How to Start Building AI Agents with LangGraph

TL;DR

Start by understanding AI agents and the frameworks used to build them, then set up model access, API keys, LangSmith tracking, and LangGraph before creating an agentic chatbot. The session mainly introduces this learning path and its planned application, while human-in-the-loop concepts and additional LangGraph material are reserved for upcoming sessions.

Transcript

hey guys can you give me a quick confirmation if everybody is able to hear me out I'll just wait for some time so that everybody joins hello everyone hello Kesh hello hello everybody hello I hope everybody's doing well I hope everybody's doing fine today we are just going to have one another amazing session uh I'll talk about the agenda each and ev... Read More

Key Insights

• AI agents are the starting concept for the series, with the instructor planning to explain what they are and why they matter before introducing implementation details. This conceptual foundation is intended to clarify what makes the planned chatbot agentic.
• LangGraph is presented as an important framework for building AI agents. The session plans to examine its documentation, explain its setup, and demonstrate how to code an agentic application from scratch rather than treating it only as a theoretical topic.
• The practical workflow begins with configuring access to a model and setting the required API keys. These setup tasks are positioned as prerequisites for writing LangGraph code and creating the planned chatbot application.
• LangSmith is proposed as the tracking mechanism for executions and instructions. The instructor says it can be configured through an API key, allowing activity to be inspected through LangSmith instead of requiring a separately developed custom logging system.
• An agentic chatbot is the main application planned for the LangGraph demonstration. The instructor intends to use this project to connect the introductory explanation of agents with framework setup, model access, tracking, and code written from scratch.
• Human-in-the-loop functionality is identified as a LangGraph concept, but it is not scheduled for the introductory session. The instructor says it will be explained later as the series continues through upcoming sessions.
• The LangGraph material is planned as a continuing series rather than a single isolated class. Additional sessions are expected on Monday and Tuesday, with future lessons adding theoretical presentations and concepts such as human-in-the-loop workflows.
• The associated bootcamp combines agentic AI and generative AI application development with AWS and GCP. Its stated scope includes frameworks, end-to-end projects, fine-tuning, application building, deployment, LangSmith, AutoGen, Langflow, and other topics across approximately 28 modules.

Questions & Answers

Q: How should beginners start building AI agents with LangGraph?

Beginners should first understand what AI agents are, why they are useful, and which frameworks can support them. The session then recommends moving into LangGraph documentation and setup, configuring model access and the necessary API keys, adding LangSmith for execution tracking, and finally writing an agentic chatbot from scratch as the practical application.

Q: What is the planned LangGraph application in the session?

The planned application is an agentic chatbot built with LangGraph. The instructor intends to show the process from initial setup through coding, including model access, API-key configuration, and execution tracking. However, the supplied transcript primarily contains introductions and the agenda, so it does not include the completed chatbot implementation or its final results.

Q: How is LangSmith used with the planned LangGraph workflow?

LangSmith is presented as a way to track instructions and executions generated during the LangGraph workflow. According to the instructor, users can set it up by providing the relevant API key and then inspect execution activity through LangSmith. This approach is offered as an alternative to building a separate custom logging system for the demonstration.

Q: What setup is required before coding with LangGraph?

The session identifies model access and API-key configuration as the main setup requirements before coding begins. It also plans to configure LangSmith through its API key so executions can be tracked. The transcript does not provide exact installation commands, package versions, or code, because it ends while the instructor is still presenting the session agenda.

Q: Does the session explain human-in-the-loop agents in LangGraph?

Human-in-the-loop is acknowledged as a concept within LangGraph, but the instructor says it will not be covered during this introductory session. It is reserved for a later lesson in the continuing series. The provided material therefore confirms the topic as part of the future plan but does not explain its mechanics or provide an implementation.

Q: What topics are included in the LangGraph session agenda?

The agenda includes an introduction to AI agents, an explanation of their importance, and a brief overview of different agent frameworks. It then moves to LangGraph, its documentation, environment and model setup, API keys, LangSmith execution tracking, coding from scratch, and the planned construction of an agentic chatbot. Future sessions are expected to extend this material.

Q: What does the associated agentic AI bootcamp cover?

The associated bootcamp focuses on building agentic AI and generative AI applications, including work on AWS and GCP. The description and transcript mention approximately 28 modules, multiple frameworks, end-to-end generative AI projects, fine-tuning, building, deployment, LangSmith, AutoGen, and Langflow. Azure is not included because obtaining OpenAI service access was described as difficult for participants.

Q: When does the announced AI bootcamp run?

The announced bootcamp starts on January 25, 2025, with sessions scheduled from 3 PM to 6 PM IST every Saturday and Sunday. The description gives a duration of 4–5 months and names Sourangshu Paul, Mayank Aggarwal, Krish Naik, and Sunny Savitha as mentors. It also advertises recorded access, community discussion, doubt clearing, hackathons, and career preparation features.

Summary & Key Takeaways

• The live session introduces a planned LangGraph series focused on building agentic AI applications from scratch. Its agenda begins with the meaning and importance of AI agents, continues with an overview of available agent frameworks, and then moves toward LangGraph documentation, environment setup, model access, API keys, and practical coding.

• A central practical goal is to create an agentic chatbot with LangGraph. Before that implementation, the instructor plans to demonstrate the required setup and connect LangSmith so executions and instructions can be tracked without creating a custom logging system. The supplied transcript ends during the introductory agenda rather than the completed build.

• The broader program described alongside the session covers agentic AI and generative AI application development for AWS and GCP. The announced bootcamp starts January 25, 2025, runs from 3 PM to 6 PM IST on Saturdays and Sundays, and includes approximately 28 modules, projects, deployment, and fine-tuning topics.