---
title: "Temporal AI Agent Demo"
description: "Join Sr. Staff Solution Architect Steve Androulakis as he builds an AI Agent with Temporal."
canonical: "https://temporal.io/resources/on-demand/demo-ai-agent.md"
source: "https://temporal.io/resources/on-demand/demo-ai-agent"
resource_type: "Webinar"
published: "2025-02-13"
industry: "AI"
sdk: "Python"
platform: "Self-Hosted"
use_case: "Agentic AI"
---

# Demo: Build an AI Agent with Temporal

Presented by: [Steve Androulakis](https://temporal.io/authors/steve-androulakis.md)

[Watch the video](https://www.youtube.com/embed/GEXllEH2XiQ)

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.

The demo and source code can be found [here](https://github.com/steveandroulakis/temporal-ai-agent).

## Related resources

- [Spiral Scout: A Practical and Tactical Approach to Temporal and AI](https://temporal.io/resources/on-demand/practical-tactical-approach-temporal-ai.md) — Replay 2024
- [Dubber, Temporal, and Conversational AI at Scale](https://temporal.io/resources/case-studies/dubber.md) — Case Study
- [Building Durable AI Agents with Pydantic AI and Temporal](https://pages.temporal.io/webinar-building-durable-agents-with-pydantic.html) — Webinar