Cover Image for Build AI Research Agents with LangGraph: React, Planning, and Memory
Cover Image for Build AI Research Agents with LangGraph: React, Planning, and Memory
Avatar for Packt - ML & AI Engineering

Build AI Research Agents with LangGraph: React, Planning, and Memory

Virtual
Get Tickets
Welcome! Please choose your desired ticket type:
Full workshop access
 
Beyond three hours of expert-led, hands-on learning, you'll receive a complete set of resources to continue building and experimenting after the workshop. This includes a full HD recording of the session, a comprehensive slide deck covering the concepts and implementation techniques, and access to the complete Python codebase featuring five agentic patterns built with LangGraph. You'll also get practical examples using real SEC filings, including implementations of ReAct, reflection, plan-and-execute and agentic memory. A certificate of participation will recognise your learning, while the reusable code and materials will help you apply these patterns to your own projects.
Available until  
AI Agents + LLM Bundle
 
Access two hands-on workshops covering AI research agents and advanced LLM engineering. Build reliable workflows using LangGraph, RAG, tools, memory, and evaluation techniques.
Available until  
About Event

​Build a financial research agent using five LangGraph patterns and real SEC filings. Learn to compare company performance, track financial trends, identify emerging risks, validate findings, and deliver evidence-based answers while controlling execution costs and errors.

​Workshop description

  • ​Build financial research agents using five LangGraph patterns and real SEC filings.

  • ​Develop agents that plan, evaluate evidence, maintain memory, and control costs.

​Who this workshop is for

  • ​Data scientists, ML engineers, AI developers, Python developers, and software engineers.

  • ​Technical leads and AI practitioners building reliable, production-focused agents.

​What you will learn

  • ​Implement fixed workflows, ReAct, reflection, planning, and four memory types.

  • ​Evaluate agent reliability, execution traces, LLM calls, and costs.

​By the end, our agent can handle questions such as

  • ​How have company revenue and R&D spending changed over five years?

  • ​Which financial risks emerged, and how do companies compare?

​Prerequisites

  • ​Python 3.11+, type hints, Pydantic, and basic LLM API knowledge.

  • ​An LLM provider or Ollama, plus Docker or Neo4j. No LangGraph experience required.

​Key takeaways

  • ​Build reliable agents with validated plans, controlled retries, and traceable decisions.

  • ​Develop reusable research workflows that deliver evidence-based answers efficiently.

​Meet your Instructor

  • ​Dr. Alessandro Negro, Senior Director, GraphAware Products at Neo4j.

  • ​PhD in Computer Science and author of Graph-Powered Machine Learning.

Avatar for Packt - ML & AI Engineering