What you'll learn

Efficiently build multi-step systems using large language models.
Learn to split complex tasks into a pipeline of subtasks using multistage prompts.
Evaluate your LLM inputs and outputs for safety, accuracy, and relevance.

Course recap

PRO

This course, taught by Andrew Ng and Isa Fulford (OpenAI), covers best practices for building complex applications that chain multiple LLM calls together. Using a running example of an end-to-end customer service assistant, it demonstrates how to classify inputs, check for problematic content, retrieve product information, generate responses, and validate outputs -- all as sequential steps invisible to the end user.

Concept map

Key concepts

Prompt EngineeringSystematic prompting for multi-step systems with different instructions per step
Chain of callsSequential LLM invocations where each step's output determines the next step's instructions
Input classificationCategorizing user queries (complaint, product inquiry, etc.) to route to appropriate processing
Content moderationChecking both inputs and outputs for problematic content (hateful speech, inaccuracy)
Evaluation and improvementIterative development process for maintaining and improving LLM-based systems

About this course

In Building Systems with the ChatGPT API, you will learn how to automate complex workflows using chain calls to a large language model. Unlock new development capabilities and improve your efficiency in this brand new short course.

You’ll build:

Chains of prompts that interact with the completions of prior prompts.
Systems where Python code interacts with both completions and new prompts.
A customer service chatbot using all the techniques from this course.

You’ll learn how to apply these skills to practical scenarios, including classifying user queries to a chat agent’s response, evaluating user queries for safety, and processing tasks for chain-of-thought, multi-step reasoning.

This one-hour course, taught by Isa Fulford (OpenAI) and Andrew Ng (DeepLearning.AI), builds on the lessons taught in the popular ChatGPT Prompt Engineering for Developers, though it is not a prerequisite.

Hands-on examples make each concept easy to understand. Built-in Jupyter notebooks allow you to seamlessly experiment with the code and prompts presented in the course.

In collaboration with OpenAI

We are thrilled to offer this course with OpenAI to support developers wanting to grow their skills using generative AI tools. This course reflects the latest understanding of best practices for getting the best performance out of LLM models, and doing so in a responsible way.

Who should join?

Building Systems With The ChatGPT API is beginner-friendly. You only need a basic understanding of Python to be able to complete the course. This course is also suitable for intermediate or advanced machine learning engineers who want to learn cutting-edge prompt engineering skills for LLMs.