Customizing Models

From prompt engineering to fine-tuning to building autonomous agents.

Concepts 6
Total time ~62 min
  1. Step 1

    Prompt Engineering Basics

    Learn the core techniques for writing effective prompts: system messages, few-shot examples, and structured instructions.

    beginner 7 min read
  2. Step 2

    Fine-Tuning vs Prompt Engineering

    Learn when to shape an LLM with prompts versus when to change its behavior with fine-tuning, and the trade-offs of each.

    intermediate 10 min read
  3. Step 3

    PEFT (LoRA) and Fine-Tuning Recipes

    Learn why LoRA-style parameter-efficient tuning is the default in practice and how to choose robust fine-tuning recipes.

    intermediate 11 min read
  4. Step 4

    Instruction Tuning, RLHF, and DPO

    Trace how base models become assistants through supervised instruction tuning and preference optimization methods like RLHF and DPO.

    advanced 12 min read
  5. Step 5

    Tool Use / Function Calling

    Understand how models call external code safely and reliably using structured outputs, validation, and execution boundaries.

    intermediate 10 min read
  6. Step 6

    Agents: Planning, Tool Orchestration, and Guardrails

    Learn how LLM agents execute multi-step workflows with planning, tool loops, recovery logic, and safety boundaries.

    advanced 12 min read