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

Everyone is learning how to build AI agents. Only a few know how to evaluate them. 

That's becoming a costly problem as agents move into production. They can call the wrong tools, get stuck in loops, make poor decisions, or become vulnerable to prompt injection attacks, all while appearing to work correctly. 

On June 27, Packt is hosting a live workshop that teaches the evaluation techniques leading AI teams use to test agent reliability, performance, and robustness before deployment. 

Evaluating AI Agents with Ammar Mohanna, PhD 

You'll learn how to evaluate: 
- Tool selection and planning quality 
- Agent trajectories and recovery 
- LLM-as-a-Judge systems 
- Adversarial attacks and prompt injection risks 

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.