Chief Financial Officer 予測エージェント
上級
これはAI, IT Ops分野の自動化ワークフローで、16個のノードを含みます。主にSet, Code, Stripe, Supabase, GoogleSheetsなどのノードを使用、AI技術を活用したスマート自動化を実現。 Stripeデータに基づくGPT-4とGoogleスプレッドシートによる自動化された収入予測
前提条件
- •Stripe API Key
- •Supabase URL と API Key
- •Google Sheets API認証情報
- •OpenAI API Key
- •Pinecone API Key
使用ノード (16)
ワークフロープレビュー
ノード接続関係を可視化、ズームとパンをサポート
ワークフローをエクスポート
以下のJSON設定をn8nにインポートして、このワークフローを使用できます
{
"id": "mHSoMMyypmRzfVZn",
"meta": {
"instanceId": "84ad02d6104594179f43f1ce9cfe3a81637b2faedb57dafcb9e649b7542988db"
},
"name": "CFO forecasting Agent",
"tags": [],
"nodes": [
{
"id": "b946638e-ba68-4d73-816e-00f3a63d138f",
"name": "構造化出力パーサー",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
1420,
220
],
"parameters": {
"jsonSchemaExample": "{\n \"forecast\": {\n \"June 2025\": \"$X,XXX.XX\",\n \"July 2025\": \"$X,XXX.XX\",\n \"August 2025\": \"$X,XXX.XX\"\n },\n \"trend\": \"Increasing / Decreasing / Stable\",\n \"confidence\": \"High / Medium / Low\",\n \"insights\": \"Short explanation of why this trend is predicted.\"\n}"
},
"typeVersion": 1.2
},
{
"id": "d80c3670-e8c8-43ee-ba12-2e0e18b99862",
"name": "OpenAI チャットモデル",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
1180,
220
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"id": "wYwTjEv45IzlAOAu",
"name": "OpenAi account 2"
}
},
"typeVersion": 1.2
},
{
"id": "bb75cafb-9dad-4952-89af-0658c4d88aa4",
"name": "Pinecone ベクターストア",
"type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
"position": [
1200,
400
],
"parameters": {
"mode": "retrieve-as-tool",
"options": {},
"toolName": "Sales_data",
"pineconeIndex": {
"__rl": true,
"mode": "list",
"value": "new",
"cachedResultName": "new"
},
"toolDescription": "The data about stripe sales"
},
"credentials": {
"pineconeApi": {
"id": "PSI5CiZnLRSkEgJg",
"name": "PineconeApi account"
}
},
"typeVersion": 1.1
},
{
"id": "7d370700-89d9-4163-8070-4a0c643531ca",
"name": "OpenAI 埋め込み",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
1140,
600
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"id": "wYwTjEv45IzlAOAu",
"name": "OpenAi account 2"
}
},
"typeVersion": 1.2
},
{
"id": "81de1ecf-75de-44fd-9e62-c381e907c1e1",
"name": "日次予測の実行",
"type": "n8n-nodes-base.scheduleTrigger",
"position": [
0,
0
],
"parameters": {
"rule": {
"interval": [
{
"triggerAtHour": 9
}
]
}
},
"typeVersion": 1.2
},
{
"id": "9ce2e0e4-8784-4ed9-9499-b5f54241d04e",
"name": "Stripe チャージデータの取得",
"type": "n8n-nodes-base.stripe",
"position": [
220,
0
],
"parameters": {
"resource": "charge",
"operation": "getAll",
"returnAll": true
},
"typeVersion": 1
},
{
"id": "c115eb0c-6877-46db-bf03-55e48527dbc5",
"name": "売上の集計",
"type": "n8n-nodes-base.code",
"position": [
440,
0
],
"parameters": {
"jsCode": "const charges = items.map(item => item.json);\nconst summary = charges.reduce((acc, charge) => {\n const date = new Date(charge.created * 1000).toISOString().split(\"T\")[0];\n acc[date] = (acc[date] || 0) + charge.amount / 100;\n return acc;\n}, {});\nreturn [{ json: { summary } }];\n"
},
"typeVersion": 2
},
{
"id": "fb33581a-9f41-49d7-a722-a68dfe5bc265",
"name": "データの準備",
