# Build an n8n AI Agent That Turns Showing Feedback into a Seller Update

> Build an n8n AI agent that turns buyer agents' showing feedback into one row per showing in Google Sheets: interest, price feedback and the next step.

Source: https://learn.ynteractive.com/content/n8n-ai-agent-real-estate-showing-feedback · Updated 2026-10-21 · Free from Stepthrough (https://learn.ynteractive.com)

## Practice it step by step

[Start the free practice](https://learn.ynteractive.com/modules/real-estate-showing-feedback-agent)

[Take the free module: why it matters, practice and a quick check →](https://learn.ynteractive.com/courses/ai-for-real-estate/11)

You do every step yourself in a practice copy of n8n. It checks your work as you go, and “Do it for me” finishes any step you get stuck on. Free, about 12 minutes, and nothing touches your real accounts. [Open full screen](https://learn.ynteractive.com/modules/real-estate-showing-feedback-agent)

Free · Live now · [AI Automation for Real Estate](https://learn.ynteractive.com/content/industry/real-estate) · [n8n](https://learn.ynteractive.com/content/tool/n8n) · ~12 min · 72 steps · Intermediate

Updated October 21, 2026. Built against the tool’s current screens and checked step by step. [How we check this lesson](https://learn.ynteractive.com/content/about#how-we-check)

Every showing ends with feedback from the buyer's agent, in a text, an email or a quick call, and by Friday the seller wants to know what people are saying. Pulling it together takes an hour, and the comment that matters most, a buyer about to write an offer, is easy to miss. In this free, interactive lesson you build an [AI agent](https://learn.ynteractive.com/content/glossary/ai-agent) in [n8n](https://learn.ynteractive.com/content/tool/n8n) that turns a week of feedback into one row per showing in a Google Sheet: the interest level, what was said about the price in the agent's own words, and the next step. It never tells you to cut the price.

## At a glance

| Question | Answer |
| --- | --- |
| What you build | Build an AI agent in n8n for Meridian Realty Group that turns buyer agents’ showing feedback into one row per showing in Google Sheets, with interest, price feedback and the next step, so the weekly seller update writes itself. Chat trigger, AI Agent, system prompt, model, memory and the Sheets tool. |
| Tools | n8n |
| Time | About 12 minutes, 72 steps in 12 parts |
| Level | Intermediate |
| Cost | Free |
| Ways to learn it | [Practice it step by step](https://learn.ynteractive.com/modules/real-estate-showing-feedback-agent), read the guide with screenshots |

### The 12 parts, in short

1. Get n8n: Go to n8n.io, Enter your email, Sign up.
2. API key: Add credit first, Ten dollars is plenty, Now the key, Create a secret key, and 4 more steps.
3. New workflow: Start a new workflow.
4. Chat trigger: Add the first step, Trigger on a chat message, Back to the canvas.
5. AI Agent: Add the next node, Open the AI nodes, Add the AI Agent.
6. System prompt: Open the options, Add a system message, Write the system prompt, Back to the canvas.
7. Chat model: Give the agent a brain, Pick OpenAI, Open the credentials, Create a new credential, and 5 more steps.
8. Memory: Add memory, Simple Memory, Back to the canvas.
9. Sheets tool: Add a tool, Search for Sheets, Add Google Sheets.
10. Create the spreadsheet: Back to the canvas, Open Google Sheets, Name the spreadsheet, Type the first column header, and 6 more steps.
11. Configure Sheets: Add a credential, Create a new credential, Sign in with Google, Choose your account, and 16 more steps.
12. Test the agent: Open the chat, Paste this week's feedback, Send the message, Save to the sheet, and 1 more step.

**Start here first:** [n8n AI Agent Tutorial: Save Social Media Ideas to Google Sheets](https://learn.ynteractive.com/content/n8n-ai-agent-tutorial-google-sheets). This Real Estate version follows the same build with its own example business, Meridian Realty Group.

**Part of:** [AI for Real Estate](https://learn.ynteractive.com/content/paths/ai-for-real-estate) (step 13 of 13)

## How to build an n8n AI Agent That Turns Showing Feedback into a Seller Update: step-by-step guide with screenshots

**About the screenshots.** They come from Stepthrough’s simulated practice environment (a practice copy of n8n), not the live tool, so no real account appears. The buttons and labels match the real screens the lesson was built against. Practice it yourself free at learn.ynteractive.com.

- Tools: n8n
- Time: about 12 minutes, 72 steps in 12 parts
- Level: intermediate

### Part 1: Get n8n

#### Step 1: Go to n8n.io

Every showing ends with feedback from the buyer's agent, in a text, an email or a quick call. By Friday your seller wants to know what people are saying, and the one comment that matters most, a buyer about to make an offer, is easy to lose. We are going to build an AI agent that logs every showing in a spreadsheet for you. First, you need an n8n account.

![The n8n.io website in Stepthrough’s practice copy, step 1 of 72 (Go to n8n.io): the cursor is on “Get started free”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-01.webp)

**Step 1 of 72.** Start at **n8n.io**. Click **Get started free**.

#### Step 2: Enter your email

This is just practice, so anything works — it won't actually send anything.

![The n8n sign-up form in Stepthrough’s practice copy, step 2 of 72 (Enter your email): the email is ready to paste, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-02.webp)

**Step 2 of 72.** Type any email address — this is practice, so a fake one is fine.

#### Step 3: Sign up

In the real n8n, it sends you a six digit code, then asks for a name, a password, and an account name. Go do that in your own browser later, then come back and we will build.

