n8n Showing Feedback Agent FAQ: Real Estate Setup

The example is made up. Meridian Realty Group is a made-up brokerage, 14 Orchard Lane is its made-up listing, and every agent and comment is made up too. The practice needs no n8n, OpenAI or Google account, nothing is billed and no workflow is published. This is our own lesson, not an official n8n course.

What does the showing feedback agent do?

You paste in the week's feedback for a listing. In the lesson, three buyer's agents report on 14 Orchard Lane, and the agent returns three entries:

1. Oct 14, Dana Ruiz, Keystone Homes. Interest: Some. Price feedback: "About $15,000 high." Follow-up: the buyers liked the kitchen and yard but worried about road noise; ask Dana if anything would change their mind.
2. Oct 15, Marcus Hill, Hill & Co. Interest: High. Price feedback: None given. Follow-up: a second showing, and his buyers plan to write an offer this week; send Marcus the roof age today.
3. Oct 15, Priya Shah, Open Door Realty. Interest: None. Price feedback: None given. Follow-up: not a fit, because her buyers need four bedrooms; no follow-up needed.

Then you type "Yes, save those to the sheet" and it writes all three rows to the Showing Feedback Log spreadsheet, ready for the weekly seller update. The comment that matters most, a buyer about to make an offer, is flagged instead of buried.

How is the agent built in n8n?

The lesson follows the same path you would take in your own n8n:

1. Sign up and get a key. Start at n8n.io with Get started free. On platform.openai.com, add credit, then create a secret key and copy it.
2. Add a chat trigger. Click Create workflow, then Add first step… and pick On chat message.
3. Add the AI Agent. Click the + on the trigger, open AI and pick AI Agent.
4. Give it its orders. Click + Add Option, choose System Message and paste the system prompt.
5. Give it a model and memory. Add OpenAI Chat Model with your key, pick gpt-5-mini, then add Simple Memory.
6. Give it the Sheets tool. Add Google Sheets Tool, sign in with Google, choose Append Row, pick the sheet and map each column.
7. Test it. Click Open chat, paste the feedback, read the entries, then ask it to save them.

The standing instruction is the system prompt. If you are new to agents in n8n, the n8n AI agent tutorial explains the parts in more depth.

Why won't the agent suggest a price change?

Because the system prompt says not to. It says to record only what was said, not to guess what a buyer will offer, and not to recommend a price change: the listing agent and the seller decide that. "About $15,000 high" is one buyer's agent's opinion, so the log keeps it in their words, in quotes. The price conversation stays with you and your seller.

The prompt also names its audience: the listing agent, who reads every entry before sharing anything with the seller. The agent saves you the hour of pulling feedback together; it doesn't speak to the seller for you.

Key takeaways

• One showing, one row: date, buyer's agent, interest, price feedback and follow-up.
• Price comments are quoted in the buyer's agent's words, or "None given".
• The agent never recommends a price change or guesses an offer.
• Vague or mixed feedback is marked Unclear, with the reason.
• Keep buyers' names, phone numbers and personal details out of what you paste.

Frequently asked questions

What columns does the Showing Feedback Log need?

Five, in row 1: Date in A1, Buyer's agent in B1, Interest in C1, Price feedback in D1 and Follow-up in E1. They match exactly what the system prompt tells the agent to return. In the Sheets tool, click the ✦ button next to each one under Values to Send so the model fills them in.

What do the interest levels mean?

The prompt gives four: High, Some, None and Unclear. In the lesson, a buyer planning an offer is High, buyers who liked parts of the home but had a worry are Some, and buyers who need a bedroom the home doesn't have are None. If feedback is vague or mixed, the agent uses Unclear and says why.

Does the log include the buyers' names?

No. The prompt says never to include buyers' names, phone numbers or personal details. The Buyer's agent column holds the agent's name and brokerage only.

Can I share the sheet with my seller?

That is what it's for, after you read it. The lesson's finish screen says to read every row before you share the sheet. Follow your brokerage's rules on what you share with sellers.

Why does the agent need memory?

Without memory, every message starts from nothing, and it wouldn't know which showings "save those" means. Simple Memory keeps the recent conversation in n8n; the defaults keep the last 5 messages.

Does it work for more than one listing?

Yes. The same workflow works for every listing: paste the week's feedback, check the rows, share the sheet. Say which listing the feedback is for, as the lesson's prompt does with 14 Orchard Lane.

What does it cost to run?

You pay OpenAI for each request you send, not a flat monthly fee. New n8n accounts include free credits too: pick Gateway credits on the model step. Check n8n's and OpenAI's pricing pages for current plans.

What do I need to build it for real?

An n8n account (the cloud trial or self-hosted), an OpenAI API key with a little credit, and a Google account for the sheet. The n8n docs cover each node.

Are there other real estate lessons?

Yes. In the same course, answer anxious buyers without overpromising or write listing descriptions and posts in your voice. For more automations, see n8n workflow ideas for real estate.

What goes wrong most often?

Pasting buyers' details, letting the agent comment on price, and wiring slips like the Sheets node left on reading rows. See n8n showing feedback agent mistakes.