# Route SaaS helpdesk chats with SoterAI and Groq: n8n workflow

> Started by someone opening a chat with it, and works across Pinecone. It puts Groq behind a retrieval step, so answers are drawn from documents you supply...

Source: https://millionrounds.com/workflow/route-saas-helpdesk-chats-with-soterai-and-groq (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)

# Route SaaS helpdesk chats with SoterAI and Groq

Started by someone opening a chat with it, and works across Pinecone. It puts Groq behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 20 steps, 1 branch: a working afternoon to understand properly.

Medium Calls a model: Groq Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Froute-saas-helpdesk-chats-with-soterai-and-groq)

**20 steps** Medium: a working afternoon

**1** Branch: places the flow splits

**0** Loops or waits

**1** Service it connects to

## The flow

Starts it 1 Model 11 Logic 6 Service 2

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

- 1 **Groq LLM Chat Core** Lm Chat Groq *Model*
- 2 **On Chat Message Received** Chat trigger *Starts it*
- 3 **Knowledge Base Memory Cache** Memory Buffer Window *Model*
- 4 **Bug Memory Cache** Memory Buffer Window *Model*
- 5 **Handoff Memory Cache** Memory Buffer Window *Model*
- 6 **Generate Cohere Embeddings** Embeddings Cohere *Model*
- 7 **Knowledge Base Agent** Agent *Model*
- 8 **Bug Analysis Agent** Agent *Model*
- 9 **Handoff Communication Agent** Agent *Model*
- 10 **Guard Input for Threats** Soter Guard *Service*
- 11 **Pinecone KB Vector Store** Vector Store Pinecone *Model*
- 12 **Verify Output for Safety** Soter Guard *Service*
- 13 **Generate Bug Ticket** Code *Logic*
- 14 **Generate Handoff Ticket** Code *Logic*
- 15 **Standardize Incoming Request** Code *Logic*
- 16 **Log Security Incidents** Code *Logic*
- 17 **Reply Success Message** Chat *Model*
- 18 **Determine User Intent** Code *Logic*
- 19 **Reply Blocked Message** Chat *Model*
- 20 **Distribute Based on Intent** Switch *Logic*

## How it's built

- **Starts on:** Someone opening a chat with it
- **Steps:** 20, with 1 branch
- **Size:** Medium: a working afternoon
- **Connects to:** Pinecone
- **Model:** Groq
- **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 Pinecone account, and a key for Groq. 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 Groq. 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?

Plan an afternoon. 20 steps is enough that you should read each one before running it.

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 20 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%2Froute-saas-helpdesk-chats-with-soterai-and-groq)
- **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.

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

## Workflows like it

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

- [**Sync website FAQs to Pinecone weekly with OpenAI** 19 steps · calls a model · Pinecone](https://millionrounds.com/workflow/sync-website-faqs-to-pinecone-weekly-with-openai)
- [**Build a website RAG support chatbot with Firecrawl** 22 steps · calls a model · Pinecone](https://millionrounds.com/workflow/build-a-website-rag-support-chatbot-with-firecrawl)
- [**Build a website-powered customer support chatbot with Decodo** 22 steps · calls a model · Pinecone](https://millionrounds.com/workflow/build-a-website-powered-customer-support-chatbot-with-decodo)
- [**Smart Customer Support System with OpenAI and Gmail** 18 steps · calls a model · Gmail, Google Drive](https://millionrounds.com/workflow/smart-customer-support-system-with-openai-and-gmail)
- [**Turn any website into an AI support chatbot with OpenAI** 18 steps · calls a model · Pinecone](https://millionrounds.com/workflow/turn-any-website-into-an-ai-support-chatbot-with-openai)
- [**AI email support system: Gmail, Gemini, GPT-4, Slack & Google** 23 steps · calls a model · Gmail, Google Drive](https://millionrounds.com/workflow/ai-email-support-system-gmail-gemini-gpt-4-slack-and-google)