Design, build, and deploy apps with an AI coding agent in an integrated web development environment. 

Build and share two applications—a website performance analyzer and a voting app—while using an AI coding agent to debug, customize, and strengthen your coding skills. Build and share two applications—a website performance analyzer and a voting app—while using an AI coding agent to debug, customize, and strengthen your coding skills.Learn the principles of agentic code development and skills to effectively build, host, and share your apps with Replit coding agents and assistants. Learn the principles of agentic code development and skills to effectively build, host, and share your apps with Replit coding agents and assistants.Use product requirement documents, wireframes, and good prompting practices to prototype, debug, and iterate your applications. Use product requirement documents, wireframes, and good prompting practices to prototype, debug, and iterate your applications._Learn to build and host applications with an AI agent in Vibe Coding 101 with Replit, built in partnership with Replit and taught by Michele Catasta, President, and Matt Palmer, Head of Developer Relations.Coding agents are changing how we write code. “Vibe coding” is a growing practice where you lean into letting a coding agent do most of the heavy lifting while you focus on the architecture and features of your application. But effective vibe coding isn’t just about one-shot prompting, accepting all recommendations, and hoping for the best. It involves structuring your work, refining your prompts, and using frameworks that lead to cleaner, more efficient code.In this course, you’ll use Replit’s cloud environment— with an integrated code editor, package manager, and deployment tools—to build and deploy two web applications with the help of an AI coding agent. Along the way, you’ll learn strategies for working effectively with agents and improve your development skills in the process.In detail, you’ll:Understand principles of agentic code development such as being precise, giving agents one task at a time, making prompts specific, keeping projects tidy, starting with fresh sessions for each new feature, and adopting patience while debugging.Learn how to get started with Replit, and understand fundamental concepts behind effective AI collaboration including a “five-skill framework” in vibe coding of thinking, using frameworks, checkpoints, debugging, and providing context.Create a product requirement document (PRD) and wireframe for your agent to build a prototype of a website performance analyzer.Use the agent to make your prototype more visually appealing, switch to assistant mode to customize your applications with screenshots and prompts, and deploy your application so others can access it online.Build a head-to-head national park ranking app, from a sample dataset, with voting capabilities and persistent data storage.Refine your app by integrating a complete dataset, and ask the assistant to recap and explain what it built to find room for improvement and reinforce your learning.By the end of this course, you’ll have a solid foundation in building with coding agents—and a process you can use to keep vibe coding effectively._Anyone can join! It’s helpful to have some coding experience and some background in prompting LLMs.To complete the course you will need to signup for a free Replit account here.

Vibe Coding 101 with Replit

Use the powerful and extensible LangChain framework, using prompts, parsing, memory, chains, question answering, and agents.

Learn LangChain directly from the creator of the framework, Harrison Chase Learn LangChain directly from the creator of the framework, Harrison ChaseApply LLMs to your proprietary data to build personal assistants and specialized chatbots Apply LLMs to your proprietary data to build personal assistants and specialized chatbotsUse agents, chained calls, and memories to expand your use of LLMs Use agents, chained calls, and memories to expand your use of LLMs_In LangChain for LLM Application Development, you will gain essential skills in expanding the use cases and capabilities of language models in application development using the LangChain framework.In this course you will learn and get experience with the following topics:Models, Prompts and Parsers: calling LLMs, providing prompts and parsing the responseMemories for LLMs: memories to store conversations and manage limited context spaceChains: creating sequences of operationsQuestion Answering over Documents: apply LLMs to your proprietary data and use case requirementsAgents: explore the powerful emerging development of LLM as reasoning agents.This one-hour course, instructed by the creator of LangChain Harrison Chase as well as Andrew Ng will vastly expand the possibilities for leveraging powerful language models, where you can now create incredibly robust applications in a matter of hours._LangChain for LLM Application Development is a beginner-friendly course. Basic Python knowledge will help you get the most out of this course.

