Prompt Engineering and LLM Application Patterns

28 lessons in AI Fundamentals

• Prompt Chaining and Multi-Step PipelinesSlides / Video
• Tool Use and Function CallingSlides / Video
• Grounding Responses with External ContextSlides / Video
• Retrieval-Augmented Generation (RAG)Slides / Video
• Prompt Injection and Security RisksSlides / Video
• Prompt Failure Modes and HallucinationsSlides / Video
• Iterative Prompt Refinement and TestingSlides / Video
• Decoding Parameters: Temperature, Top-p, Max TokensSlides / Video
• Controlling Output Format with LLMsSlides / Video
• Prompt Templating and Variable InjectionSlides / Video
• System, User, and Assistant RolesSlides / Video
• Role and Persona PromptingSlides / Video
• Chain-of-Thought Prompting for ReasoningSlides / Video
• Few-Shot Prompting and In-Context LearningSlides / Video
• Zero-Shot PromptingSlides / Video
• Anatomy of a PromptSlides / Video
• What Prompt Engineering IsSlides / Video
• Cost and Latency in LLM AppsSlides / Video
• Evaluating LLM Outputs and Prompt QualitySlides / Video
• Self-Consistency and Output VerificationSlides / Video
• Context Window and Token LimitsSlides / Video
• Agentic Loops and ReAct PatternSlides / Video
• Returning Tool Call ResultsCode Quiz
• ReAct Reasoning-Action LoopCode Quiz
• Context Window Token BudgetingCode Quiz
• Self-Consistency VotingCode Quiz
• Conversation History TruncationCode Quiz
• Prompt Injection DetectionCode Quiz