Agentic AI in Practice: Designing and Testing AI Agents

Mentor

Bharat is a Lead QA/SDET who designs and leads testing strategies for modern web and AI‑driven applications, specialising in Playwright, Cypress, JMeter, and automation frameworks. His recent focus is on agentic QA—testing intelligent agents and AI systems that make autonomous decisions.

What you'll learn

• What “agentic AI” means in real products and how agents differ from simple chatbots or single‑call LLM apps.
• How to break down a problem into tools, actions, and workflows that an AI agent can execute.
• Patterns for safely testing and validating agents: prompts, tools, state, failure modes, and regressions.
• How to use modern test automation tools and strategies to evaluate reliability, performance, and edge cases of agentic systems.
• Practical guidelines for logging, observability, and feedback loops so agents can be improved over time.