# Build an AI Follow-Up Agent for HVAC Service Calls > Build an n8n AI agent that writes follow-up texts and emails after every HVAC service call and saves them to Google Sheets. Free, step by step, no code. Source: https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n · Updated 2026-11-03 · Free from Stepthrough (https://learn.ynteractive.com) ## Practice it step by step [Start the free practice](https://learn.ynteractive.com/modules/n8n-ai-agent-hvac) [Take the free module: why it matters, practice and a quick check →](https://learn.ynteractive.com/courses/ai-for-trades/6) 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/n8n-ai-agent-hvac) Free · Live now · [AI Automation for HVAC](https://learn.ynteractive.com/content/industry/hvac) · [n8n](https://learn.ynteractive.com/content/tool/n8n) · OpenAI · Google Sheets · ~12 min · 72 steps · Intermediate Updated November 3, 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) Most HVAC companies mean to follow up after every call and rarely do. In this free lesson you build an [AI agent](https://learn.ynteractive.com/content/glossary/ai-agent) in [n8n](https://learn.ynteractive.com/content/tool/n8n) for Cedar Ridge Heating & Air that takes a list of the day's completed calls, writes a follow-up for each one with a tip that fits the job, and saves them to a Google Sheet the office can review. ## At a glance | Question | Answer | | --- | --- | | What you build | Build an AI agent for Cedar Ridge Heating & Air that writes follow-up messages for completed service calls and saves them to Google Sheets — 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/n8n-ai-agent-hvac), watch the video | ### 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, Ask for follow-ups, 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 HVAC version follows the same build with its own example business, Cedar Ridge Heating & Air. ## Build an AI Follow-Up Agent for HVAC Service Calls: video walkthrough The whole lesson in 7:59, narrated step by step. **Simulated practice environment.** Recorded in Stepthrough’s simulated practice environment, not the live tool. Practice it yourself free at learn.ynteractive.com. 7:59 · 12 chapters · 72 steps · narrated with the lesson’s own voice-over ### Chapters Click a chapter to jump the video there. 1. [0:00 Intro: what you'll build](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=0#watch) 2. [0:11 Get n8n](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=11#watch) 3. [0:42 API key](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=42#watch) 4. [1:53 Chat trigger](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=113#watch) 5. [2:26 AI Agent](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=146#watch) 6. [2:42 System prompt](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=162#watch) 7. [3:24 Chat model](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=204#watch) 8. [4:12 Memory](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=252#watch) 9. [4:27 Sheets tool](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=267#watch) 10. [4:52 Create the spreadsheet](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=292#watch) 11. [5:41 Configure Sheets](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=341#watch) 12. [7:21 Test the agent](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=441#watch) ### Now do it yourself, free Watching is the warm-up. 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 AI Follow-Up Agent for HVAC Service Calls” step by step](https://learn.ynteractive.com/modules/n8n-ai-agent-hvac?after=video) ### Full transcript #### Intro: what you'll build [0:00](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=0#watch) Now we automate. You'll build an AI agent in n8n for Cedar Ridge heating and air. It writes a follow-up for every service call and saves each one to Google Sheets. Let's build it. #### Get n8n [0:10](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=10#watch) In the last lesson you built a Custom GPT that writes HVAC estimates. That is great for one person. But what if the AI wrote a follow-up for every finished service call and saved them to a spreadsheet the office can review? That is what we are building now. First, you need an n8n account. Click get started free. [0:26](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=26#watch) Type an email address. This is just practice, so anything works — it won't actually send anything. [0:32](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=32#watch) Now click continue. 