LangChain for LLM Application Development

Learn about the latest advancements in LLM APIs and use LangChain Expression Language (LCEL) to compose and customize chains and agents.

Learn about the most recent advancements in LLM APIs. Learn about the most recent advancements in LLM APIs.Use LangChain Expression Language (LCEL), a new syntax to compose and customize chains and agents faster. Use LangChain Expression Language (LCEL), a new syntax to compose and customize chains and agents faster.Apply these new capabilities by building up a conversational agent. Apply these new capabilities by building up a conversational agent._The landscape of LLMs and the libraries that support them has evolved rapidly in recent months. This course is designed to keep you ahead of these changes. You’ll explore new advancements like ChatGPT’s function calling capability, and build a conversational agent using a new syntax called LangChain Expression Language (LCEL) for tasks like tagging, extraction, tool selection, and routing.After taking this course, you’ll know how to: Generate structured output, including function calls, using LLMs;Use LCEL, which simplifies the customization of chains and agents, to build applications;Apply function calling to tasks like tagging and data extraction;Understand tool selection and routing using LangChain tools and LLM function calling – and much more.Start applying these new capabilities to build and improve your applications today._Anyone who’s interested in learning about the latest tools to build LLM-based applications. Basic Python knowledge and a familiarity with writing prompts for LLMs is recommended.

Functions, Tools and Agents with LangChain

Build autonomous agents that intelligently navigate and analyze your data. Learn to develop agentic RAG systems using LlamaIndex, enabling powerful document Q&A and summarization. Gain valuable skills in guiding agent reasoning and debugging.

Learn how to build an agent that can reason over your documents and answer complex questions. Learn how to build an agent that can reason over your documents and answer complex questions.Build a router agent that can help you with Q&A and summarization tasks, and extend it to handle passing arguments to this agent. Build a router agent that can help you with Q&A and summarization tasks, and extend it to handle passing arguments to this agent.Design a research agent that handles multi-documents and learn about different ways to debug and control this agent. Design a research agent that handles multi-documents and learn about different ways to debug and control this agent._Join our new short course and learn from Jerry Liu, co-founder and CEO at LlamaIndex to start using agentic RAG, a framework designed to build research agents skilled in tool use, reasoning, and decision-making with your data.In this course:Build the simplest form of agentic RAG – a router. Given a query, the router will pick one of two query engines, Q&A or summarization, to execute a query over a single document.Add tool calling to your router agent where you will use an LLM to not only pick a function to execute but also infer an argument to pass to the function.Build a research assistant agent. Instead of tool calling in a single-shot setting, an agent is able to reason over tools in multiple steps. Build a multi-document agent where you will learn how to extend the research agent to handle multiple documents.Unlike the standard RAG pipeline—suitable for simple queries across a few documents—this intelligent approach adapts based on initial findings to enhance further data retrieval. You’ll learn to develop an autonomous research agent, enhancing your ability to engage with and analyze your data comprehensively.You’ll practice building agents capable of intelligently navigating, summarizing, and comparing information across multiple research papers from arXiv. Additionally, you’ll learn how to debug these agents, ensuring you can guide their actions effectively. Explore one of the most rapidly advancing applications of agentic AI!_Anyone who has basic Python knowledge and wants to learn how to quickly build agents that can reason over their own documents. 

Building Agentic RAG with Llamaindex

Systematically improve the accuracy of LLM applications with evaluation, prompting, and memory tuning.