![The n8n sign-up form in Stepthrough’s practice copy, step 3 of 72 (Sign up): the cursor is on “Continue”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-03.webp)

**Step 3 of 72.** Click **Continue**. n8n emails you a code, then asks for a name and password — do that part on your own and come back here.

### Part 2: API key

#### Step 4: Add credit first

Your agent needs a brain, and that means an [API key](https://learn.ynteractive.com/content/glossary/api-key) from OpenAI. Go to platform dot openai dot com — that is the developer side, not ChatGPT, and it bills completely separately. Before you make a key, put some money on the account. A brand new key with a zero balance just returns errors. If you would rather not spend anything yet, n8n gives every new account free [credits](https://learn.ynteractive.com/content/glossary/ai-credits). In your own n8n, you can pick gateway credits on the model step and skip the key.

![The OpenAI platform billing page in Stepthrough’s practice copy, step 4 of 72 (Add credit first): the cursor is on “Add to credit balance”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-04.webp)

**Step 4 of 72.** Your agent needs a model to think with. At **platform.openai.com → Billing**, click **Add to credit balance** — a key with no credit behind it just errors. (Want to skip this? New n8n accounts include free credits: in your own n8n, pick **Gateway credits** on the model step instead of a key.)

#### Step 5: Ten dollars is plenty

Ten dollars goes a very long way. You are charged per request, not per month, and logging a week of showings costs fractions of a cent.

![The OpenAI platform billing page in Stepthrough’s practice copy, step 5 of 72 (Ten dollars is plenty): the cursor is on “Continue”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-05.webp)

**Step 5 of 72.** Ten dollars goes a long way — you pay per request, not per month. Click **Continue**. In your own account you add a card here.

#### Step 6: Now the key

Balance sorted. Now go to API keys in the left menu.

![The OpenAI platform billing page in Stepthrough’s practice copy, step 6 of 72 (Now the key): the cursor is on “API Keys”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-06.webp)

**Step 6 of 72.** Balance sorted. Click **API Keys** in the left menu.

#### Step 7: Create a secret key

![The OpenAI API keys page in Stepthrough’s practice copy, step 7 of 72 (Create a secret key): the cursor is on “+ Create new secret key”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-07.webp)

**Step 7 of 72.** Click **+ Create new secret key**.

#### Step 8: Name the key

Name it after whatever is going to use it. Future you, staring at a list of forty keys, will thank you. I am calling this one n8n agent.

![The OpenAI API keys page in Stepthrough’s practice copy, step 8 of 72 (Name the key): “n8n agent” is typed in, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-08.webp)

**Step 8 of 72.** Name it after what will use it. Type **n8n agent**.

#### Step 9: Create it

Default project, all permissions — that is fine for this. Create the key.

![The OpenAI API keys page in Stepthrough’s practice copy, step 9 of 72 (Create it): the cursor is on “Create secret key”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-09.webp)

**Step 9 of 72.** Leave Project and Permissions alone and click **Create secret key**.

#### Step 10: Copy it now

Now pay attention, because this is the only time you will ever see this key. Copy it and paste it into n8n, or into your password manager. If you lose it, you do not get it back — you delete it and make another.

![The OpenAI API keys page in Stepthrough’s practice copy, step 10 of 72 (Copy it now): the cursor is on “Copy”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-10.webp)

**Step 10 of 72.** This is the only time OpenAI shows you the key. Click **Copy**, then paste it somewhere safe.

#### Step 11: Back to n8n

One last warning — this key can spend your money. Never commit it to code, never paste it into a chat, and if it ever shows up on screen while you are recording, revoke it before you publish.

![The OpenAI API keys page in Stepthrough’s practice copy, step 11 of 72 (Back to n8n): the cursor is on “Done”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-11.webp)

**Step 11 of 72.** Click **Done**. Treat that key like a password — never paste it into a chat, a repo, or a screen recording.

### Part 3: New workflow

#### Step 12: Start a new workflow

Now you are inside n8n. This overview page lists every workflow you have. Top right, click create workflow, and you land on an empty canvas.

![The n8n overview page in Stepthrough’s practice copy, step 12 of 72 (Start a new workflow): the cursor is on “Create workflow”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-12.webp)

**Step 12 of 72.** This is your n8n home. Click **Create workflow** in the top right.

### Part 4: Chat trigger

#### Step 13: Add the first step

Every workflow needs a trigger — the thing that kicks it off. We want a chat trigger so you can paste in the week's showing feedback.

![The n8n workflow canvas in Stepthrough’s practice copy, step 13 of 72 (Add the first step): the cursor is on “Add first step…”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-13.webp)

**Step 13 of 72.** Every workflow starts with a trigger. Click **Add first step…**

#### Step 14: Trigger on a chat message

A panel slides in with every way a workflow can start — manually, on a schedule, on a webhook. We want on chat message, so we can have a conversation with the agent.

![The n8n node list in Stepthrough’s practice copy, step 14 of 72 (Trigger on a chat message): the cursor is on “On chat message”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-14.webp)

**Step 14 of 72.** The trigger panel opened on the right. Pick **On chat message** near the bottom.

#### Step 15: Back to the canvas

n8n opens the node so you can configure it. There is nothing we need to change here, so close it with the X in the top right and get back to the canvas.

![An n8n node’s settings window in Stepthrough’s practice copy, step 15 of 72 (Back to the canvas): the cursor is on “×”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-15.webp)

**Step 15 of 72.** n8n opens the node so you can configure it. Nothing to change here — click the **×** in the top right.

