DeepLearning.AI's Building Systems with the ChatGPT API teaches you to build multi-step AI pipelines: classification chains, evaluation systems, and customer service bots using the OpenAI API. The course is free on deeplearning.ai and takes about 2 hours. After finishing, you can chain prompts together to build real applications that go beyond a single API call. It assumes you already know basic prompt engineering. The main limitation: it uses the OpenAI API specifically; you'll need to adapt the patterns for other models like Claude or Gemini.
DeepLearning.AI's courses have been taken by over 6 million learners across its platform and Coursera (source: deeplearning.ai/about/).
About This Course
Learn to build multi-step LLM systems for real production use. Covers chaining calls, moderation, evaluation, and end-to-end pipelines with the OpenAI API. Taught by Andrew Ng and Isa Fulford of OpenAI. Free.
Course Details
Frequently Asked Questions
Is this course free?
Yes, free on deeplearning.ai. No subscription required.
Should I take prompt engineering first?
Yes. Take DeepLearning.AI's Prompt Engineering for Developers first; this builds on that foundation.
What applications can I build?
Customer service bots, content moderation pipelines, structured data extractors, and multi-step reasoning systems.
Does it teach error handling and evaluation?
Yes. Evaluating LLM outputs and handling failures is one of the course's main topics.
How long does this take?
About 2 hours of interactive lessons.
More generative-ai Courses
freeCodeCamp's comprehensive introduction to generative AI covering the OpenAI API, Gemini Pro, LangChain, RAG basics, and building real AI-powered apps. Completely free on YouTube.
Harvard's introduction to AI with Python. Covers search, knowledge representation, uncertainty, optimisation, machine learning, neural networks, and NLP.
fast.ai's legendary course on deep learning for practitioners. Takes a top-down approach — you build real models in lesson 1 and understand the theory gradually. Covers CV, NLP, tabular data, and stable diffusion. Completely free.