Understand development steps, from evaluation, through prompting, self-reflection, and fine-tuning, to improve your model’s reliability and accuracy. Understand development steps, from evaluation, through prompting, self-reflection, and fine-tuning, to improve your model’s reliability and accuracy.Learn how memory tuning can increase your model performance by embedding facts into your model to reduce hallucination. Learn how memory tuning can increase your model performance by embedding facts into your model to reduce hallucination.Use the Llama 3-8b model to build an LLM application that converts text to SQL with a custom schema. Use the Llama 3-8b model to build an LLM application that converts text to SQL with a custom schema._Join our new short course, Improving Accuracy of LLM Applications with Lamini and Meta. Learn from Sharon Zhou, Co-founder & CEO of Lamini, and Amit Sangani, Senior Director of Partner Engineering, Meta.Many developers have experienced frustration with inconsistent results when working with LLM applications. This course offers a systematic approach to enhance the accuracy and reliability of your LLM applications.You will build an SQL agent, add evaluation metrics to measure performance, and use prompt engineering and self-reflection to make the model perform better. Finally, you will fine-tune the model with techniques like LoRA and memory tuning that embeds facts in model weights to reduce hallucinations.In this course, you’ll use Llama’s family of open-source models.What you’ll do: Build a text to SQL agent and simulate situations where it hallucinates to begin the evaluation process.Build an evaluation framework to systematically measure performance, including criteria for good evaluations, best practices, and how to develop an evaluation score.Learn how instruction fine-tuning enhances pre-trained LLMs to follow instructions, and how memory fine-tuning embeds facts to reduce hallucinations. Break fine-tuning myths and see how Performance-Efficient Fine-tuning (PEFT) techniques like Low-Rank Adaptation(LoRA) reduce training time by 100x and Mixture of Memory Experts (MoME) reduces it even further. Go through an iterative process of generating training data and fine-tuning, learning practical tips such as adding examples, generating variations, and filtering generated data to increase model accuracy.Start improving the accuracy of LLM applications today! _This course is ideal for anyone with intermediate Python knowledge and familiarity with large language models (LLMs) looking to build more factual and precise LLM applications. 

Improving Accuracy of LLM Applications

Learn a flexible framework to build a variety of complex AI applications.

Learn a flexible framework to Learn how Haystack components, pipelines, and document stores can be used to build custom AI applications.build custom AI applications with components, pipelines, and document stores Learn how Haystack components, pipelines, and document stores can be used to build custom AI applications.Build a RAG pipeline and extend its ability by creating custom components. Build a RAG pipeline and extend its ability by creating custom components.Use conditional branching, self-reflecting agents, and function calling to build complex pipelines and apps. Use conditional branching, self-reflecting agents, and function calling to build complex pipelines and apps._In Building AI Applications with Haystack you will learn a high-level orchestration framework that helps ensure your applications are flexible, extendible, and maintainable, even as the technology stack changes, user needs arise, and new features are added.Using a framework can provide common features out of the box that significantly speeds up the development process. Haystack offers robust and flexible architecture and framework for building AI applications. It manages complexity and helps you focus more on developing your application at a higher level of abstraction.Throughout the course, you will develop several projects, including a RAG app, a news summarization app, a chat agent with function calling, and a self-reflecting agent with loops.What you’ll do: Learn about the core abstractions and unique building blocks of the Haystack framework and see how these elements can be combined for various AI use cases.Build a RAG pipeline by using Haystack components, pipelines, and document stores.Create custom components in your pipeline by building a Hacker News summarizer that extends your app’s ability to access APIs.Use conditional routing to create a branching pipeline with a fall back to web-search when the LLM does not have the context needed to fully respond to the user’s query.Build a self-reflecting agent for named entity recognition with a Haystack pipeline that is able to loop using an output validator custom component.Create a chat agent using OpenAI’s function-calling capabilities which allow you to provide Haystack pipelines as tools to the LLM, enhancing that agent’s capabilities.Start building exciting LLM applications and optimizing your development workflow using Haystack._Anyone who has basic Python knowledge and wants to learn to build and customize complex apps using Haystack!

Building AI Applications With Haystack

Try out the features of the new Llama 3.2 models to build AI applications with multimodality.

