Prompt Engineering for Developers
Reliable patterns, structured outputs and tool use
By Houssam Kodad
One-time purchase
€19.95
VAT included
where applicable
- Instant download after purchase
- Readable on any device
- Free updates to this edition
- Secure checkout
About this book
What's inside
Prompt engineering is less about clever wording and more about disciplined software design. This concise, example-driven book teaches developers the patterns that make LLM outputs reliable enough to build on: clear instructions, structured outputs, decomposition and tool use. You'll leave able to write prompts you can test, version and trust inside a real application.
What you'll learn
Skills you'll walk away with
- Write clear, testable instructions for an LLM
- Use roles, delimiters and examples effectively
- Get structured JSON outputs you can parse safely
- Decompose hard tasks into reliable steps
- Apply chain-of-thought and self-checking patterns
- Define tools and function calls cleanly
- Version, test and iterate on prompts like code
Table of contents
8 chapters-
01
Prompting as Software Design
- · Why prompts are interfaces
- · Determinism and variance
- · Treating prompts as code
-
02
Anatomy of a Good Prompt
- · Instructions and constraints
- · Roles and delimiters
- · Examples that help
-
03
Structured Outputs
- · Asking for JSON
- · Schemas and validation
- · Recovering from bad output
-
04
Decomposition and Chaining
- · Breaking down tasks
- · Prompt chains
- · Routing between prompts
-
05
Reasoning Patterns
- · Chain-of-thought
- · Self-consistency and checking
- · When reasoning hurts
-
06
Tool Use and Function Calling
- · Describing tools clearly
- · Argument validation
- · Handling tool errors
-
07
Reducing Hallucination
- · Grounding with context
- · Asking the model to abstain
- · Citations and verification
-
08
Testing and Iterating on Prompts
- · Small evaluation sets
- · Versioning and diffs
- · Measuring improvement
This is the full chapter list — exactly what you'll receive in the PDF.
More in AI & LLMs
Keep exploring this track
Building LLM-Powered Applications
Architecture, evaluation and guardrails for production
Retrieval-Augmented Generation in Production
Chunking, embeddings, vector search and reranking that actually work
Fine-Tuning and Adapting Open LLMs
LoRA, quantization and instruction tuning on your own data