Introducing AI Agents in Langra: A Revolutionary Approach to Building Powerful Systems

I'm delighted to introduce AI agents in Langra, built in partnership with LChain and Civ. This innovative approach to building intelligent systems has been made possible by the collaborative efforts of our instructors, Harrison Chase and Ron Vice, who are both experts in their field. When writing code, we don't just type out the program from start to finish without ever using backspace. Instead, we follow a step-by-step iterative workflow, which is also how AI agents work.

For example, you may build a software architect agent by prompting an LM to propose the overall architecture. A second coder agent can then be implemented by prompting an El to write codes. The third agent could be instructed to act as a code reviewer and try to critique the software. These different agents can work iteratively together to produce a high-quality product, which is often more effective than a single-shot application of prompting an LChain.

LangChain has been a very popular open-source framework for building L applications, and they recently added LDraft, an extension that adds features specifically designed to support agentic workflows. This is an exciting development, as it allows us to create highly controllable agents that can perform reliably. In this course, you will learn how to write an agent from scratch and then rewrite it using LangGraph. You will also learn about the components of LangGraph and how to combine them to build agents and other flow-based applications.

One of the key strengths of Langra is its ability to provide a high level of control over the agent or agents being built. This is extremely useful when you need a high amount of control to get your agent to perform reliably. For example, many agents might need to use tools such as search to enhance their built-in knowledge, but standard search returns links to web locations where you might find an answer to a query, which isn't directly usable by an agent.

To address this issue, Langra has introduced agentic search, which returns multiple answers to a query rather than links to answers. This formatted result is in an agent-friendly way, making it much easier for agents to access and use the information they need. In this course, we will show you how agentic search works and how you can use it in your application.

Agentic AI workflows are an emerging cutting-edge way to build really powerful systems. By learning these skills, you will be able to create highly controllable agents that can perform reliably and make a real impact in the world. I hope you take this course and develop the skills that let you be a real change agent.

"WEBVTTKind: captionsLanguage: enI'm delighted to introduce AI agents in langra built in partnership with L chain and Civ taught by Harrison Chase and Ron fce when writing code you don't just type out the program you want from start to finish without ever using back space at least icon code like that if I were building something together with Arison RM maybe I'll try to create an outline of the architecture Harrison May code up V1 Ron may do a co- review and make suggestions and then I might edit it some more and so on AI agents use a similar stepbystep iterative workflow for example you may build a software architect agent by prompting an LM to propose the overall architecture a second coder agent implemented by prompting an El to write codes might then follow the code and the third agent could be instructed to act as a code reviewer and try to critique the software these different agents can work iteratively together to produce the word product this iterative agentic approach often produces much better results than a single shot application of prompting an L chain has been a very popular op Source framework for building L applications they recently added L draft an extension that adds features specifically AED that supporting agentic workflows I'm delighted to introduce one of our instructors Harrison J who's CEO of Lang chain thanks Andrew Lang chain has supported agents almost from the start but as agents have proliferated we found that we could better support their development debug ability and maintenance by directly supporting a graph structure that underlies so many of their implementations this resulted in Lane graph in this course you will write an agent from scratch and then you will rewrite it using Lang graph you will learn about the components of lingraph and how to combine them to build agents and other flow-based applications lingraph is aimed at letting developers create highly controllable agents you can specify exactly the state and the control flow of the agent or agents this is extremely useful when you need a high amount of control to get your agent to perform reliably that controllability aspect is a real strength of langra and when you built your own agent you find that many agents might need to use tools such as search to enhance their built-in knowledge but standard search returns links to web locations where you might find an answer to a query but this isn't directly usable by an agent to make this process easier I'm also delighted to introduce another of our instructors Ron Vice who is co-founder and CEO of to the Le thanks Andre an agentic search returns multiple answers to a query rather than links to answers it formats the results in an agent friendly way in this course we'll show you how agentic search works and how you can use it in your application agentic AI workflows are an emerging cutting way to build really powerful systems I hope you take this course and G skills that let you be a real change agentI'm delighted to introduce AI agents in langra built in partnership with L chain and Civ taught by Harrison Chase and Ron fce when writing code you don't just type out the program you want from start to finish without ever using back space at least icon code like that if I were building something together with Arison RM maybe I'll try to create an outline of the architecture Harrison May code up V1 Ron may do a co- review and make suggestions and then I might edit it some more and so on AI agents use a similar stepbystep iterative workflow for example you may build a software architect agent by prompting an LM to propose the overall architecture a second coder agent implemented by prompting an El to write codes might then follow the code and the third agent could be instructed to act as a code reviewer and try to critique the software these different agents can work iteratively together to produce the word product this iterative agentic approach often produces much better results than a single shot application of prompting an L chain has been a very popular op Source framework for building L applications they recently added L draft an extension that adds features specifically AED that supporting agentic workflows I'm delighted to introduce one of our instructors Harrison J who's CEO of Lang chain thanks Andrew Lang chain has supported agents almost from the start but as agents have proliferated we found that we could better support their development debug ability and maintenance by directly supporting a graph structure that underlies so many of their implementations this resulted in Lane graph in this course you will write an agent from scratch and then you will rewrite it using Lang graph you will learn about the components of lingraph and how to combine them to build agents and other flow-based applications lingraph is aimed at letting developers create highly controllable agents you can specify exactly the state and the control flow of the agent or agents this is extremely useful when you need a high amount of control to get your agent to perform reliably that controllability aspect is a real strength of langra and when you built your own agent you find that many agents might need to use tools such as search to enhance their built-in knowledge but standard search returns links to web locations where you might find an answer to a query but this isn't directly usable by an agent to make this process easier I'm also delighted to introduce another of our instructors Ron Vice who is co-founder and CEO of to the Le thanks Andre an agentic search returns multiple answers to a query rather than links to answers it formats the results in an agent friendly way in this course we'll show you how agentic search works and how you can use it in your application agentic AI workflows are an emerging cutting way to build really powerful systems I hope you take this course and G skills that let you be a real change agent\n"