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. #### API key [0:42](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=42#watch) 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. Click add to credit balance. [1:00](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=60#watch) Ten dollars goes a very long way. You are charged per request, not per month, and each batch of follow-ups costs fractions of a cent. Click continue — in your own account it asks for a card at this point. [1:11](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=71#watch) Balance sorted. Now go to [API](https://learn.ynteractive.com/content/glossary/api) keys in the left menu. [1:15](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=75#watch) Click create new secret key. [1:17](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=77#watch) 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. [1:24](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=84#watch) Default project, all permissions — that is fine for this. Create the key. [1:29](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=89#watch) 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. [1:40](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=100#watch) Click done. 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. #### Chat trigger [1:52](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=112#watch) 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. [2:00](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=120#watch) Every workflow needs a trigger — the thing that kicks it off. We want a chat trigger so you can tell the agent which calls were finished today. Click add first step. [2:09](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=129#watch) 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. [2:17](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=137#watch) 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. #### AI Agent [2:26](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=146#watch) Now we decide what happens when a message comes in. Click the plus on the right edge of the trigger. [2:31](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=151#watch) 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 day's service calls, and it can write the follow-ups and save them to a spreadsheet — all in one step. #### System prompt [2:42](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=162#watch) Right now this agent has no personality and no orders. It does not know it works for Cedar Ridge Heating and Air. Scroll down to options and click add option. [2:51](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=171#watch) Pick system message. This is the standing instruction the agent reads before every request. It is where we tell it who Cedar Ridge is, how the messages should sound, and how to format them. [3:01](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=181#watch) Here is the actual prompt. It describes Cedar Ridge Heating and Air, sets a friendly, plain tone, and tells the agent what to return: customer, service, follow-up message, channel, and send date. It also tells the agent to use the Google Sheets tool when you ask it to save. Click paste system prompt. [3:19](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=199#watch) That gives the agent everything it needs to know about Cedar Ridge. Close the node. #### Chat model [3:24](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=204#watch) 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. Click the plus under chat model. [3:34](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=214#watch) OpenAI chat model. This is where that API key finally gets used. [3:37](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=217#watch) And here is where that key you copied finally goes. Click the credential dropdown. [3:42](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=222#watch) You want create new credential, right at the bottom. [3:44](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=224#watch) Paste the key straight in. This is the one moment it matters that you copied it — remember, OpenAI never shows it to you again. [3:51](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=231#watch) Hit save. 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. [4:00](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=240#watch) Now the model dropdown. [4:02](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=242#watch) GPT five mini. Fast, cheap, and plenty for short follow-up messages. Do not reach for the expensive model until you have a reason. [4:09](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=249#watch) That is the brain wired in. Close it up. #### Memory [4:11](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=251#watch) Next, memory. Without this, every message starts from nothing — you could not say save those follow-ups, because it would not remember which ones you meant. Click the plus under memory. [4:20](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=260#watch) Simple memory is fine here — it keeps the recent conversation inside n8n, no database, no extra credentials. #### Sheets tool [4:27](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=267#watch) 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 follow-up into a spreadsheet the office can review. Click the plus under tool. [4:40](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=280#watch) 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 follow-ups, each one becomes a row. #### Create the spreadsheet [4:51](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=291#watch) 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. [4:58](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=298#watch) Switch