GlossaryAuto-generated index of key terms and which lesson covers them. Term Lesson A Note on MCP 09. Function Calling A Prediction Machine 01. What Are LLMs A Test Dataset 11. Evals and Testing Asking for JSON in the Prompt 06. Structured Output Build the Prompt 08. RAG from Scratch Building a Simple Vector Search 07. Embeddings and Vector Search Building Good Eval Datasets 11. Evals and Testing Chain-of-Thought 05. Prompt Engineering Chunk 08. RAG from Scratch Cloud Providers 01. What Are LLMs Collecting the Full Response 04. Streaming Responses Constraining Output 05. Prompt Engineering Cosine Similarity 07. Embeddings and Vector Search Cost: Tokens Are Money 12. Cost Latency and Guardrails Counting Tokens with Ollama 02. Tokens and Context Windows Define a Tool 09. Function Calling Embed and Store 08. RAG from Scratch Error Handling 03. Talking to LLMs with Go Evaluating RAG 11. Evals and Testing Execute the Function 09. Function Calling Extracting Structured Data 06. Structured Output Few-Shot Prompting 05. Prompt Engineering Generate 08. RAG from Scratch Generating Embeddings with Ollama 07. Embeddings and Vector Search Giving the Agent Tools 10. Building an Agent Guardrails: What the System Should Never Do 12. Cost Latency and Guardrails Handling Failures 06. Structured Output How Streaming Works 04. Streaming Responses How They Generate Text 01. What Are LLMs Implementing the Tools 10. Building an Agent Input vs Output Tokens 02. Tokens and Context Windows Latency: Speed Matters 12. Cost Latency and Guardrails LLM-as-Judge 11. Evals and Testing Models You Can Run Locally 01. What Are LLMs Multi-Turn Conversations 03. Talking to LLMs with Go Multiple Tools 09. Function Calling Ollama's JSON Mode 06. Structured Output OpenAI Streaming Format 04. Streaming Responses OpenAI's Structured Output 06. Structured Output Parsing into Go Structs 06. Structured Output Practical Token Budgeting 02. Tokens and Context Windows Prompt Injection 12. Cost Latency and Guardrails Prompt Patterns That Work 05. Prompt Engineering RAG Pipeline 08. RAG from Scratch Reading a Stream in Go 04. Streaming Responses Reducing Cost 12. Cost Latency and Guardrails Retrieve 08. RAG from Scratch Returning Arrays 06. Structured Output Running the Agent 10. Building an Agent Scoring: Contains Check 11. Evals and Testing Security: You Are the Gatekeeper 09. Function Calling Send the Request 09. Function Calling Send the Result Back 09. Function Calling Switching to OpenAI 03. Talking to LLMs with Go System Prompts 05. Prompt Engineering Temperature 05. Prompt Engineering The Agent Loop 10. Building an Agent The Context Window 02. Tokens and Context Windows The Lost-in-the-Middle Problem 02. Tokens and Context Windows The Message Roles 03. Talking to LLMs with Go The Model Decides, You Execute 09. Function Calling The Ollama API 03. Talking to LLMs with Go The ReAct Pattern 10. Building an Agent The Three Production Concerns 12. Cost Latency and Guardrails Tracking Scores Over Time 11. Evals and Testing Training Phases 01. What Are LLMs Two Ways to Use RAG 08. RAG from Scratch Using Channels for Clean Separation 04. Streaming Responses Vector Databases 07. Embeddings and Vector Search What Can Go Wrong 10. Building an Agent What Happens When You Exceed It 02. Tokens and Context Windows What Is a Token 02. Tokens and Context Windows What Is an Agent 10. Building an Agent What Is an Embedding 07. Embeddings and Vector Search What Is RAG 08. RAG from Scratch What LLMs Are Bad At 01. What Are LLMs What Makes a Good Agent 10. Building an Agent What Production RAG Adds 08. RAG from Scratch What Prompt Engineering Is 05. Prompt Engineering When Not to Use an LLM 12. Cost Latency and Guardrails When to Use Embeddings 07. Embeddings and Vector Search Wrapping It in a Function 03. Talking to LLMs with Go You're Already Using Agents 10. Building an Agent Your First API Call 03. Talking to LLMs with Go