Learn How To Evaluate AI Agents In a Live Workshop on June 27th

AI Agents are getting deployed faster than most teams know how to evaluate them. 
An agent can produce the right answer and still fail in production. 

As agents move into production, teams are discovering that a working demo doesn't guarantee reliability. Agents can choose the wrong tools, get stuck in loops, produce poor outcomes, or become vulnerable to prompt injection attacks. 

That's why evaluation is quickly becoming a must-have skill for AI engineers. 

Join Ammar Mohanna (AI Engineer, Researcher, Educator, PhD in Edge Artificial Intelligence, Expert in Production AI & Agent Evaluation) on June 27 for a live, hands-on workshop: Agent Evals Bootcamp  

In this 4-hour interactive workshop, you'll learn how to evaluate agents across four critical layers: 
- Component behavior (tool selection, arguments, planning) 
- Agent trajectories (steps, loops, recovery, cost) 
- Outcome quality (rubrics, LLM-as-a-Judge, calibration) 
- Adversarial robustness (prompt injection and attack testing) 

You'll leave with reusable evaluation workflows, hands-on notebooks, a production-readiness framework, and a Packt-endorsed certificate. 

Exclusive for Dev List subscribers: $149.99 → $75 (50% Off) 

Use code: DEVLIST50 

Seats are limited and this offer ends with the Early Bird period.