"type": "n8n-nodes-base.set",
"position": [
660,
0
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "6aa7f5d2-3aa4-4d4c-85df-0d56bb7b6c9e",
"name": "summary",
"type": "string",
"value": "={{ $json.summary }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "d3458681-2654-4e22-8b2d-1711b60ed592",
"name": "予測エージェント",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1240,
0
],
"parameters": {
"text": "=You are a CFO AI Agent. Based on the following Stripe sales data:\n\n{{ $json.summary }}\n\nAnalyze the trends, identify any patterns (growth, decline, seasonality), and forecast expected daily or weekly revenue for the next 3 months.",
"options": {},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 1.9
},
{
"id": "325e4952-868c-460a-aa78-2e718477cc78",
"name": "Supabase への予測の保存",
"type": "n8n-nodes-base.supabase",
"position": [
2100,
-160
],
"parameters": {
"dataToSend": "autoMapInputData"
},
"typeVersion": 1
},
{
"id": "9fd6efab-edc6-49be-9516-f2d36e1995b2",
"name": "Google スプレッドシートへの予測の記録",
"type": "n8n-nodes-base.googleSheets",
"position": [
2100,
120
],
"parameters": {
"columns": {
"value": {
"trend": "={{ $json.output.trend }}",
"forecast": "={{ $json.output.forecast }}",
"insights": "={{ $json.output.insights }}",
"confidence": "={{ $json.output.confidence }}"
},
"schema": [
{
"id": "forecast",
"type": "string",
"display": true,
"required": false,
"displayName": "forecast",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "trend",
"type": "string",
"display": true,
"required": false,
"displayName": "trend",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "confidence",
"type": "string",
"display": true,
"required": false,
"displayName": "confidence",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "insights",
"type": "string",
"display": true,
"required": false,
"displayName": "insights",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {},
"operation": "append",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "gid=0",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/108tyyL--yUCbDk4drB__eztLSwjlxcmoRkqYsFnMLrY/edit#gid=0",
"cachedResultName": "Sheet1"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "108tyyL--yUCbDk4drB__eztLSwjlxcmoRkqYsFnMLrY",
"cachedResultUrl": "https://docs.google.com/spreadsheets/d/108tyyL--yUCbDk4drB__eztLSwjlxcmoRkqYsFnMLrY/edit?usp=drivesdk",
"cachedResultName": "CFO Forecasting"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "K5yYfUnKFTqaRn6A",
"name": "Google Sheets account"
}
},
"typeVersion": 4.5
},
{
"id": "241e625d-7019-4919-9f93-137461ad94bf",
"name": "付箋",
"type": "n8n-nodes-base.stickyNote",
"position": [
-40,
-1820
],
"parameters": {
"color": 3,
"width": 840,
"height": 2120,