Explore the features of the new Llama 3.2 model, from image classification, vision reasoning to tool use. Explore the features of the new Llama 3.2 model, from image classification, vision reasoning to tool use.Learn the details of Llama 3.2 prompting, tokenization, built-in and custom tool calling. Learn the details of Llama 3.2 prompting, tokenization, built-in and custom tool calling.Gain knowledge of the Llama stack, which is a standardized interface for building AI applications. Gain knowledge of the Llama stack, which is a standardized interface for building AI applications._Join our new short course, Introducing Multimodal Llama 3.2, and learn from Amit Sangani, Senior Director of AI Partner Engineering at Meta, to learn all about the latest additions to the Llama models 3.1 and 3.2, from custom tool calling to multimodality and the new Llama stack.Open models are a key building block of AI and a key enabler of AI research. With Meta’s family of open models, anyone can download, customize, fine-tune, or build new applications on top of them, allowing AI innovation. The Llama model family now ranges from 1B model parameters to its 405B foundation model, allowing for diverse use cases and applications.In this course, you’ll learn about the new vision capabilities that Llama 3.2 brings to the Llama family. You’ll learn how to leverage this along with tool-calling, and Llama Stack, which is an open-source orchestration layer for building on top of the Llama family of models.In detail, you’ll: Learn about the new models, how they were trained, their features, and how they fit into the Llama family.Understand how to do multimodal prompting with Llama and work on advanced image reasoning use cases such as understanding errors on a car dashboard, adding up the total of three restaurant receipts, grading written math homework, and many more.Learn different roles—system, user, assistant, ipython—in the Llama 3.1 and 3.2 family and the prompt format that identifies those roles.Understand how Llama uses the tiktoken tokenizer, and how it has expanded to a 128k vocabulary size that improves encoding efficiency and enables support for seven non-English languages.Learn how to prompt Llama to call both built-in and custom tools with examples for web search and solving math equations.Learn about ‘Llama Stack API’, which is a standardized interface for canonical toolchain components like fine-tuning or synthetic data generation to customize Llama models and build agentic applications.Start building exciting applications on Llama!_Anyone who has basic Python knowledge and wants to learn to quickly build on Llama and Llama stack.

Introducing Multimodal Llama 3.2

Build systems with MemGPT agents that can autonomously manage their memory.

Build agents with long-term, persistent memory using Letta to manage and edit context efficiently. Build agents with long-term, persistent memory using Letta to manage and edit context efficiently.Learn how an LLM agent can act as an operating system to manage memory, autonomously optimizing context use. Learn how an LLM agent can act as an operating system to manage memory, autonomously optimizing context use.Apply memory management to create adaptive, collaborative AI agents for real-world tasks like research and HR. Apply memory management to create adaptive, collaborative AI agents for real-world tasks like research and HR._Learn how to build agentic memory into your applications in this short course, LLMs as Operating Systems: Agent Memory, created in partnership with Letta, and taught by its founders Charles Packer and Sarah Wooders.An LLM can use any information stored in its input context window but has limited space. Using a longer input context also costs more and causes slower processing. Managing this context window and what to input becomes very important.Based on the innovative approach in the MemGPT research paper “Towards LLMs as Operating Systems,” its authors, two of whom are Charles and Sarah, proposed using an LLM agent to manage this context window, building a management system that provides applications with managed, persistent memory. Examples of Managing Agent Memory are:Control Conversation Memory. As conversations grow beyond defined limits, move information from context to a persistent searchable database. Summarize information to keep relevant facts in context memory. Restore relevant conversation elements as needed by conversation flow.Persist and edit facts such as names, dates, and preferences, and make them available in context.Persist and track ‘task’ specific information. For example, a research agent needs to keep research information in context memory, swapping the most relevant information from a searchable database with previous information.In this course, you’ll learn: How to build an agent with self-editing memory, using tool-calling and multi-step reasoning, from scratch.Letta, an open-source framework that adds memory to your LLM agents, giving them advanced reasoning capabilities and transparent long-term memory.The key ideas behind the MemGPT paper, the two tiers of memory in and outside the context window, and how agent states comprised of memory, tools, and messages are turned into prompts.How to create and interact with a MemGPT agent using the Letta framework, and how to build and edit its core and archival memory.How core memory is designed and implemented with an example of how to customize it with blocks and memory tools.How to implement multi-agent collaboration both by sending messages and by sharing memory blocks.By the end of this course, you will have the tools to build LLM applications that can leverage virtual context, extending memory beyond the finite context window of LLMs._Anyone who has basic Python skills and is curious about how autonomous agents can manage their own memory.