### Part 5: AI Agent

#### Step 16: Add the next node

Now we decide what happens when a message comes in.

![The n8n workflow canvas in Stepthrough’s practice copy, step 16 of 72 (Add the next node): the cursor is on “+”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-16.webp)

**Step 16 of 72.** Click the **+** on the right edge of the trigger node.

#### Step 17: Open the AI nodes

A panel opens and asks what happens next. The agent lives under AI, right at the top.

![The n8n node list in Stepthrough’s practice copy, step 17 of 72 (Open the AI nodes): the cursor is on “AI”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-17.webp)

**Step 17 of 72.** The **What happens next?** panel opens with categories. Click **AI** at the top.

#### Step 18: Add the AI Agent

There it is — AI Agent. This is the piece that can plan and then carry out actions using whatever tools you give it. You give it the feedback, and it can sort each showing and save it to a spreadsheet — all in one step.

![The n8n node list in Stepthrough’s practice copy, step 18 of 72 (Add the AI Agent): the cursor is on “AI Agent”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-18.webp)

**Step 18 of 72.** In **AI Nodes**, click **AI Agent** — it makes a plan and carries it out using the tools you give it.

### Part 6: System prompt

#### Step 19: Open the options

Right now this agent has no personality and no orders. It does not know it works for Meridian Realty, or what a showing entry looks like.

![An n8n node’s settings window in Stepthrough’s practice copy, step 19 of 72 (Open the options): the cursor is on “+ Add Option”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-19.webp)

**Step 19 of 72.** The agent has no personality yet. Click **+ Add Option** under Options.

#### Step 20: Add a system message

Pick system message. This is the standing instruction the agent reads before every request. It is where we tell it who Meridian is, how to log a showing, and what it must never do.

![A dropdown menu in n8n in Stepthrough’s practice copy, step 20 of 72 (Add a system message): the cursor is on “System Message”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-20.webp)

**Step 20 of 72.** Choose **System Message**. This is the standing instruction the agent follows every time.

#### Step 21: Write the system prompt

Here is the actual prompt. It tells the agent what each entry needs: the date, the buyer's agent, an interest level, the price feedback in the agent's own words, and the next step. Vague feedback gets marked unclear. And two rules matter most: record only what was said, and never recommend a price change. That's your call, with your seller.

![An n8n node’s settings window in Stepthrough’s practice copy, step 21 of 72 (Write the system prompt): the system prompt is ready to paste, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-21.webp)

**Step 21 of 72.** The box starts with **You are a helpful assistant**. Replace it with the standing instruction: it is long, so just Paste in the system prompt on the box.

```text
You are the showing feedback assistant for Meridian Realty Group.

Meridian Realty Group is a small residential brokerage. Its listing agents send sellers a feedback update every week while a home is on the market.

The audience is the listing agent, who reads every entry before sharing anything with the seller.

The tone should be plain, neutral and factual.

Your job is to turn each piece of showing feedback the user gives you into one entry.

For each showing, return:
- Date
- Buyer's agent (name and brokerage only)
- Interest: High, Some, None, or Unclear
- Price feedback: what the buyer's agent said about the price, in their words, or "None given"
- Follow-up: one sentence on what the listing agent should do next, like answer a question or expect an offer

If the feedback is vague or mixed, use Unclear and say why.

When the user asks you to save the feedback, use the Google Sheets tool to store each entry.

Record only what was said. Do not guess what a buyer will offer, and do not recommend a price change; the listing agent and the seller decide that. Never include buyers' names, phone numbers or personal details.
```

#### Step 22: Back to the canvas

That gives the agent everything it needs to know about logging showings for Meridian. Close the node.

![An n8n node’s settings window in Stepthrough’s practice copy, step 22 of 72 (Back to the canvas): the cursor is on “×”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-22.webp)

**Step 22 of 72.** That tells the agent who it works for and how to log a showing. Close the node with the **×**.

### Part 7: Chat model

#### Step 23: Give the agent a brain

See that red triangle on the agent? It is complaining because it has no model. An agent can plan, but it cannot think without a language model underneath it.

![The n8n workflow canvas in Stepthrough’s practice copy, step 23 of 72 (Give the agent a brain): the cursor is on “+”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-23.webp)

**Step 23 of 72.** The agent has a red warning: it has no model. Click the **+** under **Chat Model**.

#### Step 24: Pick OpenAI

OpenAI chat model. This is where that API key finally gets used.

![The n8n node list in Stepthrough’s practice copy, step 24 of 72 (Pick OpenAI): the cursor is on “OpenAI Chat Model”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-24.webp)

**Step 24 of 72.** Click **OpenAI Chat Model**.

#### Step 25: Open the credentials

And here is where that key you copied finally goes.

![An n8n node’s settings window in Stepthrough’s practice copy, step 25 of 72 (Open the credentials): the cursor is on “Credential”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-25.webp)

**Step 25 of 72.** Here is where that key goes. Click the **Credential** dropdown.

#### Step 26: Create a new credential

You want create new credential, right at the bottom. In your own n8n, if you skipped the key, you would pick gateway credits here instead.

![A dropdown menu in n8n in Stepthrough’s practice copy, step 26 of 72 (Create a new credential): the cursor is on “+ Create new credential”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-26.webp)

**Step 26 of 72.** Click **+ Create new credential** at the bottom of the list. (Free credits instead? Pick **Gateway credits** in your own n8n.)

