chapter six

6 Building autonomous assistants

 

This chapter covers

  • Understanding the fundamental principles of behavior trees for robotics and AI applications
  • The GPT Assistants Playground project and demonstration of creating assistants and actions for assistants
  • An introduction to the agentic behavior tree for autonomous control of multiple assistants and agents
  • Simulating conversational multi-agent systems using agentic behavior trees
  • Using back chaining to create behavior trees for complex systems based on working back from your goal state

In the last chapter, we covered the power actions extended to agents. This chapter looks at how behavior trees can guide agentic systems. We will start by understanding the basics of behavior trees and how they control robotics and AI in games.

We will return to agentic actions and examine how actions can be implemented on the OpenAI Assistants platform using the GPT Assistants Playground project. From there, we will look at how to build an autonomous agentic behavior tree using OpenAI assistants. Then we move on to understanding the need for controls and guardrails on autonomous agents and using control barrier functions.

In the final section of the chapter, we will examine the use of the AgentOps platform to monitor our autonomous behavior-driven agentic systems. This will be an exciting chapter with several challenges. Let’s begin by jumping into the next section, which introduces behavior trees.

6.1 Introducing behavior trees

6.1.1 Understanding behavior tree execution

6.1.2 Deciding on behavior trees

6.1.3 Running behavior trees with Python and py-trees

6.2 Exploring the GPT Assistants Playground

6.2.1 Installing and running the Playground

6.2.2 Using and building custom actions

6.2.3 Installing the assistants database

6.2.4 Getting an assistant to run code locally

6.2.5 Investigating the assistant process through logs

6.3 Introducing agentic behavior trees

6.3.1 Managing assistants with assistants

6.3.2 Building a coding challenge ABT

6.3.3 Posting YouTube videos to X (Twitter)

6.4 Building conversational autonomous multi-agents

6.5 Building agentic behavior trees with back chaining

6.6 Exercises

6.7 Summary