Daily Automated Executive Financial Briefing: Google Sheets + GPT-4o-mini + Notion + Telegram

Weekday 7 AM trigger → parallel fetch from 5 Google Sheets tabs → KPI calculation → GPT-4o-mini generates Telegram-formatted briefing → Notion archive + Telegram delivery → critical alert if revenue drops >10% → Slack error notification

Who

Operations or finance staff who need to push daily executive briefings, or small teams automating a CFO dashboard

You get

Receive an AI-generated Telegram financial briefing every weekday morning, with extra alerts on key metric anomalies and execution logs saved to Notion

You need

n8n · google-sheets · notion · telegram · slack

Steps

1. Configure the schedule trigger

   Add a Schedule Trigger node in n8n and set the cron expression to 0 7 * * 1-5 (Mon–Fri at 7:00). Click 'Test Workflow' to confirm the trigger starts correctly.

2. Configure 5 parallel Google Sheets fetches

   Add one Google Sheets node (typeVersion 4) for each tab: CashFlow, Revenue, Payroll, Subscriptions, Expenses. In each node: select or create a googleSheetsOAuth2Api credential; replace the documentId placeholder YOUR_GOOGLE_SHEET_ID with your actual spreadsheet ID; confirm the sheetName matches your tab. Connect all 5 nodes to the same output of the Weekday 7 AM Trigger for parallel execution.

3. Merge all sheet data

   Add a Merge node (typeVersion 3.2) and set numberInputs to 5. Connect the 5 Google Sheets outputs to inputs 0–4 of the Merge node. Verify the merged output contains rows from all tabs.

4. Calculate KPIs and status labels

   Add a Code node (typeVersion 2, JavaScript) and paste the code below. It filters items by sheet name or field presence, computes current/previous revenue, payroll, marketing ROI, cash balance, monthly burn rate, runway months, subscription MRR, total expenses, and outputs GOOD/WARNING/ALERT status labels.

   Execution prompt · Source text。JS Code field of the 'Calculate KPIs & Status Labels' node

   Copy prompt

   const allItems = $input.all();
   
   const cashflowData = allItems.filter(i => i.json.sheet === 'CashFlow' || i.json.cash_in !== undefined);
   const revenueData = allItems.filter(i => i.json.sheet === 'Revenue' || i.json.revenue_current !== undefined);
   const payrollData = allItems.filter(i => i.json.sheet === 'Payroll' || i.json.payroll_current !== undefined);
   const subscriptionData = allItems.filter(i => i.json.sheet === 'Subscriptions' || i.json.subscription_revenue !== undefined);
   const expensesData = allItems.filter(i => i.json.sheet === 'Expenses' || i.json.expense_amount !== undefined);
   
   const totalRevenueCurrent = revenueData.reduce((sum, i) => sum + (parseFloat(i.json.revenue_current) || 0), 0);
   const totalRevenuePrevious = revenueData.reduce((sum, i) => sum + (parseFloat(i.json.revenue_previous) || 0), 0);
   const revenueChange = totalRevenuePrevious > 0 ? (((totalRevenueCurrent - totalRevenuePrevious) / totalRevenuePrevious) * 100).toFixed(1) : 0;
   
   const totalPayrollCurrent = payrollData.reduce((sum, i) => sum + (parseFloat(i.json.payroll_current) || 0), 0);
   const totalPayrollPrevious = payrollData.reduce((sum, i) => sum + (parseFloat(i.json.payroll_previous) || 0), 0);
   const payrollChange = totalPayrollPrevious > 0 ? (((totalPayrollCurrent - totalPayrollPrevious) / totalPayrollPrevious) * 100).toFixed(1) : 0;
   
   const totalMarketingSpend = expensesData.reduce((sum, i) => sum + (parseFloat(i.json.marketing_spend) || 0), 0);
   const totalMarketingRevenue = revenueData.reduce((sum, i) => sum + (parseFloat(i.json.marketing_attributed_revenue) || 0), 0);
   const marketingROI = totalMarketingSpend > 0 ? ((totalMarketingRevenue / totalMarketingSpend) * 100).toFixed(1) : 0;
   const marketingROIPrevious = 85;
   const marketingROIChange = (marketingROI - marketingROIPrevious).toFixed(1);
   