#### Step 27: Paste the key

This is the one moment it matters that you copied it — remember, OpenAI never shows it to you again.

![The n8n credential window in Stepthrough’s practice copy, step 27 of 72 (Paste the key): the api key is ready to paste, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-27.webp)

**Step 27 of 72.** Paste in the API key on the field to drop in the key you copied from OpenAI.

#### Step 28: Save the credential

n8n tests the connection straight away, and from now on this credential is available to every node in every workflow — you only do this once.

![The n8n credential window in Stepthrough’s practice copy, step 28 of 72 (Save the credential): the cursor is on “Save”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-28.webp)

**Step 28 of 72.** Click **Save**. n8n tests the connection and stores the key for every future node.

#### Step 29: Open the model list

Now the model dropdown.

![An n8n node’s settings window in Stepthrough’s practice copy, step 29 of 72 (Open the model list): the cursor is on “Model”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-29.webp)

**Step 29 of 72.** A new credential leaves **Model** on **Select a model...**. Click the **Model** dropdown.

#### Step 30: Choose the model

GPT five mini. Fast, cheap, and plenty for sorting showing feedback. Do not reach for the expensive model until you have a reason.

![A dropdown menu in n8n in Stepthrough’s practice copy, step 30 of 72 (Choose the model): the cursor is on “gpt-5-mini”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-30.webp)

**Step 30 of 72.** Pick **gpt-5-mini** — fast and cheap, plenty for this. (The list is long: type **gpt-5-mini** in **Search...** to find it.)

#### Step 31: Back to the canvas

That is the brain wired in. Close it up.

![An n8n node’s settings window in Stepthrough’s practice copy, step 31 of 72 (Back to the canvas): the cursor is on “×”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-31.webp)

**Step 31 of 72.** The model is wired up. Close the node with the **×**.

### Part 8: Memory

#### Step 32: Add memory

Next, memory. Without this, every message starts from nothing — you could not say save those, because it would not remember which showings you meant.

![The n8n workflow canvas in Stepthrough’s practice copy, step 32 of 72 (Add memory): the cursor is on “+”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-32.webp)

**Step 32 of 72.** Without memory the agent forgets each message. Click the **+** under **Memory**.

#### Step 33: Simple Memory

Simple memory is fine here — it keeps the recent conversation inside n8n, no database, no extra credentials.

![The n8n node list in Stepthrough’s practice copy, step 33 of 72 (Simple Memory): the cursor is on “Simple Memory”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-33.webp)

**Step 33 of 72.** Pick **Simple Memory**. It keeps the recent conversation in n8n itself.

#### Step 34: Back to the canvas

n8n opens simple memory so you can set it up. The defaults are fine. It keeps the last five messages. Close it with the X.

![An n8n node’s settings window in Stepthrough’s practice copy, step 34 of 72 (Back to the canvas): the cursor is on “Simple Memory”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-34.webp)

**Step 34 of 72.** n8n opens **Simple Memory** so you can set it up. The defaults are fine (it keeps the last 5 messages). Close it with the **×**.

### Part 9: Sheets tool

#### Step 35: Add a tool

And now the good part — tools. This is what separates an agent from a chatbot. A chatbot just talks. An agent does things. We are going to give it Google Sheets so it can save every showing into a spreadsheet you can go through with your seller.

![The n8n workflow canvas in Stepthrough’s practice copy, step 35 of 72 (Add a tool): the cursor is on “+”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-35.webp)

**Step 35 of 72.** Tools are how the agent acts on the world. Click the **+** under **Tool**.

#### Step 36: Search for Sheets

Google Sheets is not in the recommended tools, so search for it.

![The n8n node list in Stepthrough’s practice copy, step 36 of 72 (Search for Sheets): “sheets” is typed in, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-36.webp)

**Step 36 of 72.** Google Sheets is not in **Recommended Tools**. In **Search nodes...**, type **sheets**.

#### Step 37: Add Google Sheets

Google Sheets tool. Now the agent can write rows into a real spreadsheet, with columns matching what the system prompt tells it to return. When you say save those, each showing becomes a row.

![The n8n node list in Stepthrough’s practice copy, step 37 of 72 (Add Google Sheets): the cursor is on “Google Sheets Tool”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-37.webp)

**Step 37 of 72.** Click **Google Sheets Tool** — read, update and write data to Google Sheets.

### Part 10: Create the spreadsheet

#### Step 38: Back to the canvas

Before we set this up, we need to actually create the spreadsheet. Close this node for now — we are going to hop over to Google Sheets and make one.

![An n8n node’s settings window in Stepthrough’s practice copy, step 38 of 72 (Back to the canvas): the cursor is on “Back to the canvas”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-38.webp)

**Step 38 of 72.** Before we configure this node, we need a spreadsheet for the agent to write to. Close the node — we will come back.

#### Step 39: Open Google Sheets

Switch to Google Sheets. You need to create the spreadsheet that this node will write to.

![Google Sheets in Stepthrough’s practice copy, step 39 of 72 (Open Google Sheets): the cursor is on “Google Sheets”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-39.webp)

**Step 39 of 72.** Click the **Google Sheets** tab to create a new blank spreadsheet.

#### Step 40: Name the spreadsheet

First, name it so you can find it later.

![Google Sheets in Stepthrough’s practice copy, step 40 of 72 (Name the spreadsheet): the cursor is on “Showing Feedback Log”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-40.webp)

**Step 40 of 72.** Click the title and rename it to **Showing Feedback Log**.

#### Step 41: Type the first column header

Now set up the column headers. These need to match what the system prompt tells the agent to return. In A1, type Date.

