Prompt Engineering with Python & the OpenAI API

<div>The API is where real applications are built. This course is how you get there.</div><div><br></div><div>This course is for Python developers who are ready to move from experimenting with AI to actually building with it. You'll work directly with OpenAI's modern Responses API — the one OpenAI recommends for all new projects — writing real code that connects to real tools and produces real results.</div><div><br></div><div>WHAT YOU'LL BUILD</div><div><ul><li><span style="font-size: 1rem;">You'll complete three capstone projects, each one closing out a module after the concepts that make it possible have been taught.</span></li><li><span style="font-size: 1rem;">Research Assistant — Decomposes complex questions into sub-questions, investigates each one independently, and synthesizes the findings into a structured answer. Built using instruction chaining, personas, and advanced few-shot techniques.</span></li><li><span style="font-size: 1rem;">Production Support Bot — A fully functional support chatbot with budget controls, sliding window context management, and response caching. Built incrementally across two modules to show how production systems are actually assembled — not just demonstrated in a single notebook.</span></li><li><span style="font-size: 1rem;">Multi-Tool Agent — Connects to a live weather API and queries a real SQLite database using function calling. This is AI that interacts with the outside world through Python functions.</span></li></ul></div><div><br></div><div>WHAT YOU'LL LEARN</div><div><ul><li><span style="font-size: 1rem;">API Fundamentals — Connect to the OpenAI API, configure your environment, and make your first calls using the Responses API. Understand model selection, token usage, and cost tracking from day one.</span></li><li><span style="font-size: 1rem;">Core Prompting — Zero-shot, one-shot, and few-shot prompting. Understand exactly how the model responds to different prompt structures and why it matters.</span></li><li><span style="font-size: 1rem;">Production Prompting — Structured JSON outputs for reliable parsing, error handling with exponential backoff, reusable prompt templates, and systematic prompt evaluation so you can measure whether your prompts are actually working.</span></li><li><span style="font-size: 1rem;">Advanced Prompting — Instruction chaining, role-based personas, advanced few-shot techniques, and self-consistency strategies for more reliable outputs.</span></li><li><span style="font-size: 1rem;">Production Patterns — Token counting and cost tracking with tiktoken, context window strategies for long conversations, and response caching to eliminate redundant API calls.</span></li><li><span style="font-size: 1rem;">Function Calling — The complete function calling workflow. Connect the AI to external tools, live APIs, and real databases so it can take actions in the world.</span></li></ul></div><div><br></div><div>HOW THE COURSE IS STRUCTURED</div><div><ul><li><span style="font-size: 1rem;">Six modules. 25+ hands-on Jupyter notebooks. Each concept is taught in its own notebook with working code you can run, modify, and reuse. Each module closes with a capstone that puts everything you just learned into a real, deployable application.</span></li></ul></div><div><br></div><div>PREREQUISITES</div><div><ul><li>Basic Python familiarity — classes, functions, loops, and importing packages. Environment setup is covered in Module 1.</li><li><span style="font-size: 1rem;">You'll also need an OpenAI account with a minimum of $5 in API credit. That's more than enough to complete every exercise in the course using gpt-5-mini, the default model used throughout.</span></li></ul></div><div><br></div><div>WHO THIS COURSE IS FOR</div><div><ul><li><span style="font-size: 1rem;">Engineers adding AI capabilities to existing applications. Analysts automating workflows with Python. Technical leads evaluating how to integrate AI into their teams' work.</span></li></ul></div><div><br></div><div>WHO THIS COURSE IS NOT FOR</div><div><ul><li><span style="font-size: 1rem;">Complete beginners to Python. If you're new to Python, build that foundation first — you'll get significantly more out of this course when you come back.</span></li></ul></div>

What you'll learn:

• Connect to the OpenAI Responses API and make your first live API calls from Python
• Build structured JSON outputs that return reliable, parseable results every time
• Handle API errors gracefully using exponential backoff and rate limit strategies
• Design reusable prompt templates with roles, instructions, examples, and output format controls
• Track token usage and costs in real time using tiktoken and the API usage object
• Implement response caching and context window strategies for production applications
• Connect the AI to external tools and databases using the complete function calling workflow
• Build three real AI applications — a Research Assistant, Production Support Bot, and Multi-Tool Agent