to Google Sheets. You need to create the spreadsheet that this node will write to. [5:02](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=302#watch) First, name it so you can find it later. Click the title up top — it says untitled spreadsheet — and type Service Follow-Ups. [5:09](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=309#watch) Now set up the column headers. These need to match what the system prompt tells the agent to return. In A1, type Customer. [5:17](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=317#watch) B1 — Service. [5:19](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=319#watch) C1 — Follow-up Message. [5:21](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=321#watch) D1 — Channel. [5:22](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=322#watch) And E1 — Send Date. Five columns, matching exactly what the system prompt tells the agent to return. Each follow-up becomes a row in this sheet. [5:31](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=331#watch) The spreadsheet is ready. Switch back to n8n and connect the Google Sheets node to it. [5:35](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=335#watch) Double click the Google Sheets node to open it back up. Now we can connect it to the spreadsheet we just made. #### Configure Sheets [5:41](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=341#watch) Now we need to connect this to a real Google account. Click the credential dropdown. [5:45](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=345#watch) Create new credential — this one uses Google OAuth instead of an API key, so it is going to open a sign-in window. [5:52](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=352#watch) Click sign in with Google. This opens the Google account chooser so you can pick which account to connect. [5:58](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=358#watch) Pick the Google account you want n8n to use. This is the account that owns the spreadsheet. [6:03](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=363#watch) Google is asking what n8n is allowed to do. Check the first box — this lets n8n read and write your spreadsheets. [6:10](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=370#watch) Second box — n8n needs Drive access so it can find your spreadsheets by name. [6:15](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=375#watch) Last one — this lets Google connect to n8n as an external service. Check it. [6:20](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=380#watch) All three checked. Click continue and Google hands the credential back to n8n. [6:24](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=384#watch) Now we tell the node what to do. By default it reads rows, but we want to add rows. Click the operation dropdown. [6:30](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=390#watch) Append row. Every follow-up the agent writes gets added as a new row at the bottom of the sheet. [6:36](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=396#watch) Now pick the spreadsheet. Click the document dropdown. [6:39](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=399#watch) Service Follow-Ups — the sheet we set up with columns for customer, service, message, channel, and send date. [6:44](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=404#watch) Now pick which tab inside that spreadsheet. Click the sheet dropdown. [6:48](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=408#watch) Sheet one — it is the only tab, so this is simple. [6:51](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=411#watch) Now the columns. Each column has a purple button — click it and the AI agent figures out what data goes there. Click the purple button next to Customer. [6:59](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=419#watch) Service. Same thing — click the purple button. [7:02](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=422#watch) Follow-up message. [7:03](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=423#watch) Channel. [7:05](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=425#watch) And send date. Each one is now set to defined automatically by the model — the agent reads your column headers and figures out what goes where. [7:12](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=432#watch) The sheets tool is fully wired up — credential, operation, spreadsheet, sheet, and column mapping. Close it and let us test this thing. #### Test the agent [7:21](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=441#watch) Everything is connected. Time to see if it works. Click open chat at the bottom of the canvas. [7:25](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=445#watch) Give it today's finished service calls. Paste this prompt and see what comes back. [7:30](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=450#watch) Send it off. The agent reads your system prompt and writes a follow-up for each call in the exact format you asked for. [7:36](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=456#watch) Three