Sales data analyst AI agent
Ask questions about your sales in plain words: best products, cities, months and margins, answered with real numbers.
How it works
Trigger: Chat — you ask a question
- You ask, e.g. "which city grew most this month?".
- The agent reads your Sales sheet and does the maths.
- It answers with the key numbers and one insight.
- It can post the summary to Slack.
What it can do
Unlike a fixed flow, an agent decides which of its tools to use, in what order — and remembers the conversation.
- Totals, averages, growth and top-5 lists
- Margins by product, city or channel
- Short text tables for comparisons
System prompt
The instructions that shape the agent. It's already inside the n8n template — copy it into Make or Zapier, and adjust the YOUR_… parts.
You are a data analyst for YOUR_BUSINESS. You answer questions about our sales data with numbers. Today is {{ $now.toFormat('d LLLL yyyy') }}. Currency: YOUR_CURRENCY.
Tools:
- "Read sales": every order (date, order_id, customer, city, channel, product, quantity, revenue, cost).
- "Post to Slack": posts a finished summary to the team channel. Use only when the user asks to share.
How to answer:
1. Always read the data first. State the period you used.
2. Do the arithmetic carefully: totals, averages, growth vs the previous period, top 5 lists.
3. Answer in 3–6 lines with the key numbers, then one practical insight or question to dig into.
4. Show a small text table when comparing more than 3 items.
Rules:
- Never guess numbers. If the data doesn't answer the question, say what's missing.
- Gross margin = (revenue − cost) / revenue.
- Don't share individual customers' personal details in Slack posts.Safety rules
Built into the prompt and the tools:
- Never guesses numbers; says what data is missing
- Keeps customer details out of Slack posts
Uses your own AI key (Claude, OpenAI or another model). Cost depends on the model and conversation length — a small, fast model keeps most conversations to a fraction of a cent.
Diagram
Trigger AI Agent tool
Build it
Pick your tool — same automation, step by step.
Copy and paste straight into an n8n canvas (Ctrl+V), or download and use Import from File. Then connect your own credentials and replace every YOUR_… placeholder. AI steps use a Claude model node — swap it for OpenAI, Gemini or Ollama if you prefer.
Show code (198 lines)
{
"name": "Sales data analyst AI agent (Flowngn)",
"nodes": [
{
"parameters": {
"content": "## Sales data analyst AI agent\nAsk questions about your sales in plain words: best products, cities, months and margins, answered with real numbers.\n\n**Setup**\n1. Open each node and connect your own credentials.\n2. Replace every YOUR_… placeholder.\n3. Test once, then activate.\n\nFree template from Flowngn",
"height": 260,
"width": 340
},
"id": "2473c6c3-ceef-44d1-aca0-1bb2b8b2ff2e",
"name": "Setup notes",
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
-420,
-60
]
},
{
"parameters": {
"public": true,
"mode": "hostedChat",
"initialMessages": "Ask me anything about your sales: best products, cities, months, margins…",
"options": {
"responseMode": "lastNode"
}
},
"id": "2473c6c3-ceef-44d1-aca0-1bb2b8b2ff2e",
"name": "Analyst chat",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"typeVersion": 1.1,
"position": [
0,
0
],
"webhookId": "2473c6c3-ceef-44d1-aca0-1bb2b8b2ff2e"
},
{
"parameters": {
"options": {
"systemMessage": "=You are a data analyst for YOUR_BUSINESS. You answer questions about our sales data with numbers. Today is {{ $now.toFormat('d LLLL yyyy') }}. Currency: YOUR_CURRENCY.\n\nTools:\n- \"Read sales\": every order (date, order_id, customer, city, channel, product, quantity, revenue, cost).\n- \"Post to Slack\": posts a finished summary to the team channel. Use only when the user asks to share.\n\nHow to answer:\n1. Always read the data first. State the period you used.\n2. Do the arithmetic carefully: totals, averages, growth vs the previous period, top 5 lists.\n3. Answer in 3–6 lines with the key numbers, then one practical insight or question to dig into.\n4. Show a small text table when comparing more than 3 items.\n\nRules:\n- Never guess numbers. If the data doesn't answer the question, say what's missing.\n- Gross margin = (revenue − cost) / revenue.\n- Don't share individual customers' personal details in Slack posts."
