Edlitera works best when JavaScript is enabled. Click to learn more.

Workshops Deep Agents in LangGraph: Agents Using Agents as Tools

Deep Agents in LangGraph: Agents Using Agents as Tools

Move beyond flat agent architectures and unlock the power of hierarchical systems with LangGraph. This workshop teaches you to build sophisticated deep agents where high-level supervisors delegate tasks to specialized sub-agents, which can themselves contain further agents. Learn to design recursive, composable agent architectures that enhance modularity, manage complexity, and improve performance, all while mastering state propagation, cross-agent memory, and effective debugging strategies.

FREE

Upcoming cohort

May 19, 2026

Meeting time

Tuesday, 02:00PM ET

Deep Agents in LangGraph: Agents Using Agents as Tools

What will I learn?

Package entire agent workflows as callable tools for parent agents.
Build hierarchical agent architectures with supervisor agents that delegate to specialized sub-agents with their own tools and memory.
Implement state propagation to pass context down the hierarchy and results back up without losing information.

Understand the limits of recursion and nesting in agent systems, when to flatten, and how to avoid infinite delegation loops.
Manage cross-agent memory, sharing context between parent and child agents while considering isolation vs. information flow.
Debug deep agent stacks by tracing execution through multiple agent layers, identifying bottlenecks, and attributing cost.

Curriculum

Agents as Tools

Learn how to encapsulate complete agent workflows into reusable tools that can be invoked by other agents.

Hierarchical Agent Architectures

Design and implement supervisor agents capable of delegating complex tasks to specialized sub-agents, each with its own set of tools and memory.

State Propagation

Master techniques for effectively passing contextual information down the agent hierarchy and propagating results back up without data loss.

Recursion & Nesting Limits

Understand the practical limits of agent nesting, when to flatten architectures, and strategies to prevent infinite delegation loops.

Cross-Agent Memory

Explore methods for sharing context and managing memory between parent and child agents, balancing isolation with necessary information flow.

Debugging Deep Stacks

Acquire skills for tracing execution paths through multi-layered agent systems, identifying performance bottlenecks, and attributing operational costs.

Why Edlitera?

Build the coding, data and AI skills you need, online, on your own schedule. From learning to code as a beginner to mastering cutting-edge data science, machine learning and AI techniques.

Stylized drawing of a woman in front of a dashboard

Learning for the real world

Our courses are made with the input and feedback of top teams at Fortune 500 companies in Silicon Valley and on Wall Street.

No-fluff learning

Each minute of each course is packed full of insight, best practices and real-world experience from our expert instructors.

Learn by doing

Start writing code on your computer from Day One. Practice on hundreds of exercises. Apply your skills in mini-projects. Get instant feedback from video solutions.

Complete learning tracks

With over 150 hours of video lectures and hundreds of practice exercises and projects, our learning tracks will help you level up your skills whether you are a novice or an advanced learner.

What people are saying

"I walked into the bootcamp with some basic Python syntax and walked out with a much stronger, contextualized grasp of Python, an understanding of common mistakes, the ability to solve basic coding problems, and confidence in my ability to learn more."

Randi S., Edlitera Student

Randi S., a graduate of Edlitera's Python training bootcamp

"I wanted to learn Python and be able to process data without being tied and limited by Excel and macros. These classes gave me all the tools to do so and beyond. The materials provided, the engagement of the class by the tutors and their availability to help us were excellent."

Gaston G., Edlitera Student

Gaston G., a graduate of Edlitera's Python training bootcamp

Course Syllabus

Module 1: Agents as Tools

Package entire agent workflows as callable tools for parent agents.

Module 2: Hierarchical Agent Architectures

Supervisor agents that delegate to specialized sub-agents with their own tools and memory.

Module 3: State Propagation

Passing context down the hierarchy and results back up without losing information.

Module 4: Recursion & Nesting Limits

How deep can you go, when to flatten, and avoiding infinite delegation loops.

Module 5: Cross-Agent Memory

Sharing context between parent and child agents, isolation vs. information flow.

Module 6: Debugging Deep Stacks

Tracing execution through multiple agent layers, identifying bottlenecks, and cost attribution.