follow-ups — two texts and an email for the new install, each with a tip that fits the job. Now tell it to save them. This is where the Google Sheets tool kicks in. [7:45](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=465#watch) Send it. The agent uses the Google Sheets tool to write each follow-up as a row — customer, service, message, channel, and send date. [7:53](https://learn.ynteractive.com/content/hvac-service-follow-up-ai-agent-n8n?t=473#watch) Simple as that. We show you and you do it. Sign up below to learn AI automation for free. ## What you will build You build a working AI agent inside n8n, a tool that connects apps into automated workflows. You type the day's finished calls into a chat: Linda Morales, furnace tune-up. Tom Becker, replaced AC capacitor. Grace Chen, new heat pump install. The agent writes three follow-ups. Linda gets a text with a filter reminder for heating season. Tom gets a text about keeping plants two feet from the outdoor unit, plus one mention of the Comfort Club maintenance plan, because his was a repair. Grace gets an email, because installs get email, with a tip about picking a steady thermostat setting. Then you say 'Yes, save those follow-ups to the sheet' and the agent writes each one as a row in a spreadsheet called Service Follow-Ups, with columns for Customer, Service, Follow-up Message, Channel and Send Date. ## Who this is for Owners and office managers at small residential HVAC companies who know follow-ups bring in reviews, repeat work and maintenance plan sign-ups, but never find the time to write them. It is also a good second step if you finished the HVAC estimate writer lesson and want AI to do work without you copying and pasting. ## The rules that keep follow-ups on brand The system prompt tells the agent to sound like the office manager, not a salesperson. Every message thanks the customer by first name, names the work, adds one practical tip that fits the job, and invites them to reply or call. The Comfort Club plan is mentioned only after a repair, and only once, so tune-up customers who already have the plan are not pitched again. Texts stay under 300 characters. Installs go by email. The agent is told never to invent prices, discounts or warranty terms. ## Why it works An agent is different from a chatbot because it can act. The Google Sheets tool is what lets it write rows instead of just talking. Memory is what makes the second message work. Without it, 'save those follow-ups' means nothing. The spreadsheet gives the office a place to check every message before it goes out, which matters when a message is going to a homeowner who just paid you. ## What a good HVAC follow-up looks like A follow-up is not a sales email. The best ones are short, personal and useful, and the tip is what makes them useful. A furnace tune-up customer hears about changing the filter every one to three months in heating season. A repair customer with a failed capacitor hears about keeping the outdoor unit clear so it can breathe. A new heat pump owner hears that big thermostat swings make the system work harder, which heads off the classic 'my heat pump isn't keeping up' call in the first cold week. The channel matters too. A quick text suits a tune-up or a small repair. A new install is a big purchase, so it gets a longer email that points to the warranty registration details in the install paperwork. The send date spaces them out: texts the next day, the install email a few days later, after the family has lived with the new system. Those small choices are written into the system prompt once, and the agent applies them to every call you give it. ## How to use this in your HVAC business Swap in your own company details, tips and maintenance plan name. At the end of the day, paste in the completed calls from your dispatch board and let the agent draft the batch. In spring and fall, when tune-ups stack up, one prompt can cover a full day of calls. After the first cold snap or heat wave, the same agent helps you thank every emergency customer and point repair customers toward a maintenance plan. The lesson covers writing and saving the messages; sending them is a step you add later. ## 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 AI Follow-Up Agent for HVAC Service Calls”](https://learn.ynteractive.com/modules/n8n-ai-agent-hvac) ## Step by step: Build an AI Follow-Up Agent for HVAC Service Calls All 72 steps of the interactive module, in order. In the module you watch each one, then do it yourself in a practice copy that checks your work. ### 1. Get n8n 1. **Go to n8n.io.** Start at **n8n.io**. Click **Get started free**. In the last lesson you built a Custom GPT that writes HVAC estimates. That is great for one person. But what if the AI wrote a follow-up for every finished service call and saved them to a spreadsheet the office can review? That is what we are building now. First, you need an n8n account. 2. **Enter your email.** Type any email address — this is practice, so a fake one is fine. This is just practice, so anything works — it won't actually send anything. 3. **Sign up.