LLMs as Operating Systems: Agent Memory

Learn to use OpenAI Canvas to write, code, and create more effectively in collaboration with AI.

Learn to write and code more effectively with OpenAI Canvas, using features like targeted editing, in-line feedback, changing the reading level, final polish, reviewing code, and fixing bugs. Learn to write and code more effectively with OpenAI Canvas, using features like targeted editing, in-line feedback, changing the reading level, final polish, reviewing code, and fixing bugs.Learn how to build practical use cases like creating a game app, generating Python code from plot screenshots, and creating SQL databases from architecture images. Learn how to build practical use cases like creating a game app, generating Python code from plot screenshots, and creating SQL databases from architecture images.Gain knowledge of how GPT-4o was trained to bring the OpenAI Canvas features and functionalities to life. Gain knowledge of how GPT-4o was trained to bring the OpenAI Canvas features and functionalities to life._Explore a new way to write and code with OpenAI Canvas, a user-friendly interface that allows you to brainstorm, draft, and refine text and code in collaboration with ChatGPT. In the short course Collaborative Writing and Coding with OpenAI Canvas, taught by Karina Nguyen, research lead at OpenAI, you’ll learn how to use this tool to enhance your writing and coding.Canvas provides a side-by-side workspace where you and ChatGPT can collaboratively edit and refine text or code. This makes brainstorming, drafting, and iterating on the text feel more natural and effective.For instance, after writing the first version of your code, Canvas can review it and give suggestions for improvement. It can also help with debugging by adding logs, identifying problems to fix, and writing comments for your code.This course will teach you how to make the most of the new interactive Canvas workspace and tools to make your writing more flexible, more efficient, and a lot more fun as you go behind the scenes with examples of the different use cases and learn what it takes to train the model to powers Canvas’s features and functionalities.In this video-only short course, you’ll:Learn how to ask for in-line feedback and control the iteration of your creative work by directly editing selected areas of your text or code from the model’s output.Learn how to access quick automation tools in a shortcut menu that allows you to modify your writing tone and length, enhance your code, and restore previous versions of your work.Learn how to use Canvas as a research assistant tool with an example of asking the model to reason through the screenshot of a plot to write a research report, in which you can ask questions within the report.Extend its use case by asking the model to write Python code to replicate the graph seen on a screenshot image.Go behind the scenes of how you can create a video game such as Space Battleship from scratch, edit it, and display it in one self-contained HTML file.Get a real-world application example of creating a SQL database from the image of its architecture.Understand the model training and design processes that power Canvas.By the end of this course, you’ll learn about all the possibilities that the new Canvas interface can bring to your writing and coding workflow._Anyone who wants to learn how to use the new OpenAI Canvas interface to write and code better.

Collaborative Writing and Coding with OpenAI Canvas

Learn how to use and prompt OpenAI's o1 model for complex reasoning tasks.