"content": "## 1️⃣ **🔁 Data Retrieval & Preprocessing**\n\n**Nodes:**\n\n* 🕒 `Run Daily Forecast`\n* 🟦 `Fetch Stripe Charges`\n* 🧩 `Summarize Daily Sales`\n* ✏️ `Prepare Forecast Prompt`\n\n---\n\n### 🕒 `Run Daily Forecast`\n\n**Type:** Cron Trigger\n**Purpose:**\nAutomatically runs the workflow every day to keep forecasts updated with the latest sales data.\n\n🔧 **Configuration:**\n\n* Schedule: Daily at 6 AM UTC (or as needed)\n\n---\n\n### 🟦 `Fetch Stripe Charges`\n\n**Type:** Stripe Node\n**Purpose:**\nRetrieves all successful transactions from Stripe in a defined timeframe.\n\n📥 **Details:**\n\n* Resource: `Charges`\n* Operation: `Get Many`\n* Filters:\n\n * `created[gte]` (e.g. last 30 days)\n * `status: succeeded`\n* Expansion (optional): `data.customer` for customer context\n\n✅ **Output:** Raw Stripe sales data with timestamps and amounts\n\n---\n\n### 🧩 `Summarize Daily Sales`\n\n**Type:** Code Node\n**Purpose:**\nProcesses Stripe charges and summarizes revenue per day.\n\n🧠 **Logic:**\n\n* Converts Unix timestamps to `YYYY-MM-DD`\n* Aggregates total revenue per day\n* Converts cents to dollars\n\n📦 **Output Sample:**\n\n```json\n{\n \"2025-05-01\": 1245.50,\n \"2025-05-02\": 980.00\n}\n```\n\n---\n\n### ✏️ `Prepare Forecast Prompt`\n\n**Type:** Edit Fields / Function\n**Purpose:**\nFormats the summary into a natural language prompt for OpenAI.\n\n🧠 **Example Prompt:**\n\n```txt\nGiven the following sales data:\n{ \"2025-05-01\": 1245.50, ... }\n\nPredict trends and forecast sales for the next 3 months.\n```\n\n🧾 **Output:** `prompt` (String) → sent to the AI Agent\n"
},
"typeVersion": 1
},
{
"id": "f60c6c15-8449-457a-aaad-2ebca8d75318",
"name": "付箋1",
"type": "n8n-nodes-base.stickyNote",
"position": [
940,
-1880
],
"parameters": {
"color": 6,
"width": 840,
"height": 2680,
"content": "## 2️⃣ **🤖 AI Agent Forecasting**\n\n**Nodes:**\n\n* 🤖 `Forecast with OpenAI Agent`\n* 🧠 `OpenAI GPT-4 Model`\n* 📄 `Extract Forecast Output`\n* 🌲 `Store Context in Pinecone` *(Optional)*\n* 🧬 `Generate Embeddings` *(Optional)*\n\n---\n\n### 🤖 `Forecast with OpenAI Agent`\n\n**Type:** Tools Agent\n**Purpose:**\nActs as an intelligent agent that reads the sales summary and responds with forecasts and reasoning.\n\n🧠 **Prompt Input:**\nPassed from `Prepare Forecast Prompt`\n\n💬 **Uses:**\n\n* Model: `GPT-4`\n* Output Parser: Structured JSON format\n\n📈 **Forecast Intent:**\nPredicts next 3 months, identifies trends, and gives a confidence level\n\n---\n\n### 🧠 `OpenAI GPT-4 Model`\n\n**Type:** OpenAI Node\n**Purpose:**\nHandles the natural language generation based on the supplied prompt.\n\n🧾 **Configuration:**\n\n* Model: `gpt-4` or `gpt-4-turbo`\n* Temperature: `0.2` (more deterministic)\n* Max Tokens: `1000`\n\n---\n\n### 📄 `Extract Forecast Output`\n\n**Type:** Structured Output Parser\n**Purpose:**\nParses the GPT response into usable JSON format.\n\n📦 **Expected Output:**\n\n```json\n{\n \"forecast\": {\n \"June\": \"$15,000.00\",\n \"July\": \"$16,500.00\",\n \"August\": \"$17,200.00\"\n },\n \"trend\": \"Increasing\",\n \"confidence\": \"High\",\n \"insights\": \"Sales show strong momentum...\"\n}\n```\n\n---\n\n### 🌲 `Store Context in Pinecone` *(optional)*\n\n**Type:** Vector Store\n**Purpose:**\nIndexes past data for retrieval-based prompting (RAG). Useful for long-term memory.\n\n---\n\n### 🧬 `Generate Embeddings` *(optional)*\n\n**Type:** Embeddings Node\n**Purpose:**\nConverts text into vector format before inserting into Pinecone."