   const currentCash = cashflowData.reduce((sum, i) => sum + (parseFloat(i.json.cash_balance) || 0), 0);
   const monthlyBurnRate = expensesData.reduce((sum, i) => sum + (parseFloat(i.json.monthly_burn) || 0), 0);
   const cashRunway = monthlyBurnRate > 0 ? (currentCash / monthlyBurnRate).toFixed(1) : 'N/A';
   
   const totalSubscriptions = subscriptionData.reduce((sum, i) => sum + (parseFloat(i.json.subscription_revenue) || 0), 0);
   const totalExpenses = expensesData.reduce((sum, i) => sum + (parseFloat(i.json.expense_amount) || 0), 0);
   
   const today = new Date().toISOString().split('T')[0];
   
   const revenueStatus = revenueChange < -10 ? '🔴 ALERT' : revenueChange < 0 ? '🟡 WARNING' : '🟢 GOOD';
   const payrollStatus = payrollChange > 10 ? '🔴 ALERT' : payrollChange > 5 ? '🟡 WARNING' : '🟢 GOOD';
   const cashRunwayStatus = parseFloat(cashRunway) < 3 ? '🔴 CRITICAL' : parseFloat(cashRunway) < 6 ? '🟡 WARNING' : '🟢 HEALTHY';
   const marketingStatus = marketingROIChange > 0 ? '🟢 IMPROVING' : '🟡 DECLINING';
   
   return [{
     json: {
       date: today,
       revenue_current: totalRevenueCurrent,
       revenue_previous: totalRevenuePrevious,
       revenue_change_pct: parseFloat(revenueChange),
       payroll_current: totalPayrollCurrent,
       payroll_change_pct: parseFloat(payrollChange),
       marketing_roi: parseFloat(marketingROI),
       marketing_roi_change: parseFloat(marketingROIChange),
       cash_balance: currentCash,
       monthly_burn_rate: monthlyBurnRate > 0 ? monthlyBurnRate / allItems.filter(i => i.json.monthly_burn).length : 0,
       cash_runway_months: parseFloat(cashRunway),
       subscriptions_mrr: totalSubscriptions,
       total_expenses: totalExpenses,
       revenue_status: revenueStatus,
       payroll_status: payrollStatus,
       cash_status: cashRunwayStatus,
       marketing_status: marketingStatus
     }
   }];

5. Configure the AI Agent to generate the briefing

   Add an AI Agent node (@n8n/n8n-nodes-langchain.agent, typeVersion 3, promptType: define). Connect an OpenAI GPT-4o-mini sub-node (@n8n/n8n-nodes-langchain.lmChatOpenAi, typeVersion 1.3, model: gpt-4o-mini) to its ai_languageModel input. Fill the Agent node's options.systemMessage and text fields with the prompts below. The {{ $json.* }} variables in the text field automatically reference the previous KPI node's output.

   Execution prompt · Source text。options.systemMessage field of the 'Generate AI Outreach Message1' node

   Copy prompt

   You are a senior CFO assistant. Your job is to turn raw financial KPI data into a sharp, scannable executive briefing for Telegram. Rules: use Telegram Markdown (*bold* for labels), include emojis for each section, keep total length under 350 words, be direct and action-oriented — if a metric is at WARNING or ALERT status call out the specific recommended action, otherwise just confirm it is healthy. Never add filler sentences.

   Execution prompt · Source text。text field (user prompt) of the 'Generate AI Outreach Message1' node

   Copy prompt

   =You are an expert CFO assistant. Write a concise daily financial briefing for the executive team based on the data below. Format it for Telegram using *bold* for section labels. Use emojis for quick scanning. Be direct, highlight what changed and what action (if any) is needed. Keep it under 350 words.
   