Learn about o1, what makes it work, how it performs, and the best scenarios to use it. Learn about o1, what makes it work, how it performs, and the best scenarios to use it.Learn how to prompt o1 effectively and when to delegate tasks to more cost-efficient, lower latency models. Learn how to prompt o1 effectively and when to delegate tasks to more cost-efficient, lower latency models.Learn how o1 outperforms on coding and vision reasoning tasks, and how to apply meta-prompting to optimize your applications. Learn how o1 outperforms on coding and vision reasoning tasks, and how to apply meta-prompting to optimize your applications._Learn how to effectively prompt and use OpenAI’s o1 model in Reasoning with o1, a short course built in collaboration with OpenAI and taught by Colin Jarvis, Head of AI Solutions at OpenAI.The o1 model is exceptionally good at abstract reasoning tasks. It has record-breaking performance on tasks such as planning, coding, analyzing, domain-specific reasoning like law, and other STEM subjects.In this course, you will learn how OpenAI utilized reinforcement learning to produce a model that uses ‘test-time compute’ to improve performance on many reasoning tasks. Learn what ‘chain-of-thought’ prompting is and how o1 autonomously utilizes it to break problems into smaller steps, try multiple strategies, and think through responses before returning them.In detail, you’ll: Learn to recognize what tasks the o1 model is suited for and when you might want to use a smaller or faster model or combine those two.Understand four key principles of prompting using o1 from “simple and direct” to “show rather than tell,” and explore the difference in performance.Implement a multi-step task in which o1 acts as an orchestrator creating a plan and handing it over to the 4o-mini model to execute the plan in sequence, balancing the trade-off between intelligence and cost.Use o1 for a coding task to build a new application, edit existing code, and test performance by running a coding competition between o1-mini and GPT 4o.Use o1 for image understanding and learn how it performs better with a hierarchy of reasoning, in which it incurs the latency and cost upfront, preprocessing the image and indexing it with rich details so it can be used for Q&A later.Learn a technique called meta-prompting, in which you use o1 to improve your prompts. Using a customer support evaluation set, you iteratively use o1 to modify a prompt to improve performance.Start building applications that require complex reasoning with o1._It’s helpful to be familiar with Python and have a basic understanding of LLM prompting and LLM application development.

Reasoning with o1

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

Learn about Anthropic’s family of models, its approach to AI research, and the best way to prompt it, including multi-modal use cases. Learn about Anthropic’s family of models, its approach to AI research, and the best way to prompt it, including multi-modal use cases.Learn effective prompting techniques, implement prompt caching to reduce costs and latency, and build AI applications that can call tools. Learn effective prompting techniques, implement prompt caching to reduce costs and latency, and build AI applications that can call tools.See how you can combine multimodal capabilities, agentic workflows, and tool use to build an AI assistant that can navigate and interact with computer interfaces, executing tasks like web searches. See how you can combine multimodal capabilities, agentic workflows, and tool use to build an AI assistant that can navigate and interact with computer interfaces, executing tasks like web searches._Building Towards Computer Use with Anthropic introduces an innovative capability from Anthropic that enables models to interact with and navigate computer interfaces.Taught by Colt Steele, Anthropic’s Head of Curriculum, this course covers Anthropic’s family of models and the building blocks that lead to the amazing new application – Computer Use. Computer Use utilizes the capabilities of the latest models including image reasoning and tool use to enable an LLM-based agent to use a computer. Like a human user, the model processes an image of the screen, analyzes it to understand what’s going on, and navigates the computer by issuing mouse clicks and generating keyboard strokes to get things done.In this course, you’ll learn the features that lead up to computer use from working with the Anthropic’s API, to multimodal prompting, prompt caching, and tool use, ending in a demo that combines these features to build an AI assistant that uses a computer.In detail, you’ll:Learn Anthropic’s approach to AI research, principles of AI safety, alignment, and interpretability while understanding the key differences between its models.Make API requests to Claude, format messages for better responses, and control API parameters like system prompts, temperature, and max tokens for optimal responses.Write multi-modal prompts that combine text and image content blocks and build with streaming responses.Learn effective prompting techniques such as using prompt templates, structuring prompts in XML, and providing examples to get consistent high-quality responses.Learn to implement prompt caching and see how it can reduce costs and latency.Understand tool-use workflows and build a chatbot that can call different tools in response to users’ queries.See all these concepts come together in a demo that uses Anthropic Computer Use to achieve a task on a computer.Start utilizing Anthropic’s family of models to build towards Computer Use applications._Anyone who has basic Python knowledge, wants to learn how to use all of the features of the Anthropic family of models, and understand the capabilities of computer use applications. 

Building toward Computer Use with Anthropic

Learn how to systematically evaluate, improve, and iterate on AI agents using structured assessments.