},
"typeVersion": 1
},
{
"id": "8e9b2ea7-58bb-4f62-a69c-eed70032019c",
"name": "付箋2",
"type": "n8n-nodes-base.stickyNote",
"position": [
1920,
-1220
],
"parameters": {
"color": 5,
"width": 460,
"height": 1560,
"content": "## 3️⃣ **📦 Storage & Reporting**\n\n**Nodes:**\n\n* 🟩 `Save Forecast to Supabase`\n* 📊 `Log Forecast in Google Sheets`\n\n---\n\n### 🟩 `Save Forecast to Supabase`\n\n**Type:** Supabase Node\n**Purpose:**\nStores all forecast results for analytics, versioning, or historical comparisons.\n\n🛢️ **Table:** `forecasts`\n🧾 **Columns Example:**\n\n| timestamp | raw\\_data | forecast\\_data |\n| ---------- | --------- | -------------- |\n| 2025-05-29 | {...} | {...} |\n\n---\n\n### 📊 `Log Forecast in Google Sheets`\n\n**Type:** Google Sheets Node\n**Purpose:**\nPushes structured data into a visual format for reporting dashboards or human review.\n\n📋 **Column Format:**\n\n| Date | Forecast (USD) | Trend | Confidence | Insights |\n| ---------- | -------------- | ---------- | ---------- | -------------------------- |\n| 2025-05-29 | \\$15,000.00 | Increasing | High | Sales rising at 10% weekly |\n\n---\n\n## ✅ Summary Flow\n\n```txt\n🔁 Sales Data (Stripe) \n → 🧠 Forecast Agent (OpenAI) \n → 📦 Stored in Supabase \n → 📊 Reported in Google Sheets"
},
"typeVersion": 1
},
{
"id": "7d1186c9-cba1-4876-a405-fa67773b8dad",
"name": "付箋9",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1840,
-1800
],
"parameters": {
"color": 4,
"width": 1300,
"height": 320,
"content": "=======================================\n WORKFLOW ASSISTANCE\n=======================================\nFor any questions or support, please contact:\n Yaron@nofluff.online\n\nExplore more tips and tutorials here:\n - YouTube: https://www.youtube.com/@YaronBeen/videos\n - LinkedIn: https://www.linkedin.com/in/yaronbeen/\n=======================================\n"
},
"typeVersion": 1
},
{
"id": "2b9e9108-8084-4e3f-a620-5bee07040bc3",
"name": "付箋4",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1840,
-1460
],
"parameters": {
"color": 4,
"width": 1289,
"height": 4778,
"content": "# 📊 CFO Forecasting Agent – Workflow Documentation\n\n---\n\n## 1️⃣ **🔁 Data Retrieval & Preprocessing**\n\n**Nodes:**\n\n* 🕒 `Run Daily Forecast`\n* 🟦 `Fetch Stripe Charges`\n* 🧩 `Summarize Daily Sales`\n* ✏️ `Prepare Forecast Prompt`\n\n---\n\n### 🕒 `Run Daily Forecast`\n\n**Type:** Cron Trigger\n**Purpose:**\nAutomatically runs the workflow every day to keep forecasts updated with the latest sales data.\n\n🔧 **Configuration:**\n\n* Schedule: Daily at 6 AM UTC (or as needed)\n\n---\n\n### 🟦 `Fetch Stripe Charges`\n\n**Type:** Stripe Node\n**Purpose:**\nRetrieves all successful transactions from Stripe in a defined timeframe.\n\n📥 **Details:**\n\n* Resource: `Charges`\n* Operation: `Get Many`\n* Filters:\n\n * `created[gte]` (e.g. last 30 days)\n * `status: succeeded`\n* Expansion (optional): `data.customer` for customer context\n\n✅ **Output:** Raw Stripe sales data with timestamps and amounts\n\n---\n\n### 🧩 `Summarize Daily Sales`\n\n**Type:** Code Node\n**Purpose:**\nProcesses Stripe charges and summarizes revenue per day.\n\n🧠 **Logic:**\n\n* Converts Unix timestamps to `YYYY-MM-DD`\n* Aggregates total revenue per day\n* Converts cents to dollars\n\n📦 **Output Sample:**\n\n```json\n{\n \"2025-05-01\": 1245.50,\n \"2025-05-02\": 980.00\n}\n```\n\n---\n\n### ✏️ `Prepare Forecast Prompt`\n\n**Type:** Edit Fields / Function\n**Purpose:**\nFormats the summary into a natural language prompt for OpenAI.