** Click **Continue**. n8n emails you a code, then asks for a name and password — do that part on your own and come back here. 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. ### 2. API key 4. **Add credit first.** Practice only: no card, no charge. Your agent needs a model to think with, and in the real world that is an OpenAI key with a little credit behind it. This is **platform.openai.com → Billing**. Click **Add to credit balance**. (Rather not spend anything later? New n8n accounts include free credits: pick **Gateway credits** on the model step instead of a key.) Your agent needs a brain, and that means an 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. In your own n8n, you can pick gateway credits on the model step and skip the key. 5. **Ten dollars is plenty.** Ten dollars goes a long way — you pay per request, not per month. Click **Continue**. In your own account you add a card here. Ten dollars goes a very long way. You are charged per request, not per month, and each batch of follow-ups costs fractions of a cent. 6. **Now the key.** Balance sorted. Click **API Keys** in the left menu. Balance sorted. Now go to API keys in the left menu. 7. **Create a secret key.** Click **+ Create new secret key**. 8. **Name the key.** Name it after what will use it. Type **n8n agent**. 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. 9. **Create it.** Leave Project and Permissions alone and click **Create secret key**. Default project, all permissions — that is fine for this. Create the key. 10. **Copy it now.** This is the only time OpenAI shows you the key. Click **Copy**, then paste it somewhere safe. 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. 11. **Back to n8n.** Click **Done**. Treat that key like a password — never paste it into a chat, a repo, or a screen recording. 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. ### 3. New workflow 12. **Start a new workflow.** This is your n8n home. Click **Create workflow** in the top right. 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. ### 4. Chat trigger 13. **Add the first step.** Every workflow starts with a trigger. Click **Add first step…** Every workflow needs a trigger — the thing that kicks it off. We want a chat trigger so you can tell the agent which calls were finished today. 14. **Trigger on a chat message.** The trigger panel opened on the right. Pick **On chat message** near the bottom. 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. 15. **Back to the canvas.** n8n opens the node so you can configure it. Nothing to change here — click the **×** in the top right. 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. ### 5. AI Agent 16. **Add the next node.** Click the **+** on the right edge of the trigger node. Now we decide what happens when a message comes in. 17. **Open the AI nodes.** The **What happens next?** panel opens with categories. Click **AI** at the top. A panel opens and asks what happens next. The agent lives under AI, right at the top. 18. **Add the AI Agent.** In **AI Nodes**, click **AI Agent** — it makes a plan and carries it out using the tools you give it. 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 day's service calls, and it can write the follow-ups and save them to a spreadsheet — all in one step. ### 6. System prompt 19. **Open the options.** The agent has no personality yet. Click **+ Add Option** under Options. Right now this agent has no personality and no orders. It does not know it works for Cedar Ridge Heating and Air. 20. **Add a system message.** Choose **System Message**. This is the standing instruction the agent follows every time. Pick system message. This is the standing instruction the agent reads before every request. It is where we tell it who Cedar Ridge is, how the messages should sound, and how to format them. 21. **Write the system prompt.** 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. Here is the actual prompt. It describes Cedar Ridge Heating and Air, sets a friendly, plain tone, and tells the agent what to return: customer, service, follow-up message, channel, and send date. It also tells the agent to use the Google Sheets tool when you ask it to save. ```text You are the customer follow-up assistant for Cedar Ridge Heating & Air. Cedar Ridge Heating & Air is a small, family-owned company that installs, repairs and maintains furnaces, air conditioners and heat pumps in homes. The audience is homeowners whose service call was just completed. The tone should be friendly, plain, professional and brief. Sound like the office manager, not a salesperson. Your job is to write a follow-up message for each completed service call the user gives you. For each message: - Thank the customer by first name and name the work that was done - Add one practical tip that fits the job (filters, thermostat, keeping the outdoor unit clear) - Invite them to reply or call the office if anything seems off - Mention the Comfort Club maintenance plan only after a repair, and only once For each follow-up, return: - Customer - Service - Follow-up Message - Channel (Text or Email) - Send Date Keep text messages under 300 characters. Use email for installs. When the user asks you to save the follow-ups, use the Google Sheets tool to store each one. Do not invent prices, discounts or warranty terms. ``` 22. **Back to the canvas.