Slate
Explore
Tracks
History
Pricing
Start session
All tracks
Computer Science
Prompt engineering, honestly
What actually works when steering a large model — past the tricks, into the real craft.
6 lessons
~80 min total
Natural
What you'll learn
Write prompts that get reliable, useful behavior out of modern models
Know which 'tricks' still matter and which are cargo-culted
Debug a flaky prompt instead of just adding adjectives
Progress
0 / 6
Track complete ✓
Lessons
1
A mental model for prompting
You're not casting spells — you're conditioning a very big function.
3 objectives
2
Clarity beats cleverness
The boring rule that outperforms most 'techniques'.
3 objectives
3
Few-shot examples, properly
When they help, when they hurt, and what makes a good one.
3 objectives
4
Structure the output
Schemas, JSON mode, and why they change everything downstream.
3 objectives
5
Reasoning prompts that still matter
Chain-of-thought, self-consistency, and the modern reality.
3 objectives
6
Debugging a flaky prompt
Systematic fixes beat 'add more adjectives'.
3 objectives
Related tracks
How LLMs actually work
From tokens to transformers to the training loop — what's really happening when a model responds.
7 lessons
SLATE
Software architecture
Why real systems are shaped the way they are — monoliths, services, databases, caches, queues, and the tradeoffs behind each.
8 lessons
SLATE
How the internet actually works
What happens between typing a URL and the page appearing — packets, DNS, TCP, TLS, the works.
8 lessons
SLATE