![Google Sheets in Stepthrough’s practice copy, step 41 of 72 (Type the first column header): the cursor is on “A1”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-41.webp)

**Step 41 of 72.** In cell **A1**, type **Date**.

#### Step 42: Buyer's agent

B1 — Buyer's agent.

![Google Sheets in Stepthrough’s practice copy, step 42 of 72 (Buyer's agent): the cursor is on “B1”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-42.webp)

**Step 42 of 72.** In cell **B1**, type **Buyer's agent**.

#### Step 43: Interest

C1 — Interest.

![Google Sheets in Stepthrough’s practice copy, step 43 of 72 (Interest): the cursor is on “C1”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-43.webp)

**Step 43 of 72.** In cell **C1**, type **Interest**.

#### Step 44: Price feedback

D1 — Price feedback.

![Google Sheets in Stepthrough’s practice copy, step 44 of 72 (Price feedback): the cursor is on “D1”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-44.webp)

**Step 44 of 72.** In cell **D1**, type **Price feedback**.

#### Step 45: Follow-up

And E1 — Follow-up. Five columns, matching exactly what the system prompt tells the agent to return. Each showing becomes a row in this sheet.

![Google Sheets in Stepthrough’s practice copy, step 45 of 72 (Follow-up): the cursor is on “E1”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-45.webp)

**Step 45 of 72.** In cell **E1**, type **Follow-up**. That is all five columns — matching the system prompt.

#### Step 46: Back to n8n

The spreadsheet is ready. Switch back to n8n and connect the Google Sheets node to it.

![Google Sheets in Stepthrough’s practice copy, step 46 of 72 (Back to n8n): the cursor is on “n8n”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-46.webp)

**Step 46 of 72.** The spreadsheet is ready. Click the **n8n** tab to go back and connect it.

#### Step 47: Open the Sheets node

Double click the Google Sheets node to open it back up. Now we can connect it to the spreadsheet we just made.

![The n8n workflow canvas in Stepthrough’s practice copy, step 47 of 72 (Open the Sheets node): the cursor is on “Get row(s) in sheet in Google Sheets”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-47.webp)

**Step 47 of 72.** Double-click the Google Sheets node (n8n named it **Get row(s) in sheet in Google Sheets**) to configure it.

### Part 11: Configure Sheets

#### Step 48: Add a credential

Now we need to connect this to a real Google account.

![An n8n node’s settings window in Stepthrough’s practice copy, step 48 of 72 (Add a credential): the cursor is on “Credential”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-48.webp)

**Step 48 of 72.** The Sheets node needs a Google account. Click the **Credential** dropdown.

#### Step 49: Create a new credential

Create new credential — this one uses Google OAuth instead of an API key, so it is going to open a sign-in window.

![A dropdown menu in n8n in Stepthrough’s practice copy, step 49 of 72 (Create a new credential): the cursor is on “+ Create new credential”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-49.webp)

**Step 49 of 72.** Click **+ Create new credential** to sign in with Google.

#### Step 50: Sign in with Google

This opens the Google account chooser so you can pick which account to connect.

![An n8n node’s settings window in Stepthrough’s practice copy, step 50 of 72 (Sign in with Google): the cursor is on “Sign in with Google”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-50.webp)

**Step 50 of 72.** Click **Sign in with Google** to connect your account.

#### Step 51: Choose your account

Pick the Google account you want n8n to use. This is the account that owns the spreadsheet.

![An n8n node’s settings window in Stepthrough’s practice copy, step 51 of 72 (Choose your account): the cursor is on “Google account”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-51.webp)

**Step 51 of 72.** Click your **Google account** to continue.

#### Step 52: Allow Sheets access

Google is asking what n8n is allowed to do. Check the first box — this lets n8n read and write your spreadsheets.

![An n8n node’s settings window in Stepthrough’s practice copy, step 52 of 72 (Allow Sheets access): the cursor is on “See, edit, create, and delete all your Google Sheets…”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-52.webp)

**Step 52 of 72.** Google needs permission. Check **See, edit, create, and delete all your Google Sheets spreadsheets**.

#### Step 53: Allow Drive access

Second box — n8n needs Drive access so it can find your spreadsheets by name.

![An n8n node’s settings window in Stepthrough’s practice copy, step 53 of 72 (Allow Drive access): the cursor is on “See, edit, create, and delete all of your Google Drive files”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-53.webp)

**Step 53 of 72.** Check **See, edit, create, and delete all of your Google Drive files**.

#### Step 54: Allow external service

Last one — this lets Google connect to n8n as an external service. Check it.

![An n8n node’s settings window in Stepthrough’s practice copy, step 54 of 72 (Allow external service): the cursor is on “Connect to an external service”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-54.webp)

**Step 54 of 72.** Check **Connect to an external service**.

#### Step 55: Sign in

All three checked.

![An n8n node’s settings window in Stepthrough’s practice copy, step 55 of 72 (Sign in): the cursor is on “Continue”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-55.webp)

**Step 55 of 72.** All three are checked. Click **Continue** to complete the Google sign-in.

#### Step 56: Pick the operation

Now we tell the node what to do. By default it reads rows, but we want to add rows.

![An n8n node’s settings window in Stepthrough’s practice copy, step 56 of 72 (Pick the operation): the cursor is on “Operation”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-56.webp)

**Step 56 of 72.** Now tell n8n what to do with the sheet. Click the **Operation** dropdown.

#### Step 57: Append Row

Append row. Every showing the agent logs gets added as a new row at the bottom of the sheet.