   📅 Report Date: {{ $json.date }}
   
   💰 REVENUE
   - Current: ${{ $json.revenue_current }}
   - Previous: ${{ $json.revenue_previous }}
   - Change: {{ $json.revenue_change_pct }}%
   - Status: {{ $json.revenue_status }}
   
   👥 PAYROLL
   - Current: ${{ $json.payroll_current }}
   - Change: {{ $json.payroll_change_pct }}%
   - Status: {{ $json.payroll_status }}
   
   📣 MARKETING ROI
   - ROI: {{ $json.marketing_roi }}%
   - Change vs baseline: {{ $json.marketing_roi_change }}%
   - Status: {{ $json.marketing_status }}
   
   🏦 CASH POSITION
   - Balance: ${{ $json.cash_balance }}
   - Monthly Burn: ${{ $json.monthly_burn_rate }}
   - Runway: {{ $json.cash_runway_months }} months
   - Status: {{ $json.cash_status }}
   
   📦 SUBSCRIPTIONS MRR: ${{ $json.subscriptions_mrr }}
   💸 TOTAL EXPENSES: ${{ $json.total_expenses }}
   
   End with a 1–2 line executive summary highlighting the single most important insight today.

6. Merge AI briefing with financial data

   Add a Code node (typeVersion 2) and paste the code below. It merges the AI Agent output (output) with the KPI data into a single object containing a telegram_report field, used by downstream Notion and Telegram nodes.

   Execution prompt · Source text。JS Code field of the 'Merge AI Report + Financial Data' node

   Copy prompt

   const aiOutput = $('Generate AI Outreach Message1').item.json.output || '';
   const financialData = $('Calculate KPIs & Status Labels').item.json;
   
   return [{
     json: {
       ...financialData,
       telegram_report: aiOutput
     }
   }];

7. Configure delivery and archiving

   From the 'Merge AI Report + Financial Data' node, create 3 branches: 1) Notion node (typeVersion 2, resource: databasePage): set databaseId to your CFO Report database ID; title to =CFO Report — {{ $json.date }}; blockUi and propertiesUi to {{ $json.telegram_report }} and {{ $json.marketing_status }}. 2) Telegram node (typeVersion 1.1): set chatId to your target Chat ID; text to {{ $json.telegram_report }}; additionalFields.parse_mode to Markdown. 3) If node (typeVersion 2, 'Check for Critical Revenue Drop'): condition revenue_change_pct < -10 (number/lt). The true branch connects to a second Telegram node that sends the critical alert.

   Execution prompt · Source text。text field of the 'Send Critical Revenue Alert' node

   Copy prompt

   =🚨 *CRITICAL CFO ALERT — {{ $json.date }}*
   
   ⚠️ Revenue has dropped {{ $json.revenue_change_pct }}% — immediate attention required!
   
   💰 Cash Runway: {{ $json.cash_runway_months }} months
   🔥 Monthly Burn: ${{ $json.monthly_burn_rate }}
   
   Check the full report in Notion now.

8. Configure error alerting

   Add an Error Trigger node (typeVersion 1) and a Slack node (typeVersion 2.3). Connect the Error Trigger output to the Slack node input. In the Slack node: select channel mode and specify the target channel; set authentication to oAuth2; the text field currently contains a placeholder '=Error occured ' — replace it with a template including workflow name, node name, and error timestamp for production use. This branch is independent of the main flow and catches failures from any node.

You are reproducing an n8n workflow template: daily automated executive financial briefings. Proceed in this order: 1) Confirm you have an n8n instance and all required credentials (Google Sheets OAuth2, OpenAI, Notion, Telegram Bot, Slack OAuth2); 2) Import workflow.json or build manually following the steps; 3) Replace YOUR_GOOGLE_SHEET_ID, YOUR_NOTION_DATABASE_ID, and YOUR_TELEGRAM_CHAT_ID with real values; 4) Trigger manually once to verify the 5 sheets load, KPIs calculate correctly, the AI briefing generates, and the Telegram message arrives; 5) Test the >10% revenue drop critical alert branch (temporarily adjust test data if needed); 6) Confirm the Slack error alert channel receives notifications. If you hit credential permission issues, check Google Sheets sharing settings and Notion integration permissions first.