GuideIntermediate
Advanced Prompt Engineering Guide
Master the prompt engineering techniques that separate casual LLM users from production AI engineers: zero-shot and few-shot patterns, Chain-of-Thought reasoning, ReAct, Self-Consistency, prompt composition, systematic evaluation, and production prompt management with versioning, caching, and cost optimization.
- 64
- lessons
- 8
- modules
- English · Spanish
- available in
- Yes
- certificate
- Free
- access
Outcomes
What you'll be able to do
- Design prompts systematically using structured frameworks, not intuition
- Master zero-shot and few-shot prompting with example engineering and boundary testing
- Obtain reliable structured outputs (JSON, Pydantic schemas) across multiple providers
- Implement Chain-of-Thought reasoning with verification patterns for math, logic, and code
- Apply ReAct (Reasoning + Acting), Self-Consistency, and Tree-of-Thought for complex tasks
- Compose multi-stage prompt pipelines with chaining, decomposition, and context management
- Evaluate prompts with quantitative metrics: LLM-as-judge, regression testing, A/B testing
- Manage prompts in production: versioning, caching, cost optimization, monitoring, and deployment
Before you start
What you need to bring
It's for you if...
- AI Engineers who use LLMs in production and need consistent, evaluable prompts
- Python developers building applications with OpenAI/Anthropic who want to go beyond ad-hoc prompting
- Backend engineers integrating LLMs into existing systems that require structured, reliable outputs
- Engineers who completed LangChain & LangGraph and want to master the prompting layer
- Anyone preparing for AI Engineering roles where prompt design is a core competency
Requirements and materials
- Intermediate Python (functions, classes, basic async/await)
- Experience calling LLM APIs (OpenAI, Anthropic, or similar)
- Familiarity with REST APIs and JSON
- At least one LLM API key (OpenAI recommended, Anthropic optional)
- Python 3.11+ installed
Content
The syllabus, module by module
Open any of them to see its lessons.
- 1. Introduction: Prompt Engineering as a Discipline
- 2. Anatomy of a Prompt
- 3. Roles: system, user, assistant
- 4. Temperature and Generation Parameters
- 5. Mental Models for Designing Prompts: CRISPE
- 6. Comparison: Casual Prompt vs Engineered Prompt
- 7. Providers and Behavioral Differences
- 8. Project: Prompt Analyzer
- 1. Introduction: The Two Fundamental Techniques
- 2. Zero-Shot Prompting Patterns
- 3. Few-Shot: Choosing Examples
- 4. Advanced Few-Shot: Example Engineering
- 5. Output Formatting and Parsing
- 6. Boundary Testing and Edge Cases
- 7. Zero-Shot vs Few-Shot: Decision Framework
- 8. Project: Few-Shot Classification System
- 1. Introduction: Why LLMs Need to Think Step by Step
- 2. Zero-Shot CoT: "Let's Think Step by Step"
- 3. Manual CoT: Designing Reasoning Chains
- 4. CoT for Specific Tasks
- 5. Verification Patterns in CoT
- 6. Multi-Step Reasoning Pipelines
- 7. Limitations and Anti-Patterns of CoT
- 8. Project: Reasoning Engine with Verifiable CoT
Where it fits
This guide is part of something bigger
It's studied inside these programs, with support and dates.
Common questions
What people usually ask
No limit. It's a free guide: come in whenever you like, as often as you like.
No. Modules run from easier to harder, but you can jump to the one you need. Progress is saved per lesson.
Whatever is needed is listed under “What you need to bring”, above. If nothing is listed there, you can start from zero.
In the Club's WhatsApp group, and every two weeks there's a live with an instructor where questions get worked through.
Yes. It's issued automatically once you finish every lesson, with a verifiable code you can share on LinkedIn.
No. This guide is self-paced with no dates. The bootcamp is live, by cohort, with work someone reviews.
Start whenever you like
What students say
These reviews are from enrolled students who completed at least 50% of the course. We moderate reviews only on content grounds (spam, offensive language, personal data), never for being critical or negative.
No approved reviews yet.
Be the first to share your experience!