Prompt Engineering
Get reliable, high-quality output from models. Learn proven prompting patterns, how to manage the context window as it fills up, and how prompt caching cuts latency and cost.
What you will be able to do
- Apply structured prompting patterns including chain-of-thought
- Manage context to avoid bloat, context rot, and lost-in-the-middle
- Use prompt caching to reduce latency and cost
Prompting Basics
BeginnerThe core techniques: clear instructions, examples, roles, output formats, and chain-of-thought. A small set of patterns covers most real needs.
45 min4 resources · 1 videoContext Handling
IntermediateA bigger context window is not free. Learn how models degrade when context is bloated, how relevant facts get lost in the middle, and how to engineer context deliberately.
40 min4 resources · 1 videoPrompt Caching
IntermediateWhen prompts share a large static prefix, caching lets the model reuse it, cutting cost and latency dramatically. Learn how to structure prompts to benefit.
25 min3 resources · 1 video
Put it to work
Apply what you learned by building real projects.
Test your thinking
Challenge yourself with scenario-based questions. Need 80% to mark complete.