Learn how an AI Assistant is built to use and accomplish tasks on computers.

Building toward Computer Use with Anthropic

Learn to break down complex tasks, automate workflows, chain LLM calls, and get better outputs from LLMs. Evaluate LLM inputs and outputs for safety and relevance.

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

Building Systems with the ChatGPT API

Learn how to evaluate the safety and security of your LLM applications and protect against risks. Monitor and enhance security measures to safeguard your apps.

Monitor and enhance security measures over time to safeguard your LLM applications. Monitor and enhance security measures over time to safeguard your LLM applications.Detect and prevent critical security threats like hallucinations, jailbreaks, and data leakage. Detect and prevent critical security threats like hallucinations, jailbreaks, and data leakage.Explore real-world scenarios to prepare for potential risks and vulnerabilities. Explore real-world scenarios to prepare for potential risks and vulnerabilities._It’s always crucial to address and monitor safety and quality concerns in your applications. Building LLM applications poses special challenges.In this course, you’ll explore new metrics and best practices to monitor your LLM systems and ensure safety and quality. You’ll learn how to: Identify hallucinations with methods like SelfCheckGPT Detect jailbreaks (prompts that attempt to manipulate LLM responses) using sentiment analysis and implicit toxicity detection models.Identify data leakage using entity recognition and vector similarity analysis.Build your own monitoring system to evaluate app safety and security over time.Upon completing the course, you’ll have the ability to identify common security concerns in LLM-based applications, and be able to customize your safety and security evaluation tools to the LLM that you’re using for your application. _Anyone with basic Python knowledge interested in mitigating issues like hallucinations, prompt injections, and toxic outputs. 

Quality and Safety for LLM Applications

Learn LLMOps best practices as you design and automate steps to fine-tune and deploy an LLM for a specific task.

Adapt an open source pipeline that applies supervised fine-tuning on an LLM to better answer user questions. Adapt an open source pipeline that applies supervised fine-tuning on an LLM to better answer user questions.Learn best practices, including versioning your data and your models, and pre-process large datasets inside a data warehouse. Learn best practices, including versioning your data and your models, and pre-process large datasets inside a data warehouse.Learn responsible AI by outputting safety scores on sub-categories of harmful content. Learn responsible AI by outputting safety scores on sub-categories of harmful content._In this course, you’ll go through the LLMOps pipeline of pre-processing training data for supervised instruction tuning, and adapt a supervised tuning pipeline to train and deploy a custom LLM. This is useful in creating an LLM workflow for your specific application. For example, creating a question-answer chatbot tailored to answer Python coding questions, which you’ll do in this course.Through the course, you’ll go through key steps of creating the LLMOps pipeline:Retrieve and transform training data for supervised fine-tuning of an LLM.Version your data and tuned models to track your tuning experiments. Configure an open-source supervised tuning pipeline and then execute that pipeline to train and then deploy a tuned LLM.Output and study safety scores to responsibly monitor and filter your LLM application’s behavior.Try out the tuned and deployed LLM yourself in the classroom!Tools you’ll practice with include BigQuery data warehouse, the open-source Kubeflow Pipelines, and Google Cloud. _Anyone who wants to learn to tune an LLM, and learn to work with and build an LLMOps pipeline.

LLMOps

Learn best practices for prompting and selecting among Meta Llama 2 & 3 models. Interact with Meta Llama 2 Chat, Code Llama, and Llama Guard models.

Learn best practices specific to prompting Llama 2 & 3 models. Learn best practices specific to prompting Llama 2 & 3 models.Interact with Meta Llama 2 Chat, Code Llama, and Llama Guard models. Interact with Meta Llama 2 Chat, Code Llama, and Llama Guard models.See how you can build safe, responsible AI applications using the Llama Guard model. See how you can build safe, responsible AI applications using the Llama Guard model._Open up your prompt engineering to the Llama 2 & 3 collection of models! Learn best practices for prompting and building applications with these powerful open commercial license models.Interact with the Llama 2 and Llama 3 models with a simple API call, and explore the differences in output between models for a variety of tasks.What you’ll do: Learn best practices for prompting and selecting among the Llama 2 & 3 models by using them as a personal assistant to help you complete day-to-day tasks.Experiment with advanced prompt engineering techniques, like few-shot prompting to get Llama 2 to classify the sentiment of text messages, and chain-of-thought prompting to solve logic problems.Treat Code Llama as a pair programming partner to both learn to write and improve code.Promote safe and responsible use of LLMs by having Llama Guard check user prompts and model responses for harmful content.Llama 2 and Llama 3 models and model weights are free to download, including quantized model versions that can run on your local machine. Join a thriving community of open source developers that is building applications powered by Llama 2 and Llama 3._Anyone who is interested in learning prompt engineering and wants to try out Meta Llama 2 and Llama 3 models.

Prompt Engineering with Llama 2&3

Learn how to make safer LLM apps through red teaming. Learn to identify and evaluate vulnerabilities in large language model (LLM) applications.