![A dropdown menu in n8n in Stepthrough’s practice copy, step 57 of 72 (Append Row): the cursor is on “Append Row”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-57.webp)

**Step 57 of 72.** Pick **Append Row** — the agent will add a new row for each showing.

#### Step 58: Choose the spreadsheet

Now pick the spreadsheet.

![An n8n node’s settings window in Stepthrough’s practice copy, step 58 of 72 (Choose the spreadsheet): the cursor is on “Document”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-58.webp)

**Step 58 of 72.** Click the **Document** dropdown to pick which spreadsheet to write to.

#### Step 59: Showing Feedback Log

Showing Feedback Log — the sheet we set up with columns for the date, the buyer's agent, interest, price feedback, and follow-up.

![A dropdown menu in n8n in Stepthrough’s practice copy, step 59 of 72 (Showing Feedback Log): the cursor is on “Showing Feedback Log”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-59.webp)

**Step 59 of 72.** Click **Showing Feedback Log** — the sheet we set up for Meridian.

#### Step 60: Pick the sheet tab

Now pick which tab inside that spreadsheet.

![An n8n node’s settings window in Stepthrough’s practice copy, step 60 of 72 (Pick the sheet tab): the cursor is on “Sheet”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-60.webp)

**Step 60 of 72.** Click the **Sheet** dropdown to choose which tab inside the spreadsheet.

#### Step 61: Sheet1

Sheet one — it is the only tab, so this is simple.

![A dropdown menu in n8n in Stepthrough’s practice copy, step 61 of 72 (Sheet1): the cursor is on “Sheet1”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-61.webp)

**Step 61 of 72.** Click **Sheet1**.

#### Step 62: Map the Date column

Now the columns. Each column has a purple button — click it and the AI agent figures out what data goes there.

![An n8n node’s settings window in Stepthrough’s practice copy, step 62 of 72 (Map the Date column): the cursor is on “✦”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-62.webp)

**Step 62 of 72.** Under **Values to Send**, click the **✦** button next to **Date** — the AI agent will fill this in automatically.

#### Step 63: Map the Buyer's agent column

Buyer's agent. Same thing — click the purple button.

![An n8n node’s settings window in Stepthrough’s practice copy, step 63 of 72 (Map the Buyer's agent column): the cursor is on “✦”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-63.webp)

**Step 63 of 72.** Click the **✦** button next to **Buyer's agent**.

#### Step 64: Map the Interest column

Interest.

![An n8n node’s settings window in Stepthrough’s practice copy, step 64 of 72 (Map the Interest column): the cursor is on “✦”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-64.webp)

**Step 64 of 72.** Click the **✦** button next to **Interest**.

#### Step 65: Map the Price feedback column

Price feedback.

![An n8n node’s settings window in Stepthrough’s practice copy, step 65 of 72 (Map the Price feedback column): the cursor is on “✦”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-65.webp)

**Step 65 of 72.** Click the **✦** button next to **Price feedback**.

#### Step 66: Map the Follow-up column

And follow-up. Each one is now set to defined automatically by the model — the agent reads your column headers and figures out what goes where.

![An n8n node’s settings window in Stepthrough’s practice copy, step 66 of 72 (Map the Follow-up column): the cursor is on “✦”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-66.webp)

**Step 66 of 72.** Click the **✦** button next to **Follow-up**.

#### Step 67: Back to the canvas

The sheets tool is fully wired up — credential, operation, spreadsheet, sheet, and column mapping. Close it and let us test this thing.

![An n8n node’s settings window in Stepthrough’s practice copy, step 67 of 72 (Back to the canvas): the cursor is on “×”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-67.webp)

**Step 67 of 72.** Google Sheets is fully configured. Close the node with the **×**.

### Part 12: Test the agent

#### Step 68: Open the chat

Everything is connected. Time to see if it works.

![The n8n workflow editor in Stepthrough’s practice copy, step 68 of 72 (Open the chat): the cursor is on “Open chat”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-68.webp)

**Step 68 of 72.** Time to test. Click **Open chat** at the bottom of the canvas.

#### Step 69: Paste this week's feedback

Give it this week's feedback for 14 Orchard Lane, the way it actually arrives: three buyer's agents, three different messages.

![The n8n chat test panel in Stepthrough’s practice copy, step 69 of 72 (Paste this week's feedback): the prompt is ready to paste, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-69.webp)

**Step 69 of 72.** Type a prompt — give the agent three showings of feedback for **14 Orchard Lane**.

```text
Log this feedback for 14 Orchard Lane: Oct 14, Dana Ruiz of Keystone Homes: buyers loved the kitchen and the yard, worried about road noise, think it is about $15,000 high. Oct 15, Marcus Hill of Hill & Co.: second showing, his buyers plan to write an offer this week and asked how old the roof is. Oct 15, Priya Shah of Open Door Realty: nice house, but her buyers need four bedrooms, so it is not a fit.
```

#### Step 70: Send the message

Send it off. The agent reads your system prompt and turns each showing into one entry, with an interest level, the price comment in the agent’s own words, and the next step.

![The n8n chat test panel in Stepthrough’s practice copy, step 70 of 72 (Send the message): the cursor is on “send arrow”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-70.webp)

**Step 70 of 72.** Click the **send arrow** to talk to the agent.

#### Step 71: Save to the sheet

Three showings: some interest with a price comment, a buyer ready to write an offer, and one that's simply not a fit. The agent flagged the one that needs you today: send Marcus the roof age. And notice it didn't suggest cutting the price. Now tell it to save them. This is where the Google Sheets tool kicks in.