** That tells the agent who it works for and how to write follow-ups. Close the node with the **×**. That gives the agent everything it needs to know about Cedar Ridge. Close the node. ### 7. Chat model 23. **Give the agent a brain.** The agent has a red warning: it has no model. Click the **+** under **Chat Model**. 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. 24. **Pick OpenAI.** Click **OpenAI Chat Model**. OpenAI chat model. This is where that API key finally gets used. 25. **Open the credentials.** Here is where that key goes. Click the **Credential** dropdown. And here is where that key you copied finally goes. 26. **Create a new credential.** Click **+ Create new credential** at the bottom of the list. (Free credits instead? Pick **Gateway credits** in your own n8n.) 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. 27. **Paste the key.** Paste in the API key on the field to drop in the key you copied from OpenAI. This is the one moment it matters that you copied it — remember, OpenAI never shows it to you again. 28. **Save the credential.** Click **Save**. n8n tests the connection and stores the key for every future node. 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. 29. **Open the model list.** A new credential leaves **Model** on **Select a model...**. Click the **Model** dropdown. Now the model dropdown. 30. **Choose the model.** Pick **gpt-5-mini** — fast and cheap, plenty for this. (The list is long: type **gpt-5-mini** in **Search...** to find it.) GPT five mini. Fast, cheap, and plenty for short follow-up messages. Do not reach for the expensive model until you have a reason. 31. **Back to the canvas.** The model is wired up. Close the node with the **×**. That is the brain wired in. Close it up. ### 8. Memory 32. **Add memory.** Without memory the agent forgets each message. Click the **+** under **Memory**. Next, memory. Without this, every message starts from nothing — you could not say save those follow-ups, because it would not remember which ones you meant. 33. **Simple Memory.** Pick **Simple Memory**. It keeps the recent conversation in n8n itself. Simple memory is fine here — it keeps the recent conversation inside n8n, no database, no extra credentials. 34. **Back to the canvas.** n8n opens **Simple Memory** so you can set it up. The defaults are fine (it keeps the last 5 messages). Close it with the **×**. 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. ### 9. Sheets tool 35. **Add a tool.** Tools are how the agent acts on the world. Click the **+** under **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 follow-up into a spreadsheet the office can review. 36. **Search for Sheets.** Google Sheets is not in **Recommended Tools**. In **Search nodes...**, type **sheets**. Google Sheets is not in the recommended tools, so search for it. 37. **Add Google Sheets.** Click **Google Sheets Tool** — read, update and write data to 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 follow-ups, each one becomes a row. ### 10. Create the spreadsheet 38. **Back to the canvas.** Before we configure this node, we need a spreadsheet for the agent to write to. Close the node — we will come back. 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. 39. **Open Google Sheets.** Click the **Google Sheets** tab to create a new blank spreadsheet. Switch to Google Sheets. You need to create the spreadsheet that this node will write to. 40. **Name the spreadsheet.** Click the title and rename it to **Service Follow-Ups**. First, name it so you can find it later. 41. **Type the first column header.** In cell **A1**, type **Customer**. Now set up the column headers. These need to match what the system prompt tells the agent to return. In A1, type Customer. 42. **Service.** In cell **B1**, type **Service**. B1 — Service. 43. **Follow-up Message.** In cell **C1**, type **Follow-up Message**. C1 — Follow-up Message. 44. **Channel.** In cell **D1**, type **Channel**. D1 — Channel. 45. **Send Date.** In cell **E1**, type **Send Date**. That is all five columns — matching the system prompt. And E1 — Send Date. Five columns, matching exactly what the system prompt tells the agent to return. Each follow-up becomes a row in this sheet. 46. **Back to n8n.** The spreadsheet is ready. Click the **n8n** tab to go back and connect it. The spreadsheet is ready. Switch back to n8n and connect the Google Sheets node to it. 47. **Open the Sheets node.** Double-click the Google Sheets node (n8n named it **Get row(s) in sheet in Google Sheets**) to configure it. Double click the Google Sheets node to open it back up. Now we can connect it to the spreadsheet we just made. ### 11. Configure Sheets 48. **Add a credential.** The Sheets node needs a Google account. Click the **Credential** dropdown. Now we need to connect this to a real Google account. 49. **Create a new credential.