\n\n🧠 **Example Prompt:**\n\n```txt\nGiven the following sales data:\n{ \"2025-05-01\": 1245.50, ... }\n\nPredict trends and forecast sales for the next 3 months.\n```\n\n🧾 **Output:** `prompt` (String) → sent to the AI Agent\n\n---\n\n## 2️⃣ **🤖 AI Agent Forecasting**\n\n**Nodes:**\n\n* 🤖 `Forecast with OpenAI Agent`\n* 🧠 `OpenAI GPT-4 Model`\n* 📄 `Extract Forecast Output`\n* 🌲 `Store Context in Pinecone` *(Optional)*\n* 🧬 `Generate Embeddings` *(Optional)*\n\n---\n\n### 🤖 `Forecast with OpenAI Agent`\n\n**Type:** Tools Agent\n**Purpose:**\nActs as an intelligent agent that reads the sales summary and responds with forecasts and reasoning.\n\n🧠 **Prompt Input:**\nPassed from `Prepare Forecast Prompt`\n\n💬 **Uses:**\n\n* Model: `GPT-4`\n* Output Parser: Structured JSON format\n\n📈 **Forecast Intent:**\nPredicts next 3 months, identifies trends, and gives a confidence level\n\n---\n\n### 🧠 `OpenAI GPT-4 Model`\n\n**Type:** OpenAI Node\n**Purpose:**\nHandles the natural language generation based on the supplied prompt.\n\n🧾 **Configuration:**\n\n* Model: `gpt-4` or `gpt-4-turbo`\n* Temperature: `0.2` (more deterministic)\n* Max Tokens: `1000`\n\n---\n\n### 📄 `Extract Forecast Output`\n\n**Type:** Structured Output Parser\n**Purpose:**\nParses the GPT response into usable JSON format.\n\n📦 **Expected Output:**\n\n```json\n{\n \"forecast\": {\n \"June\": \"$15,000.00\",\n \"July\": \"$16,500.00\",\n \"August\": \"$17,200.00\"\n },\n \"trend\": \"Increasing\",\n \"confidence\": \"High\",\n \"insights\": \"Sales show strong momentum...\"\n}\n```\n\n---\n\n### 🌲 `Store Context in Pinecone` *(optional)*\n\n**Type:** Vector Store\n**Purpose:**\nIndexes past data for retrieval-based prompting (RAG). Useful for long-term memory.\n\n---\n\n### 🧬 `Generate Embeddings` *(optional)*\n\n**Type:** Embeddings Node\n**Purpose:**\nConverts text into vector format before inserting into Pinecone.\n\n---\n\n## 3️⃣ **📦 Storage & Reporting**\n\n**Nodes:**\n\n* 🟩 `Save Forecast to Supabase`\n* 📊 `Log Forecast in Google Sheets`\n\n---\n\n### 🟩 `Save Forecast to Supabase`\n\n**Type:** Supabase Node\n**Purpose:**\nStores all forecast results for analytics, versioning, or historical comparisons.\n\n🛢️ **Table:** `forecasts`\n🧾 **Columns Example:**\n\n| timestamp | raw\\_data | forecast\\_data |\n| ---------- | --------- | -------------- |\n| 2025-05-29 | {...} | {...} |\n\n---\n\n### 📊 `Log Forecast in Google Sheets`\n\n**Type:** Google Sheets Node\n**Purpose:**\nPushes structured data into a visual format for reporting dashboards or human review.\n\n📋 **Column Format:**\n\n| Date | Forecast (USD) | Trend | Confidence | Insights |\n| ---------- | -------------- | ---------- | ---------- | -------------------------- |\n| 2025-05-29 | \\$15,000.00 | Increasing | High | Sales rising at 10% weekly |\n\n---\n\n## ✅ Summary Flow\n\n```txt\n🔁 Sales Data (Stripe) \n → 🧠 Forecast Agent (OpenAI) \n → 📦 Stored in Supabase \n → 📊 Reported in Google Sheets\n```\n"
},
"typeVersion": 1
}
],
"active": false,
"pinData": {
"Fetch Stripe Charges": [
{
"json": {
"id": "ch_1NxXy2LzPp3ZhRAbCD123456",
"amount": 3500,
"object": "charge",
"status": "succeeded",
"created": 1716940800,
"currency": "usd",
"customer": {