Learn to identify and evaluate vulnerabilities in large language model (LLM) applications. Learn to identify and evaluate vulnerabilities in large language model (LLM) applications. Apply red teaming techniques from cybersecurity to ensure the safety and reliability of your LLM application. Use an open source library from Giskard to help automate LLM red-teaming methods._Learn how to test and find vulnerabilities in your LLM applications to make them safer. In this course, you’ll attack various chatbot applications using prompt injections to see how the system reacts and understand security failures. LLM failures can lead to legal liability, reputational damage, and costly service disruptions. This course helps you mitigate these risks proactively. Learn industry-proven red teaming techniques to proactively test, attack, and improve the robustness of your LLM applications.In this course:Explore the nuances of LLM performance evaluation, and understand the differences between benchmarking foundation models and testing LLM applications.Get an overview of fundamental LLM application vulnerabilities and how they affect real-world deployments.Gain hands-on experience with both manual and automated LLM red-teaming methods.See a full demonstration of red-teaming assessment, and apply the concepts and techniques covered throughout the course.After completing this course, you will have a fundamental understanding of how to experiment with LLM vulnerability identification and evaluation on your own applications._Red Teaming LLM Applications is a beginner-friendly course. Basic Python knowledge is recommended to get the most out of this course.

Red Teaming LLM Applications

Move your LLM-powered applications beyond proof-of-concept and into production with the added control of guardrails.

Learn the common failure modes of LLM-powered applications that guardrails can help mitigate, including hallucinations and revealing sensitive information. Learn the common failure modes of LLM-powered applications that guardrails can help mitigate, including hallucinations and revealing sensitive information.Understand how AI guardrails validate and verify your applications with input and output guards, ensuring reliable and controlled interactions. Understand how AI guardrails validate and verify your applications with input and output guards, ensuring reliable and controlled interactions.Add guardrails to a RAG-powered customer service chatbot to create a new layer of control of the applications behavior. Add guardrails to a RAG-powered customer service chatbot to create a new layer of control of the applications behavior._Join our new short course, Safe and Reliable AI via Guardrails, and learn how to build production-ready applications with Shreya Rajpal, co-founder & CEO of GuardrailsAI.The output of LLMs is fundamentally probabilistic, making it impossible to know in advance, or to guarantee the same response twice. This makes it difficult to put LLM-powered applications into production for industries with strict regulations or clients who require high consistency in application behavior. Fortunately, installing guardrails on your system gives you an additional layer of control in creating safe and reliable applications. Guardrails are safety mechanisms and validation tools built into AI applications, acting as a protective framework that prevents your application from revealing incorrect, irrelevant, or sensitive information. This course will show you how to build robust guardrails from scratch that mitigate common failure modes of LLM-powered applications like hallucinations or revealing personally identifiable information (PII). You’ll also learn how to access a variety of pre-built guardrails on the GuardrailsAI hub and are ready to integrate into your projects.You’ll implement these guardrails in the context of a RAG-powered customer service chatbot for a small pizzeria.In detail, you’ll: Explore the common failure modes of LLM-powered applications including hallucinations, going off-topic, revealing sensitive information, and generating responses that can harm your reputation.Learn to mitigate these failure modes with input and output guards that validate and verify your application’s responses.Create a guardrail to prevent the chatbot from discussing sensitive topics, such as a confidential project at the pizza shop.Develop a guardrail to detect hallucinations using a Natural Language Inference (NLI) model, ensuring responses are grounded in the truth of your trusted documents.Add a Personal Identifiable Information (PII) guardrail to detect and redact sensitive information in user prompts and LLM outputs using tools from the Guardrails hub.Set up a guardrail to limit the chatbot’s responses to topics relevant to the pizza shop, keeping interactions focused and appropriate.Configure a guardrail that prevents your chatbot from mentioning any competitors using a name detection pipeline consisting of conditional logic that routes to an exact match or a threshold check with a named entity recognition.The tools in this course will unlock more opportunities for you to build and deploy safe, reliable LLM-powered applications ready for real-world use._Anyone who has basic Python knowledge looking to enhance the safety and reliability of LLM-powered applications with practical, hands-on guardrail techniques.

Safe and reliable AI via guardrails

Learn to build with LLMs by creating a fun interactive game from scratch.

Learn LLM app development by designing and developing a text-based AI game, creating immersive game worlds, characters, and storylines through hierarchical content generation.  Learn LLM app development by designing and developing a text-based AI game, creating immersive game worlds, characters, and storylines through hierarchical content generation. Learn to implement game mechanics using AI to convert text data into structured JSON outputs, enabling features like an inventory detection system. Learn to implement game mechanics using AI to convert text data into structured JSON outputs, enabling features like an inventory detection system.Learn to enforce safety and compliance for AI content creation, and create custom policies using Llama Guard. Learn to enforce safety and compliance for AI content creation, and create custom policies using Llama Guard._Join our new short course, Building an AI-Powered Game, with Together AI and AI Dungeon! Learn from Niki Birkner, Senior Product Manager at Together AI, and Nick Walton, CEO and Co-Founder of Latitude.This course teaches you how to build a LLM-based application by creating your own AI-powered text-based game. You’ll create a world with hierarchical content generation based on a prompt, setting up its core mechanics, and giving it a simple Gradio user interface. By the end of this course, you’ll have a playable text-based game to share with your friends, built from scratch using LLMs. You will be guided through the building blocks of app development using LLMs, including incorporating safeguards using Llama Guard. What you’ll do: Use prompt engineering to create a world with hierarchical content generation so your narrative is consistent and the AI can flesh out your game.Build the first version of your game with a user interface, load the world, and define the core action loop of the game, so you can have a game to play and interact with.Implement safe user-dependent and context-dependent guardrails into your game application with Llama Guard and custom content policy.Learn LLM tool calling by adding story and state components that improve your game’s memory, track inventory, and show progress.  With these techniques, you’ll hone your AI skills by building your own sharable game! _Anyone who has basic Python knowledge and wants to learn how to build with LLMs in a hands-on, fun way!