← Tech Station
02 — Core skill

Prompt Engineering

Zero-shot to few-shot, chain-of-thought, and structured output patterns.

13 guides in this track·1.1h reading·Beginner → Intermediate
What you'll learn

Move from "prompts that work sometimes" to prompts you can put in production — structured, tested, versioned, and cheap enough to run at scale.

Who this is for

Anyone whose product depends on an LLM output being correct: engineers wiring model calls, PMs writing spec, and analysts using models to think faster.

How to use it

The guides are numbered — read in order for the curriculum path, or jump straight to the one you need. Each card is self-contained.

The guides

Ordered by recommended reading path
01
What Is Prompt Engineering (and Why Wording Actually Works)

Why prompts shift outputs, tied back to next-token prediction.

5 minRead →
02
Anatomy of a Prompt: Role, Task, Context, Format

The universal prompt skeleton.

5 minRead →
03
Zero-Shot, Few-Shot & In-Context Learning

Showing vs telling; when examples beat instructions.

5 minRead →
04
Chain-of-Thought: Making Models Reason

Forcing intermediate steps to improve accuracy.

5 minRead →
05
The 7 Prompt Patterns That Cover 90% of Cases

The consolidated pattern toolkit.

5 minRead →
06
Chain-of-Thought vs Tree-of-Thought

Linear vs branching reasoning and when each wins.

5 minRead →
07
Structured Output: Reliable JSON Every Time

Schemas, JSON-only, validation and retries.

4 minRead →
08
Delimiting Context & Prompt-Injection Basics

Separating instructions from data; first security awareness.

5 minRead →
09
System Prompts & Persona Design

Setting durable behaviour and voice.

5 minRead →
10
Reducing Hallucination Through Prompting

Grounding, say-I-don't-know, uncertainty handling.

5 minRead →
11
Prompt Chaining & Task Decomposition

Breaking big tasks into linked prompts.

5 minRead →
12
Evaluating & Iterating on Prompts

Test cases, comparison, avoiding tuning by vibes.

5 minRead →
13
Prompt Engineering in Production

Versioning, testing, treating prompts as deployable artifacts.

5 minRead →

Related tracks

Continue in the same group
01 — Start hereAI PrimerThe concepts every LLM practitioner needs before writing a single prompt.03 — ArchitectureRAGChunking, embeddings, vector search, and fixing hallucinations in production.04 — LLMOpsLLM Fine-Tuning & LLMOpsWhen to fine-tune vs. prompt, LoRA, QLoRA, evaluation, and deployment.05 — AdvancedAgentic AIPlanning loops, tool use, memory, and multi-agent coordination.