Learn how to add observability to your agent to gain insights into its steps and know how to debug it. Learn how to add observability to your agent to gain insights into its steps and know how to debug it.Learn how to set up evaluations for the agent components by preparing testing examples, choosing the appropriate evaluator (code-based or LLM-as-a-Judge), and identifying the right metrics. Learn how to set up evaluations for the agent components by preparing testing examples, choosing the appropriate evaluator (code-based or LLM-as-a-Judge), and identifying the right metrics.Learn how to structure your evaluation into experiments to iterate on and improve the output quality and the path taken by your agent. Learn how to structure your evaluation into experiments to iterate on and improve the output quality and the path taken by your agent._Learn how to systematically assess and improve your AI agent’s performance in Evaluating AI Agents, a short course built in partnership with Arize AI and taught by John Gilhuly, Head of Developer Relations, and Aman Khan, Director of Product.When you’re building an AI Agent, an important part of the development process is evaluations or evals. Whether you’re building a shopping assistant, coding agent, or research assistant, having a structured evaluation process helps you refine its performance systematically—rather than relying on trial and error. With a systematic approach, you structure your evaluations to assess the performance of each component of the agent, as well as its end-to-end performance. For each component, you select the appropriate evaluators, testing examples, and metrics. This process helps you identify any areas of improvement so you can iterate on your agent during development and in production. In this course, you’ll build an AI agent, add observability to visualize and debug its steps, and evaluate its performance component-wise.In detail, you’ll: Distinguish between evaluating LLM-based systems and traditional software testing.Explore the basic structure of AI agents – routers, skills, and memory – and implement an AI  agent from scratch.Add observability to the agent by collecting traces of the steps taken by the agent and visualizing the traces.Choose the appropriate evaluator – code-based, LLM-as-a-Judge, and human annotations – for each component of the agent. Set up evaluations for the skills and router decisions of the agent example using code-based and LLM-as-a-judge evaluators, by creating testing examples from collected traces and preparing detailed prompts for the LLM-as-a-judge.Compute a convergence score to evaluate if the example agent can respond to a query in an efficient number of steps.Run structured experiments to improve the performance of the agent by exploring changes to the prompt, LLM model, or the agent’s logic.Understand how to deploy these evaluation techniques to monitor the agent’s performance in production.By the end of this course, you’ll know how to trace AI agents, systematically evaluate them, and improve their performance. _Anyone who has basic Python knowledge and wants to learn to evaluate, troubleshoot, and improve AI agents effectively—both during development and in production. Familiarity with prompting an LLM model would be helpful but not required.

Evaluating AI Agents

Learn to build, debug, and deploy applications with an Agentic AI-powered integrated development environment.

