---
title: "A Multi-Agent Support Bot with the OpenAI Agents SDK"
url: https://daily.dev/posts/a-multi-agent-support-bot-with-the-openai-agents-sdk-l6j8d0c44
source_url: https://marmelab.com/blog/2026/07/03/a-multi-agent-support-bot-with-the-openai-agents-sdk.html
type: article
source: "marmelab"
published: 2026-07-03T09:05:38.123Z
updated: 2026-07-03T09:05:58.690Z
tags: ["ai-agents", "bots", "rag"]
reading_time: 9
upvotes: 4
comments: 2
language: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# A Multi-Agent Support Bot with the OpenAI Agents SDK

**[marmelab](https://daily.dev/sources/Marmelab)** · 9 min read · 4 upvotes · 2 comments

## Summary

A walkthrough of building a multi-agent support chatbot for react-admin using the OpenAI Agents SDK. The architecture includes a TriageAgent that classifies incoming questions and hands off to either a DocsAgent (which searches a vector store of 300+ markdown docs using fileSearchTool) or a SupportAgent for billing/subscription queries. Input and output guardrails are implemented to block prompt injections and prevent information leaks, including OpenAI's omni-moderation model for harmful content filtering. The bot is exposed via a Hono API with a custom React frontend, streaming responses to the UI. The post also touches on tracing, human-in-the-loop, and voice agent features available in the SDK.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://marmelab.com/blog/2026/07/03/a-multi-agent-support-bot-with-the-openai-agents-sdk.html>

## Community discussion

Top comments from developers on daily.dev.

**@kartiknvj** · 1 upvotes

> Routing through a TriageAgent before the DocsAgent or SupportAgent is a clean way to keep each agent's context narrow, and putting guardrails on both the input and the output sides is the part people usually skip. Misclassification at triage is where I would expect the quiet failures, since a billing question sent to the docs vector store just returns confident nonsense. How do you handle low-confidence triage, do you fall back to a clarifying question or route to a default agent?

## Similar posts on daily.dev

- [Build a Support Agent with Vercel AI SDK](https://daily.dev/posts/build-a-support-agent-with-vercel-ai-sdk-k4qdf4p91) · freeCodeCamp · 9 upvotes · 0 comments

---

Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#bots](https://daily.dev/tags/bots), [#rag](https://daily.dev/tags/rag)

[View this post on daily.dev](https://daily.dev/posts/a-multi-agent-support-bot-with-the-openai-agents-sdk-l6j8d0c44)