Prompt Chaining and Multi-Step Pipelines

Tool Use and Function Calling

Grounding Responses with External Context

Retrieval-Augmented Generation (RAG)

Prompt Injection and Security Risks

Prompt Failure Modes and Hallucinations

Iterative Prompt Refinement and Testing

Decoding Parameters: Temperature, Top-p, Max Tokens

Controlling Output Format with LLMs

Prompt Templating and Variable Injection

System, User, and Assistant Roles

Role and Persona Prompting

Chain-of-Thought Prompting for Reasoning

Few-Shot Prompting and In-Context Learning

Zero-Shot Prompting

Anatomy of a Prompt

What Prompt Engineering Is

Cost and Latency in LLM Apps

Evaluating LLM Outputs and Prompt Quality

Self-Consistency and Output Verification

Context Window and Token Limits

Agentic Loops and ReAct Pattern

Returning Tool Call Results

ReAct Reasoning-Action Loop

Context Window Token Budgeting

Self-Consistency Voting

Conversation History Truncation

Prompt Injection Detection

Tool Calling Schema Definition

Sequential Prompt Chaining

ReAct Pattern

Prompt Templates and Variables

Prompt Chaining and Decomposition

Negative Instructions and Constraints

Agent Orchestration Patterns

Tool/Function Calling Pattern

Message Roles in Chat APIs

Guardrails and Content Constraints

Anatomy of a Well-Structured Prompt

Delimiters and Input Isolation

Self-Consistency Sampling

Reducing Hallucinations

LLM-as-Judge Evaluation

Map-Reduce Summarization

Iterative Prompt Refinement

Controlling Response Length

Structured Output Control

Role and Persona Prompting

Token Efficiency in Prompt Design

Handling Ambiguity with Clarification

Grounding Instructions Against Hallucination

LLM-as-Judge Evaluation Prompt

Structured Output Constraint via Enum

Estimating Token Count for a Prompt

Retrying on API/Parse Failures

Top-K Similarity Retrieval

Assembling a RAG Prompt