Learn how to collaborate with AI agents to streamline coding workflows, generate and modify code across multiple files, and enhance development efficiency. Learn how to collaborate with AI agents to streamline coding workflows, generate and modify code across multiple files, and enhance development efficiency.Understand how AI coding agents combine tool usage, context awareness, and human-action tracking to function effectively and get a deep dive into search and discovery as one of the main challenges of AI coding agents. Understand how AI coding agents combine tool usage, context awareness, and human-action tracking to function effectively and get a deep dive into search and discovery as one of the main challenges of AI coding agents.Use Windsurf to do real-world coding tasks, including debugging JavaScript code, updating an old large codebase, and building a Wikipedia analysis app that retrieves, processes, and visualizes data while learning to manage unexpected AI behavior. Use Windsurf to do real-world coding tasks, including debugging JavaScript code, updating an old large codebase, and building a Wikipedia analysis app that retrieves, processes, and visualizes data while learning to manage unexpected AI behavior._Join our latest course Build Apps with Windsurf’s AI Coding Agents, built in partnership with Windsurf and taught by Anshul Ramachandran.AI-assisted Integrated Development Environments, or IDEs, make coding and development workflows faster, more efficient, and more fun.Agentic tools like Windsurf are more than just code autocomplete—they are collaborative coding agents that help you break down complex applications, iterate efficiently, and generate code that spans multiple files. Using an AI coding agent effectively requires a new approach to prompting, iteration, and structuring development tasks.In this course, you’ll learn the inner workings of coding agents and how to use Windsurf to code and build several applications. In details, you’ll:Learn how to get started with Windsurf, and build your first app (a snake game) in a couple of minutes.Look at the evolution of AI coding assistants, from simple code suggestions to agentic systems that collaborate with developers.Use an AI agent to analyze and resolve issues in Javascript code, like debugging test issues and multi-file refactoring.Learn mental models to understand how coding agents combine human-action tracking, tool integration, and context awareness in their agentic coding workflow.Learn the challenges of code search and discovery of AI coding agents and how a multi-step retrieval approach helps overcome them.Use Windsurf to analyze and understand a large, old codebase and update it to the latest versions of the frameworks and packages it uses. Use Windsurf to build a Wikipedia data analysis app — retrieving, parsing, and analyzing word frequencies.Enhance the performance of your Wikipedia app by adding caching and while doing so learn how to course-correct when the AI agent produces unexpected results.Learn tips and tricks such as command, autocomplete, @mentions, and explain functionalities to maximize your interactions with the overall AI system as you build a full-stack app to visualize the data of your Wikipedia analysis app.Leverage the multimodal capabilities of the AI agent to increase your development velocity with an example in which you upload a mockup with sketched-out reference UI features to add new functionalities to your app.By the end of this course, you’ll understand agentic coding in-depth and learn to use it to make your development process faster, more efficient, and more enjoyable._It’s helpful for anyone familiar with coding to have a basic understanding of LLM prompting and AI-assisted application development.

Build Apps with Windsurf’s AI Coding Agents

Learn to build AI agents with long-term memory with LangGraph, using LangMem for memory management.

Learn how memory works and how the three types of memory - semantic, episodic, and procedural - are used in agentic workflows. Learn how memory works and how the three types of memory – semantic, episodic, and procedural – are used in agentic workflows.Build a personal email agent with routing, writing, scheduling tools to automatically ignore, respond to, or notify about incoming emails. Build a personal email agent with routing, writing, scheduling tools to automatically ignore, respond to, or notify about incoming emails.Add long-term memory to your agent by adding facts, user preferences, and evolving system prompts to a memory store that can be searched for on-going interactions. Add long-term memory to your agent by adding facts, user preferences, and evolving system prompts to a memory store that can be searched for on-going interactions._Learn to build an agent with long-term memory in Long-Term Agentic Memory with LangGraph! Created in partnership with LangChain, and taught by its Co-Founder and CEO, Harrison Chase.Imagine you had a human personal assistant who forgot about their previous conversation with you—not ideal. The same goes for Agents.The main use cases for agents include personal assistance and productivity tasks. One core aspect of these tasks is long-term memory.In this course, you will learn how to build an agent with long-term memory by creating a personal email agent that can respond, ignore, and notify the user using writing, scheduling, and memory tools. You’ll develop your agent’s memory by adding facts to its memory store, providing examples to learn the user’s preferences, and optimizing system prompts to evolve instructions based on previous responses.By the end of this course, you will have the foundational mental framework to build an agent with long-term memory using LangGraph.In detail, you’ll: Learn how the three types of memory–semantic, episodic, and procedural–and the two mechanisms–via hot path and in the background– apply to your agent.  Build an email agent with writing, scheduling, and availability tools, along with a router that triages incoming email and handles it accordingly by ignoring, responding, or notifying the user.Add tools to your email agent that allow it to operate on semantic memory by learning facts about the user, storing them in a long-term memory store, and searching over them in future interactions.Incorporate episodic memory in the form of few-shot examples in the triage step of your agents to help them learn and update user preferences.  Add procedural memory as system prompts, optimized with feedback to improve the instructions the agent follows.Start building agents with long-term memory with LangGraph._It’s helpful to be familiar with Python and a basic understanding of LLM prompting and LLM application development.