Join Sr. Staff Solutions Architect Steve Androulakis as he builds a durable AI agent using Temporal. The agent is first given a description of the goal and the tools it has at its disposal. The agent uses the LLM to decide which tool to use. If the LLM gives a "bad" response at any point, Temporal will help the agent 'self-heal' by retrying the LLM until it succeeds. The agent allows for amending of parameters such as flight dates using natural language. The agent is not hard-coded to this use case. The Workflow supports dynamic agent goals and tool definitions, so it can essentially work toward any goal so long as the correct tools and goals are provided. Temporal handles the human-in-the-loop confirmation steps via signals. The React JS UI simply queries the Temporal Workflow to display the conversation history. The workflow is coded using Temporal’s Python SDK.
Temporal is changing how modern software is built by guaranteeing the execution of complex, long-running workflows, even in the presence of system failures. This allows developers to focus entirely on writing business logic without dealing with infrastructure complexities. Thousands of leading enterprises such as Snap, Netflix, Hashicorp, Box, Datadog, and many others use Temporal to eliminate the complexity of distributed systems and ensure applications run reliably at scale. Temporal also powers AI initiatives across industries, from foundational projects at major AI labs and chip makers to AI modernization projects at Fortune 500 companies.
