Prompt Engineering Essentials
Learn prompt engineering by writing real prompts.
$ open "Write your first prompt"
The simplest possible loop. Hit Run, watch the agent save a file, then edit the prompt and try again.
checkpoints run as you work
✓ checkpoint passed, lab 2 unlocked
What you'll build
Curriculum
9 labs, about 1.5 h
- 1
Write your first prompt
The simplest possible loop. Hit Run, watch the agent save a file, then edit the prompt and try again.
3 min
Pro - 2
Vague vs specific
Write a specific prompt. Pin down count, length, and format so the output is predictable.
5 min
Pro - 3
The four elements of a prompt
Use instruction, input data, and output indicator to build a sentiment classifier in one prompt.
7 min
Pro - 4
Weak vs strong prompts
Diagnose a deliberately weak prompt. Name what's missing before you fix it.
8 min
Pro - 5
Clear instructions
Turn the vague one-liner into specific, constrained, unambiguous instructions.
10 min
Pro - 6
Add a role
Give the prompt a system-prompt persona that fits the task and sharpens its judgement.
8 min
Pro - 7
Multishot examples
Add 2–3 worked input→output examples so the model learns the shape from demonstration.
12 min
Pro - 8
XML structure
Wrap the prompt's sections in XML-style tags so the model gets unambiguous boundaries.
10 min
Pro - 9
Capstone: output format & before-after
Add an explicit output-format spec, then write a before-after comparison. Verifies the prompt now has a role, examples, XML tags, and a format spec.
15 min
Pro
What learners say
This course is meticulously designed, reflecting Elvis's deep expertise and attention to detail. The exercises are relevant, engaging, and challenging, making the learning process both enjoyable and highly effective.
Praveen
Senior Software Engineer at Google
Elvis expertly ties in the latest developments when answering questions, provides pointers to the foremost resources, and shares his experience working with many of the tools and frameworks out there.
Yevgeniy S. Meyer, Ph.D.
Chief Scientist at Gretel
The best prompt engineering course out there.
Taeha
AI Engineer at Marker Inc.
It was clear that Elvis was at the cutting edge of best practices. Not only did we learn about prompting techniques, but all the different tools used across the stack. I've already applied the learnings to R&D at our organization.
Hannah
Director of Clinical Product at Moneta Health
Your instructor
Elvis Saravia
Founder, DAIR.AI
Elvis founded DAIR.AI and wrote the Prompt Engineering Guide, one of the most widely used references on working with language models. He has worked at companies like Meta AI and Elastic, and specializes in AI agents, RAG, and harness engineering.
How labs work
Live workspace
You run the real tools in a browser workspace. Nothing to install.
Checkpoints
Each lab checks your files and output, then unlocks the next one.
Your work stays
The workspace persists between labs so you finish with a project.