# Multi-agent personal assistant orchestration with OpenAI: n8n workflow

> Started by another system calling it, and works across Redis and Supabase. It puts OpenAI behind a retrieval step, so answers are drawn from documents you...

Source: https://millionrounds.com/workflow/multi-agent-personal-assistant-orchestration-with-openai (Millionrounds; every figure on the page links to its filing or article)

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

# Multi-agent personal assistant orchestration with OpenAI

Started by another system calling it, and works across Redis and Supabase. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 49 steps, 5 branches, 4 loops or waits: large, and worth reading before you trust it with anything live.

Large Calls a model: OpenAI Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fmulti-agent-personal-assistant-orchestration-with-openai)

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

**5** Branches: places the flow splits

**4** Loops or waits

**2** Services it connects to

## The flow

Starts it 1 Model 7 Logic 23 Service 18

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

- 1 **OpenAI Chat Model** Lm Chat Open Ai *Model*
- 2 **Postgres Chat Memory** Memory Postgres Chat *Model*
- 3 **Webhook** Webhook *Starts it*
- 4 **Encerrado** Supabase Tool *Service*
- 5 **leadQualificado** Tool Workflow *Model*
- 6 **AI Agent** Agent *Model*
- 7 **Variáveis Globais** Set *Logic*
- 8 **Edit Fields5** Set *Logic*
- 9 **Supabase** Supabase *Service*
- 10 **Split Out** Split Out *Logic*
- 11 **If1** If *Logic*
- 12 **Loop Over Items** Split In Batches *Logic*
- 13 **If2** If *Logic*
- 14 **Crypto** Crypto *Service*
- 15 **Replace Me** No Op *Logic*
- 16 **Wait1** Wait *Logic*
- 17 **Supabase3** Supabase *Service*
- 18 **Supabase1** Supabase *Service*
- 19 **Switch1** Switch *Logic*
- 20 **Switch** Switch *Logic*
- 21 **Wait3** Wait *Logic*
- 22 **OpenAI2** Open Ai *Model*
- 23 **Responde texto** Http Request *Service*
- 24 **Responde imagem** Http Request *Service*
- 25 **Responde pdf** Http Request *Service*
- 26 **Responde vídeo** Http Request *Service*
- 27 **Edit Fields4** Set *Logic*
- 28 **Edit Fields** Set *Logic*
- 29 **Edit Fields3** Set *Logic*
- 30 **separa o base1** Set *Logic*
- 31 **Extract from File1** Extract From File *Service*
- 32 **Merge** Merge *Logic*
- 33 **Convert to File** Convert To File *Service*
- 34 **Convert to File1** Convert To File *Service*
- 35 **Converte documento** Convert To File *Service*
- 36 **Responde audio** Http Request *Service*
- 37 **Redis** Redis *Service*
- 38 **OpenAI** Open Ai *Model*
- 39 **OpenAI1** Open Ai *Model*
- 40 **Extract from File** Extract From File *Service*
- 41 **Wait** Wait *Logic*
- 42 **Edit Fields8** Set *Logic*
- 43 **Edit Fields9** Set *Logic*
- 44 **separa o telefone e texto3** Set *Logic*
- 45 **Redis1** Redis *Service*
- 46 **If** If *Logic*
- 47 **Edit Fields1** Set *Logic*
- 48 **No Operation, do nothing** No Op *Logic*
- 49 **Redis2** Redis *Service*

## How it's built

- **Starts on:** Another system calling it
- **Steps:** 49, with 5 branches, 4 loops or waits
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Redis, Supabase
- **Model:** OpenAI
- **Retrieval:** Answers are drawn from documents you supply, not from the model alone

## Questions

What does it need to run?

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

What starts it?

It starts on another system calling it.

Does it use AI?

Yes. It calls OpenAI. 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 49 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 49 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%2Fmulti-agent-personal-assistant-orchestration-with-openai)
- **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.

## Connects to

Each opens the other workflows that use it.

[Redis](https://millionrounds.com/workflows?service=Redis#library)[Supabase](https://millionrounds.com/workflows?service=Supabase#library)

## Workflows like it

Also data collection, with the same services where possible, closest in size first.

- [**WordPress - AI chatbot to enhance user experience** 45 steps · calls a model · Postgres, Supabase](https://millionrounds.com/workflow/wordpress-ai-chatbot-to-enhance-user-experience)
- [**Spotify to YouTube playlist synchronization with Discord** 45 steps · Discord, Supabase](https://millionrounds.com/workflow/spotify-to-youtube-playlist-synchronization-with-discord)
- [**Interactive knowledge base chat with Supabase RAG** 43 steps · calls a model · Gmail, Google Drive](https://millionrounds.com/workflow/interactive-knowledge-base-chat-with-supabase-rag)
- [**Collect student absence reasons with WhatsApp** 41 steps · calls a model · Google Sheets, Redis](https://millionrounds.com/workflow/collect-student-absence-reasons-with-whatsapp)
- [**From sitemap crawling to vector storage: Creating an efficient** 35 steps · calls a model · Postgres, Supabase](https://millionrounds.com/workflow/from-sitemap-crawling-to-vector-storage-creating-an-efficien)
- [**AI personal assistant with RAG and Supabase** 64 steps · calls a model · Postgres, Redis](https://millionrounds.com/workflow/ai-personal-assistant-with-rag-and-supabase)