Skip to main content

Quote split assistant

A chat agent on the quote editor that finds quote lines with missing prices or missing stock, proposes a split and moves the problem lines into separate review quotes for your specialists. The clean lines stay behind, ready to convert to an order.

Runs: Embedded in Propeller · Trigger: Chat · Difficulty: Advanced

What you need​

  • An n8n account. See Set up n8n.
  • A Propeller API key.
  • Owner access on the Configuration role to create the agent.

How it works​

You open the chat agent on a quote and type "split order". The workflow checks every line:

  • Lines without a price go to the pricing specialist.
  • Lines without enough stock go to the product specialist.
  • The rest stays in the quote.

The agent replies in Dutch with its proposal and asks for confirmation. When you confirm, it removes the flagged lines from the quote, creates a separate review quote per specialist with its own review status and creates a ticket per review quote so the specialists pick it up.

Before you adapt it​

This entry is labeled Advanced because it assumes things your environment may not have:

  • It sets the review quotes to the custom order statuses PRICING_REVIEW and PRODUCT_REVIEW. Create those statuses first or change them to statuses you use. See Order statuses.
  • The chat responses are written in Dutch.

Install it​

  1. In n8n, import the downloaded JSON as a new workflow.
  2. On the Webhook node, set a header auth credential and copy the production URL.
  3. Create a header auth credential with your Propeller API key and select it on the GraphQL nodes.
  4. Adapt the order statuses and texts as described above.
  5. Activate the workflow.
  6. Go to Admin > Agents and create an agent with Trigger Chat and Interaction Mode Multi Turn. Under Types, pick SALES_HUB_QUOTE_EDITOR. Paste the webhook URL. See AI Agents.
  7. Open a quote with a line that has no price or no stock, type "split order" in the agent chat and confirm.
Placement matters

An agent type is the page where the agent appears. Stick to the types listed in the install steps: the workflow depends on the data that page sends along, so placing the agent on other pages may not work.

Make it yours​

  • Split rules: what counts as a problem line lives in the Categorize Products node.
  • Language: the proposal and confirmation texts live in the Format Response and response nodes.
  • Trigger phrase: the chat message that starts the check is compared in the first If node. Default is "split order".

Use it outside n8n​

Copy the JSON into an AI assistant and follow Adjust a workflow with an AI assistant.

Good to know

The workflows and agents in the Agent Hub are free to use and adapt. They are examples, not supported product features, so test them in a staging environment and check the results before using them in production.