}
},
"id": "2473c6c3-ceef-44d1-aca0-1bb2b8b2ff2e",
"name": "Analyst agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.9,
"position": [
300,
0
]
},
{
"parameters": {
"model": {
"__rl": true,
"value": "claude-sonnet-5",
"mode": "list"
},
"options": {}
},
"id": "2473c6c3-ceef-44d1-aca0-1bb2b8b2ff2e",
"name": "Claude model",
"type": "@n8n/n8n-nodes-langchain.lmChatAnthropic",
"typeVersion": 1.3,
"position": [
45,
220
]
},
{
"parameters": {
"contextWindowLength": 10
},
"id": "2473c6c3-ceef-44d1-aca0-1bb2b8b2ff2e",
"name": "Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"typeVersion": 1.3,
"position": [
215,
220
]
},
{
"parameters": {
"descriptionType": "manual",
"toolDescription": "Returns every order: date, order_id, customer, city, channel, product, quantity, revenue, cost.",
"operation": "read",
"documentId": {
"__rl": true,
"value": "YOUR_SPREADSHEET_ID",
"mode": "id"
},
"sheetName": {
"__rl": true,
"value": "Sales",
"mode": "name"
},
"options": {}
},
"id": "2473c6c3-ceef-44d1-aca0-1bb2b8b2ff2e",
"name": "Read sales",
"type": "n8n-nodes-base.googleSheetsTool",
"typeVersion": 4.5,
"position": [
385,
220
]
},
{
"parameters": {
"descriptionType": "manual",
"toolDescription": "Posts a finished summary to the team channel.",
"select": "channel",
"channelId": {
"__rl": true,
"value": "#numbers",
"mode": "name"
},
"text": "={{ $fromAI('summary', \"The summary to share\", 'string') }}",
"otherOptions": {}
},
"id": "2473c6c3-ceef-44d1-aca0-1bb2b8b2ff2e",
"name": "Post to Slack",
"type": "n8n-nodes-base.slackTool",
"typeVersion": 2.2,
"position": [
555,
220
]
}
],
"connections": {
"Analyst chat": {
"main": [
[
{
"node": "Analyst agent",
"type": "main",
"index": 0
}
]
]
},
"Claude model": {
"ai_languageModel": [
[
{
"node": "Analyst agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Memory": {
"ai_memory": [
[
{
"node": "Analyst agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Read sales": {
"ai_tool": [
[
{
"node": "Analyst agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Post to Slack": {
"ai_tool": [
[
{
"node": "Analyst agent",
"type": "ai_tool",
"index": 0
}
]
]
}
},
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"meta": {
"templateCredsSetupCompleted": false
},
"tags": []
}In Make, create a new scenario and add these modules in order:
- Webhooks › Custom webhook — called by your website's chat widget
- Make AI Agents › Run an agent — give it these tools: “Read sales” (Google Sheets), “Post to Slack” (Slack); paste the system prompt as the agent's instructions
- Every module run uses Make operations — the free plan includes a monthly quota.
- Module and step names can differ slightly as Make and Zapier update their apps.
In Zapier, create a new Zap and add these steps in order:
- Zapier Chatbots, or Webhooks by Zapier — Catch Hook from your chat widget
- Zapier Agents — create an agent (or AI by Zapier for a single step) — give it these tools: “Read sales” (Google Sheets), “Post to Slack” (Slack); paste the system prompt as the agent's instructions
- Zaps with more than two steps need a paid Zapier plan.
- Module and step names can differ slightly as Make and Zapier update their apps.
Tips
- Large sheets slow it down; keep the last 12 months in the Sales tab and archive the rest.
Related flows
AI AgentsAdvanced
Recruiting screening AI agent
Reads every application and CV, scores it against the job's must-haves, and flags strong candidates.
Webhook → AI model → Google Sheets → Slack15h/mo
AI AgentsAdvanced
Unpaid invoices collections AI agent
Every morning, the agent reviews overdue invoices, drafts polite reminders in the right tone, and flags the ones that need a call.
AI model → Google Sheets → Gmail → Slack10h/mo
AI AgentsAdvanced
IT helpdesk AI agent
Staff describe their IT problem in a chat; the agent walks them through known fixes and logs a ticket when needed.
AI model → Google Sheets → Slack15h/mo