent with new domain objects and actions without breaking existing flows

• Apply a repeatable habit stack for reliable agent engineering

Whether you’re designing workflow agents, platform automations, or domain-specific assistants, this workshop gives you the practical skills and engineering discipline to build agents that behave safely and reason predictably — fit for production, and even fit for regulated environments.