# Build an AI IT support agent with Azure Search and Entra ID: n8n workflow

> Started by someone opening a chat with it. It calls services over plain HTTP rather than through connectors.

Source: https://millionrounds.com/workflow/build-an-ai-it-support-agent-with-azure-search-and-entra-id (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Customer support](https://millionrounds.com/workflows?category=Customer+support#library)

# Build an AI IT support agent with Azure Search and Entra ID

Started by someone opening a chat with it. It calls services over plain HTTP rather than through connectors. It puts Gemini behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 26 steps: large, and worth reading before you trust it with anything live.

Large Calls a model: Gemini Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fbuild-an-ai-it-support-agent-with-azure-search-and-entra-id)

**26 steps** Large: read it before trusting it with anything live

**0** Branches: places the flow splits

**0** Loops or waits

**0** Services by connector: it calls them over plain HTTP

## The flow

Starts it 4 Model 3 Logic 5 Service 14

The steps in the order they run, from what starts it.

- 1 **When chat message received** Chat trigger *Starts it*
- 2 **Google Gemini Chat Model** Lm Chat Google Gemini *Model*
- 3 **Simple Memory** Memory Buffer Window *Model*
- 4 **Create Jira Ticket** Jira Tool *Service*
- 5 **On Knowledge Upload** Form trigger *Starts it*
- 6 **When clicking ‘Test workflow’** Manual trigger *Starts it*
- 7 **Semantic Search** Webhook *Starts it*
- 8 **Invoke Query Vector Store Webhook** Http Request Tool *Service*
- 9 **Reset User Password** Http Request Tool *Service*
- 10 **Query Microsoft Entra ID Users** Http Request Tool *Service*
- 11 **Set Common Fields2** Set *Logic*
- 12 **IT Support Agent** Agent *Model*
- 13 **Split Out Binary Files** Split Out *Logic*
- 14 **Set Common Fields** Set *Logic*
- 15 **Get Embeddings1** Http Request *Service*
- 16 **Prep Content** Code *Logic*
- 17 **Create Azure AI Search Service** Http Request *Service*
- 18 **Get Azure AI Search Admin Key2** Http Request *Service*
- 19 **Get Embeddings** Http Request *Service*
- 20 **Enable Semantic Search** Http Request *Service*
- 21 **Query Azure AI Search Index** Http Request *Service*
- 22 **Set Common Fields1** Set *Logic*
- 23 **Get Azure AI Search Admin Key** Http Request *Service*
- 24 **Get Azure AI Search Admin Key1** Http Request *Service*
- 25 **Create Azure AI Vector Index** Http Request *Service*
- 26 **Upload Embedding to Vector Store** Http Request *Service*

## How it's built

- **Starts on:** Someone opening a chat with it
- **Steps:** 26
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Nothing by connector; it calls services over plain HTTP
- **Model:** Gemini
- **Retrieval:** Answers are drawn from documents you supply, not from the model alone

## Questions

What does it need to run?

An n8n account, and a key for Gemini. You connect your own accounts after importing it; none are included.

What starts it?

It starts on someone opening a chat with it.

Does it use AI?

Yes. It calls Gemini. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 26 steps it is large: read it before trusting it with anything live.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

**Before you run it**

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 26 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fbuild-an-ai-it-support-agent-with-azure-search-and-entra-id)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Workflows like it

Also customer support, with the same services where possible, closest in size first.

- [**Answer HR questions with OpenAI and PostgreSQL** 26 steps · calls a model · Pinecone, Postgres](https://millionrounds.com/workflow/answer-hr-questions-with-openai-and-postgresql)
- [**Email sorting & drafting for customer support with Gemini** 26 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/email-sorting-and-drafting-for-customer-support-with-gemini)
- [**Run a WhatsApp customer support chatbot with OpenWA and OpenAI** 26 steps · calls a model · Gmail, Google Drive](https://millionrounds.com/workflow/run-a-whatsapp-customer-support-chatbot-with-openwa-and-open)
- [**Answer Slack knowledge questions with Notion and Google Drive** 25 steps · calls a model · Google Drive, Notion](https://millionrounds.com/workflow/answer-slack-knowledge-questions-with-notion-and-google-driv)
- [**Answer Telegram data questions with DeepSeek and Open-Meteo** 25 steps · calls a model · Google Sheets, Telegram](https://millionrounds.com/workflow/answer-telegram-data-questions-with-deepseek-and-open-meteo)
- [**Automate customer support with Slack and CRM** 27 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/automate-customer-support-with-slack-and-crm)