The A to Z of Building AI Agents

Abstract: 

2025 is widely touted to be the year of AI agents, and we don’t want you to miss out! With the ability to observe, plan, and act autonomously, AI agents are driving transformation across industries—automating business processes, driving data insights, and augmenting human potential like never before.

In this tutorial, you will learn the foundational concepts of AI agents, such as reasoning, memory, and tool use. We will also cover a few different agent architectures and explore real-world applications of AI agents. Finally, you will see a live code walkthrough of how to build an AI agent end-to-end. The tutorial code and detailed documentation will be shared so you can build the AI agent after the fact at your own pace.

Session Outline:

Part 1: Core Concepts and Use Cases
This module will cover core concepts of building agentic systems, use cases for AI agents, and a few different agent architectures.

Part 2: Build an AI Agent
In this module, we will actually build an AI agent for a technical documentation website using LangGraph, MongoDB, Claude 3.5 Sonnet from Anthropic, and open-source embedding models from Hugging Face. This involves the following:
- Create agent tools
Create two tools for the AI agent, one for Q&A and another for summarization.
- Create the agent
Orchestrate the agent as a graph using LangGraph.
- Add memory to the agent
Add short-term memory to the AI agent so it can have multi-turn conversations with users.

Background Knowledge:

In this tutorial, attendees will learn the core concepts of AI agents and also get a feel for how these systems are built during the live code walkthrough.

We will be using the following free and/or open-source tools in the tutorial:
- LangGraph: Agent orchestration framework
- MongoDB: Knowledge base and persistent memory store for the agent
- Hugging Face: LLM and embedding model provider for the agent

While this lab doesn’t assume any prior Python programming experience, a basic understanding of Python would be helpful.

Bio: 

Apoorva is a Data Scientist turned Developer Advocate, with over 6 years of experience applying Machine Learning to problems in Cybersecurity. As an AI Developer Advocate at MongoDB, she now helps developers be successful at building AI applications through written content and hands-on workshops.

Open Data Science

 

 

 

Open Data Science
One Broadway
Cambridge, MA 02142
info@odsc.com

Privacy Settings
We use cookies to enhance your experience while using our website. If you are using our Services via a browser you can restrict, block or remove cookies through your web browser settings. We also use content and scripts from third parties that may use tracking technologies. You can selectively provide your consent below to allow such third party embeds. For complete information about the cookies we use, data we collect and how we process them, please check our Privacy Policy
Youtube
Consent to display content from - Youtube
Vimeo
Consent to display content from - Vimeo
Google Maps
Consent to display content from - Google