** Click **+ Create new credential** to sign in with Google. Create new credential — this one uses Google OAuth instead of an API key, so it is going to open a sign-in window. 50. **Sign in with Google.** Click **Sign in with Google** to connect your account. This opens the Google account chooser so you can pick which account to connect. 51. **Choose your account.** Click your **Google account** to continue. Pick the Google account you want n8n to use. This is the account that owns the spreadsheet. 52. **Allow Sheets access.** Google needs permission. Check **See, edit, create, and delete all your Google Sheets spreadsheets**. Google is asking what n8n is allowed to do. Check the first box — this lets n8n read and write your spreadsheets. 53. **Allow Drive access.** Check **See, edit, create, and delete all of your Google Drive files**. Second box — n8n needs Drive access so it can find your spreadsheets by name. 54. **Allow external service.** Check **Connect to an external service**. Last one — this lets Google connect to n8n as an external service. Check it. 55. **Sign in.** All three are checked. Click **Continue** to complete the Google sign-in. All three checked. 56. **Pick the operation.** Now tell n8n what to do with the sheet. Click the **Operation** dropdown. Now we tell the node what to do. By default it reads rows, but we want to add rows. 57. **Append Row.** Pick **Append Row** — the agent will add a new row for each follow-up. Append row. Every follow-up the agent writes gets added as a new row at the bottom of the sheet. 58. **Choose the spreadsheet.** Click the **Document** dropdown to pick which spreadsheet to write to. Now pick the spreadsheet. 59. **Service Follow-Ups.** Click **Service Follow-Ups** — the sheet we set up for Cedar Ridge. Service Follow-Ups — the sheet we set up with columns for customer, service, message, channel, and send date. 60. **Pick the sheet tab.** Click the **Sheet** dropdown to choose which tab inside the spreadsheet. Now pick which tab inside that spreadsheet. 61. **Sheet1.** Click **Sheet1**. Sheet one — it is the only tab, so this is simple. 62. **Map the Customer column.** Under **Values to Send**, click the **✦** button next to **Customer** — the AI agent will fill this in automatically. Now the columns. Each column has a purple button — click it and the AI agent figures out what data goes there. 63. **Map the Service column.** Click the **✦** button next to **Service**. Service. Same thing — click the purple button. 64. **Map the Follow-up Message column.** Click the **✦** button next to **Follow-up Message**. Follow-up message. 65. **Map the Channel column.** Click the **✦** button next to **Channel**. Channel. 66. **Map the Send Date column.** Click the **✦** button next to **Send Date**. And send date. Each one is now set to defined automatically by the model — the agent reads your column headers and figures out what goes where. 67. **Back to the canvas.** Google Sheets is fully configured. Close the node with the **×**. The sheets tool is fully wired up — credential, operation, spreadsheet, sheet, and column mapping. Close it and let us test this thing. ### 12. Test the agent 68. **Open the chat.** Time to test. Click **Open chat** at the bottom of the canvas. Everything is connected. Time to see if it works. 69. **Ask for follow-ups.** Type a prompt — give the agent today's completed service calls. Give it today's finished service calls. ```text Write follow-ups for today's completed calls: Linda Morales, furnace tune-up. Tom Becker, replaced AC capacitor. Grace Chen, new heat pump install. ``` 70. **Send the message.** Click the **send arrow** to talk to the agent. Send it off. The agent reads your system prompt and writes a follow-up for each call in the exact format you asked for. 71. **Save to the sheet.** Now tell the agent to save those follow-ups to Google Sheets. Three follow-ups — two texts and an email for the new install, each with a tip that fits the job. Now tell it to save them. This is where the Google Sheets tool kicks in. 72. **Send it.** Click the **send arrow** — the agent will use the Google Sheets tool to write the rows. Send it. The agent uses the Google Sheets tool to write each follow-up as a row — customer, service, message, channel, and send date. [All free Stepthrough videos](https://learn.ynteractive.com/content/videos) ## Frequently asked questions **What does it cost to run this agent?** Stepthrough is free. For real use you need your own n8n and OpenAI accounts, and OpenAI charges per request. The lesson suggests adding ten dollars of credit, and a batch of short follow-ups uses a small fraction of that. Check each tool's current pricing. **Does the agent send the texts and emails for me?** Not in this lesson. It writes each follow-up and saves it to Google Sheets with a channel and send date, so the office can review before anything goes out. **Do I need to code to build an n8n AI agent?** No. You click nodes onto a canvas and paste a system prompt. The lesson is 69 short steps and takes about 12 minutes. **How does the interactive lesson work?