![The n8n chat test panel in Stepthrough’s practice copy, step 71 of 72 (Save to the sheet): the prompt is ready to paste, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-71.webp)

**Step 71 of 72.** Marcus Hill’s buyers plan to write an offer this week, and the agent flagged it. Now tell the agent to save the showings to Google Sheets.

#### Step 72: Send it

Send it. The agent uses the Google Sheets tool to write each showing as a row — date, buyer's agent, interest, price feedback, and follow-up.

![The n8n chat test panel in Stepthrough’s practice copy, step 72 of 72 (Send it): the cursor is on “send arrow”, highlighted.](https://learn.ynteractive.com/content/guide/real-estate-showing-feedback-agent/step-72.webp)

**Step 72 of 72.** Click the **send arrow** — the agent will use the Google Sheets tool to write the rows.

**Part of these free courses:** [AI for Real Estate](https://learn.ynteractive.com/courses/ai-for-real-estate)

### Now do it yourself, free

Reading the steps is a start. Doing them is how it sticks. The interactive lesson puts you in a practice copy of n8n: you do every step yourself, it checks your work, and “Do it for me” finishes any step you get stuck on. Nothing touches your real accounts.

[Practice “Build an n8n AI Agent That Turns Showing Feedback into a Seller Update” step by step](https://learn.ynteractive.com/modules/real-estate-showing-feedback-agent?after=guide)

## The example: three showings at 14 Orchard Lane

Meridian Realty Group is a made-up brokerage, and 14 Orchard Lane is its made-up listing. Three buyer's agents send feedback: one says their buyers loved the kitchen but worry about road noise and think the home is about $15,000 high; one says their buyers are coming back and plan to write an offer this week, but want to know how old the roof is; and one says the house is nice but their buyers need four bedrooms.

The agent turns that into three entries: Some interest with the price comment quoted, High interest with "send the roof age today" as the follow-up, and None with no follow-up needed. Then it saves all three to the Showing Feedback Log sheet, one row per showing, ready for the weekly seller update.

## Who this lesson is for

Listing agents, real-estate assistants, transaction coordinators and team leads who send sellers a weekly update. You don't need to code: you click through n8n's editor, paste a system prompt and map five columns. The practice copy needs no n8n, OpenAI or Google account.

It is part of the AI for Real Estate course.

## The two rules that keep sellers' trust

The system prompt says to record only what was said, and never to recommend a price change. "About $15,000 high" is one buyer's agent's opinion, and the log keeps it in their words. The price conversation belongs to the listing agent and the seller.

It also says never to include buyers' names or personal details. The log names the buyer's agent and their brokerage, and nothing about the buyers themselves.

## Why an agent and not just a chat

- The fixed interest levels (High, Some, None, Unclear) make the sheet quick to read, and vague feedback is flagged as Unclear instead of guessed.
- Memory lets you say "save those" after it sorts the feedback.
- The Google Sheets tool writes the rows itself, so the log fills in without copying and pasting.
- The same workflow works for every listing: paste the week's feedback, check the rows, share the sheet.

## Try it yourself, free

Reading the steps is a start. Doing them is how it sticks. The interactive module walks you through every click in a practice copy of n8n, checks each step, and never touches your real accounts.

[Start “Build an n8n AI Agent That Turns Showing Feedback into a Seller Update”](https://learn.ynteractive.com/modules/real-estate-showing-feedback-agent)

## Frequently asked questions

**Can an AI agent organize showing feedback for sellers?**

Yes. In the lesson an n8n AI agent turns pasted feedback into one entry per showing (date, buyer's agent, interest, price feedback, follow-up) and saves each one as a row in Google Sheets. You read every row before sharing it.

**Will the agent tell me to lower the price?**

No. The system prompt says to record only what was said and never recommend a price change. Price feedback is quoted in the buyer's agent's own words.

**What do I need to build it for real?**

An n8n account (the cloud trial or self-hosted), an OpenAI API key with a few dollars of credit, and a Google account for the sheet. Logging a week of showings costs fractions of a cent.

**What should I leave out of the feedback I paste?**

Buyers' names, phone numbers and personal details. Follow your brokerage's rules on what you share with sellers.

**Is this lesson free?**

Yes. Stepthrough is completely free and the practice copy needs no accounts.

[Start this module free](https://learn.ynteractive.com/modules/real-estate-showing-feedback-agent)

