About This Course
<div>In Red Teaming AI Apps with Promptfoo: RAG, Chatbots & Agents, you will learn how to systematically identify and test vulnerabilities using Promptfoo, an open-source framework for AI evaluation and red teaming.</div><div><br></div><div>This is a practical, application-focused course. Instead of working only with isolated prompts, we will attack a real AI-powered e-commerce application called EA SmartKart. The application includes an LLM-powered shopping assistant, product recommendations, shopping-cart operations, order information, RAG-based product retrieval, embeddings, and a vector database.</div><div><br></div><div>What you will learn</div><div><ul><li>Understand the fundamentals of AI red teaming and why traditional testing alone is insufficient</li><li><span style="font-size: 1rem;">Understand important OWASP risks for LLM-powered applications</span></li><li><span style="font-size: 1rem;">Install and configure Promptfoo from scratch</span></li><li><span style="font-size: 1rem;">Test real HTTP-based AI applications with Promptfoo</span></li><li><span style="font-size: 1rem;">Configure targets, providers, plugins, policies, strategies, graders, and assertions</span></li><li><span style="font-size: 1rem;">Write application-specific security and business policies</span></li><li><span style="font-size: 1rem;">Run single-turn and multi-turn attacks</span></li><li><span style="font-size: 1rem;">Use Meta Jailbreak, Hydra, and Crescendo strategies</span></li><li><span style="font-size: 1rem;">Test PII leakage, excessive agency, bias, hallucination, and business-rule violations</span></li><li><span style="font-size: 1rem;">Red team RAG applications for source attribution, context injection, and data poisoning</span></li><li><span style="font-size: 1rem;">Work with local LLMs as well as cloud-based model providers</span></li><li><span style="font-size: 1rem;">Analyze Promptfoo reports and understand why individual attacks pass or fail</span></li><li><span style="font-size: 1rem;">Build repeatable AI security tests suitable for regression testing and continuous evaluation</span></li></ul></div><div><span style="font-size: 1rem;">This course is designed for QA engineers, SDETs, automation engineers, developers, AI engineers, security testers, and anyone building or testing LLM-powered applications.</span></div><div><br></div><div>You do not need prior red-team experience. We start with the fundamentals and progressively move into real-world and advanced AI security testing.</div><div><br></div><div>If you want to move beyond simply asking whether an AI application works, and start asking how it can be broken, manipulated, or misused, this course will give you a practical path to doing exactly that.</div>
What you'll learn:
- Understand AI red teaming fundamentals and how Promptfoo tests RAG apps, chatbots, and AI agents.
- Configure Promptfoo targets, providers, plugins, policies, strategies, assertions, and red-team workflows.
- Run attacks for PII leakage, hallucination, excessive agency, hijacking, prompt injection, and policy violations.
- Test RAG applications for grounding, source attribution, indirect prompt injection, and knowledge-base poisoning.
- Use hosted and local red-team providers, including Promptfoo, MiniMax, and Ollama-based local LLMs.
- Generate, evaluate, and analyze Promptfoo red-team reports to identify and improve AI application security.