** Each step is shown to you first on the left (Watch). Then you do it yourself in a practice copy on the right (Your turn), and every click is checked. If you get stuck, press Do it for me. It is a practice copy, so no real accounts are touched. **Will it push the maintenance plan on every customer?** No. The system prompt says to mention the Comfort Club plan only after a repair, and only once. [Start this module free](https://learn.ynteractive.com/modules/n8n-ai-agent-hvac) - Next in AI Automation for HVAC: [Build an AI Service Request Form for Your HVAC Company](https://learn.ynteractive.com/content/hvac-service-request-form-ai-lovable-n8n) ## 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 - [AI for Contractors: How to Book More Jobs With AI (Free)](https://learn.ynteractive.com/content/blog/ai-for-contractors): How HVAC, plumbing and electrical contractors can use AI to book more jobs: triage, quotes and follow-ups, with free lessons for each trade. - [Automate Customer Follow-Ups After Every Service Call](https://learn.ynteractive.com/content/blog/customer-follow-up-after-service-call): Customer follow-up after a service call, done every time: an n8n AI agent drafts each message with a job-specific tip and saves it for review. - [AI for HVAC Companies: Follow-Ups and Service Requests](https://learn.ynteractive.com/content/blog/ai-for-hvac-companies): AI for HVAC companies, made practical: an n8n agent that drafts every service follow-up, and a web form that spots emergencies and emails back. [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. - [HVAC follow-ups people actually read](https://learn.ynteractive.com/content/visual/hvac-not-a-sales-email-quote): A follow-up is not a sales email. The best ones are short, personal and useful, and the tip is what makes them useful. - [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. - [An AI follow-up agent for HVAC service calls](https://learn.ynteractive.com/content/visual/hvac-follow-ups): Most HVAC companies mean to follow up after every call and rarely do. [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. - [AI Quick-Start for HVAC Companies: Cheat Sheet](https://learn.ynteractive.com/content/cheat-sheets/ai-quick-start-hvac): A free one-page cheat sheet for HVAC offices: the free AI lessons to take in order, a missed-call text prompt and what AI must never decide. - [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. [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 · [AI agent](https://learn.ynteractive.com/content/glossary/ai-agent) · [API key](https://learn.ynteractive.com/content/glossary/api-key) · [API usage billing](https://learn.ynteractive.com/content/glossary/api-usage-billing) · [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) · Chatbot [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… - [Customer call notes summary prompt](https://learn.ynteractive.com/content/prompts/customer-call-notes-summary-prompt): A copy-ready prompt that turns raw customer call notes into a clean summary: needs, decisions, owners and next steps. Includes a… - [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… - [Home maintenance tips email prompt](https://learn.ynteractive.com/content/prompts/home-maintenance-tips-email-prompt): Write a seasonal home tips email from your own techs' advice: practical, safe for homeowners, one soft offer, and no scare… [All free prompt templates](https://learn.ynteractive.com/content/prompts) ## More terms on this topic Text-to-speech · [Zero-shot prompting](https://learn.ynteractive.com/content/glossary/zero-shot-prompting) ## More prompts on this topic - [Cancellation request reply prompt](https://learn.ynteractive.com/content/prompts/cancellation-request-reply-prompt): A ChatGPT prompt for confirming a cancellation gracefully: what ends and when, any refund in exact dollars, and at most one… - [Declined card notice prompt](https://learn.ynteractive.com/content/prompts/card-declined-notice-prompt): Tell a customer their card was declined without embarrassing them: what failed, the amount, a safe way to update it and what… - [Employee handbook section prompt](https://learn.ynteractive.com/content/prompts/employee-handbook-section-prompt): Turn your own rules into one plain-English handbook section, with every gap and anything touching pay, discipline or privacy… - [Maintenance agreement renewal prompt](https://learn.ynteractive.com/content/prompts/maintenance-agreement-renewal-prompt): A renewal email for a maintenance plan member: the visits they really had, the renewal terms stated plainly, and canceling made… - [Post-job care instructions prompt](https://learn.ynteractive.com/content/prompts/post-job-care-instructions-prompt): Turn your own care notes for one job type into a leave-behind sheet: what's normal, simple upkeep, what not to touch, and when… - [Review request email prompt](https://learn.ynteractive.com/content/prompts/review-request-email-prompt): A ChatGPT prompt for a short, personal email asking a happy customer for an honest review: the real job, your exact link, no… ## Browse related tutorials [AI for HVAC (2)](https://learn.ynteractive.com/content/industry/hvac) · [n8n tutorials (56)](https://learn.ynteractive.com/content/tool/n8n)