## More n8n tutorials

- [Lovable + n8n: Build a Web App with an AI Backend](https://learn.ynteractive.com/content/lovable-n8n-web-app-ai-backend): Build a contact form in Lovable and connect it to an n8n workflow — webhook trigger, AI Agent, Google Sheets, Gmail, and a Respond node that ties it all together.
- [AI Receipt Extractor: Receipts to Google Sheets with n8n](https://learn.ynteractive.com/content/ai-receipt-extractor-n8n-google-sheets): Drop a photo of a receipt into an n8n chat. An AI agent reads it, pulls out the date, vendor and amount, picks a category, and adds a row to Google Sheets.
- [n8n AI Email Responder: Draft Gmail Replies Automatically](https://learn.ynteractive.com/content/ai-email-responder-gmail-drafts-n8n): Build an n8n agent that watches your Gmail, reads each new customer email, and writes a reply as a draft in the same thread, ready for you to check and send.
- [Daily Job Alerts: Email Each Tech Their Jobs from Google Sheets with n8n](https://learn.ynteractive.com/content/n8n-daily-job-alerts-google-sheets-gmail): Every morning at 7, n8n reads a plumbing company's jobs sheet, skips anything not assigned yet, and emails each job to the tech it's assigned to — customer, address…
- [Gmail AI Triage: Auto-Label Every Email and Draft Replies](https://learn.ynteractive.com/content/gmail-ai-triage-labels-drafts-n8n): Build an n8n workflow that reads each new email, sorts it as a lead, a client or an invoice with a Text Classifier, adds the matching Gmail label, and drafts a reply to…
- [A Support Agent That Answers from Your Own Docs](https://learn.ynteractive.com/content/support-agent-answers-from-your-docs-n8n): Turn an n8n chat agent into a support agent that answers only from your policies in a Google Doc, refuses what it should, and hands off to a person by email.

## From the blog

- [n8n Showing Feedback Agent FAQ: Real Estate Setup](https://learn.ynteractive.com/content/blog/n8n-showing-feedback-agent-faq): Plain answers about an n8n AI agent that turns buyer agents' showing feedback into one row per showing in Google Sheets for the weekly seller update.
- [n8n Showing Feedback Agent: 9 Mistakes to Avoid](https://learn.ynteractive.com/content/blog/n8n-showing-feedback-agent-mistakes): Mistakes that hurt an n8n showing feedback agent for listing agents, from price advice and buyers' names to mismatched columns and missing memory.

[All blog posts](https://learn.ynteractive.com/content/blog)

## Visual guides

This lesson’s key ideas as quick visual guides: swipe through the slides, or read the same guide as text.

- [Build your first AI agent in n8n](https://learn.ynteractive.com/content/visual/agent-can-act-quote): ChatGPT answers. An agent does something with the answer.
- [5 Steps to an n8n AI Agent That Saves to Google Sheets](https://learn.ynteractive.com/content/visual/5-steps-n8n-ai-agent-google-sheets): A visual guide: build an n8n AI agent that writes social media ideas and saves each one as a Google Sheets row, in 5 steps from the free lesson.
- [Myth: An AI Model Looks Things Up Before It Answers](https://learn.ynteractive.com/content/visual/myth-ai-models-look-things-up): Myth vs fact: by default a large language model answers from its training plus your prompt. Web search or file lookup is a separate step.

[All visual guides](https://learn.ynteractive.com/content/visual)

## Free cheat sheets

Print it or save the PDF: the key steps and checks from this lesson on one page, free.

- [n8n AI Agent to Google Sheets Cheat Sheet](https://learn.ynteractive.com/content/cheat-sheets/n8n-ai-agent-google-sheets): A free one-page cheat sheet for an n8n AI agent: chat trigger, AI Agent, system message, OpenAI model, Simple Memory and a Google Sheets tool.
- [Lovable + n8n Form Flow Cheat Sheet](https://learn.ynteractive.com/content/cheat-sheets/lovable-n8n-form-flow): A free one-page cheat sheet: a Lovable form posts to an n8n webhook, and an AI Agent logs it in Google Sheets and replies by Gmail.
- [AI Glossary Cheat Sheet: 30 Terms in Plain English](https://learn.ynteractive.com/content/cheat-sheets/ai-glossary-top-30): A free one-page cheat sheet of 30 AI and automation terms in plain English: models, prompts, n8n workflows, apps and data.

[All free printable cheat sheets](https://learn.ynteractive.com/content/cheat-sheets)

## Terms in this lesson

Plain-English definitions, each with an example from a free lesson.

[A/B testing](https://learn.ynteractive.com/content/glossary/ab-testing) · [AI agent](https://learn.ynteractive.com/content/glossary/ai-agent) · [API key](https://learn.ynteractive.com/content/glossary/api-key) · [Append row](https://learn.ynteractive.com/content/glossary/append-row) · [Buyer persona](https://learn.ynteractive.com/content/glossary/buyer-persona) · [Chat Trigger](https://learn.ynteractive.com/content/glossary/chat-trigger) · [Customer acquisition cost (CAC)](https://learn.ynteractive.com/content/glossary/customer-acquisition-cost) · [Foundation model](https://learn.ynteractive.com/content/glossary/foundation-model)

[The full AI glossary](https://learn.ynteractive.com/content/glossary)

## Related prompts

- [Case study interview questions prompt](https://learn.ynteractive.com/content/prompts/case-study-interview-questions-prompt): Plan a client interview that gets a case study's before, during and after story in their own words, with follow-up probes and…
- [Email subject lines prompt](https://learn.ynteractive.com/content/prompts/email-subject-lines-prompt): Get ten honest subject lines for a finished email, each with preview text and a character count, grouped by approach so you can…
- [SEO meta description prompt](https://learn.ynteractive.com/content/prompts/seo-meta-description-prompt): Write short search-result descriptions for your web pages: what the page offers, who it is for and one reason to click, inside…
- [Social post ideas prompt](https://learn.ynteractive.com/content/prompts/social-post-ideas-prompt): A four-part ChatGPT prompt for social post ideas built on your services and real customer questions: platform, hook and call to…

[All free prompt templates](https://learn.ynteractive.com/content/prompts)

## Browse related tutorials

[AI for Real Estate (4)](https://learn.ynteractive.com/content/industry/real-estate) · [n8n tutorials (56)](https://learn.ynteractive.com/content/tool/n8n)