"id": "cus_N8U1xX5TVgB1vW",
"name": "Jane Doe",
"email": "jane.doe@example.com"
},
"description": "Pro plan subscription",
"amount_captured": 3500,
"amount_refunded": 0,
"payment_method_details": {
"card": {
"brand": "visa",
"last4": "4242"
},
"type": "card"
}
}
},
{
"json": {
"id": "ch_1NxXy3LzPp3ZhRAbCD654321",
"amount": 1299,
"object": "charge",
"status": "succeeded",
"created": 1717027200,
"currency": "usd",
"customer": {
"id": "cus_N8U9YT5TWzA7LM",
"name": "John Smith",
"email": "john.smith@example.com"
},
"description": "Add-on purchase",
"amount_captured": 1299,
"amount_refunded": 0,
"payment_method_details": {
"card": {
"brand": "mastercard",
"last4": "5555"
},
"type": "card"
}
}
}
]
},
"settings": {
"executionOrder": "v1"
},
"versionId": "56196260-ac1a-4ef1-87c1-d5a8e1eb438f",
"connections": {
"fb33581a-9f41-49d7-a722-a68dfe5bc265": {
"main": [
[
{
"node": "d3458681-2654-4e22-8b2d-1711b60ed592",
"type": "main",
"index": 0
}
]
]
},
"c115eb0c-6877-46db-bf03-55e48527dbc5": {
"main": [
[
{
"node": "fb33581a-9f41-49d7-a722-a68dfe5bc265",
"type": "main",
"index": 0
}
]
]
},
"d3458681-2654-4e22-8b2d-1711b60ed592": {
"main": [
[
{
"node": "325e4952-868c-460a-aa78-2e718477cc78",
"type": "main",
"index": 0
},
{
"node": "9fd6efab-edc6-49be-9516-f2d36e1995b2",
"type": "main",
"index": 0
}
]
]
},
"7d370700-89d9-4163-8070-4a0c643531ca": {
"ai_embedding": [
[
{
"node": "bb75cafb-9dad-4952-89af-0658c4d88aa4",
"type": "ai_embedding",
"index": 0
}
]
]
},
"d80c3670-e8c8-43ee-ba12-2e0e18b99862": {
"ai_languageModel": [
[
{
"node": "d3458681-2654-4e22-8b2d-1711b60ed592",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"81de1ecf-75de-44fd-9e62-c381e907c1e1": {
"main": [
[
{
"node": "9ce2e0e4-8784-4ed9-9499-b5f54241d04e",
"type": "main",
"index": 0
}
]
]
},
"9ce2e0e4-8784-4ed9-9499-b5f54241d04e": {
"main": [
[
{
"node": "c115eb0c-6877-46db-bf03-55e48527dbc5",
"type": "main",
"index": 0
}
]
]
},
"bb75cafb-9dad-4952-89af-0658c4d88aa4": {
"ai_tool": [
[
{
"node": "d3458681-2654-4e22-8b2d-1711b60ed592",
"type": "ai_tool",
"index": 0
}
]
]
},
"b946638e-ba68-4d73-816e-00f3a63d138f": {
"ai_outputParser": [
[
{
"node": "d3458681-2654-4e22-8b2d-1711b60ed592",
"type": "ai_outputParser",
"index": 0
}
]
]
}
}
}よくある質問
このワークフローの使い方は？
上記のJSON設定コードをコピーし、n8nインスタンスで新しいワークフローを作成して「JSONからインポート」を選択、設定を貼り付けて認証情報を必要に応じて変更してください。
このワークフローはどんな場面に適していますか？
上級 - 人工知能, IT運用
有料ですか？
このワークフローは完全無料です。ただし、ワークフローで使用するサードパーティサービス（OpenAI APIなど）は別途料金が発生する場合があります。
関連ワークフロー
COOタスク優先順位付け
GPT-4とPinecone Memoryを基盤としたAI駆動のAsanaタスク優先順位付け
Asana
Postgres
Agent
+
Asana
Postgres
Agent
15 ノードYaron Been
人工知能
CFO 費用審査インターフェース
GPT-4、Airtable、Pineconeベクトルデータベースを使った自動経費承認システム
Airtable
Agent
Airtable Trigger
+
Airtable
Agent
Airtable Trigger
15 ノードYaron Been
人工知能
ペットショップ 4
ペットショップ予約AIエージェント
If
Set
Code
+
If
Set
Code
187 ノードBruno Dias
人工知能
Upwork 求人の集約と通知
自動職缺検索：Upwork機会の集約とAI駆動型通知器
Set
Gmail
Http Request
+
Set
Gmail
Http Request
13 ノードYaron Been
その他
Bright Dataを使った自動化フォーラムモニタリング
Bright Dataとn8nを使ったフォーラム監視の自動化
Set
Code
Html
+
Set
Code
Html
17 ノードYaron Been
人工知能
基于AIのMISエージェント
基于AIの管理信息系统エージェント
If
Set
Code
+
If
Set
Code
129 ノードKumar Shivam
サポート
ワークフロー情報
難易度
上級
ノード数16
カテゴリー2
ノードタイプ12
作成者
Yaron Been
@yaron-nofluffBuilding AI Agents and Automations | Growth Marketer | Entrepreneur | Book Author & Podcast Host If you need any help with Automations, feel free to reach out via linkedin: https://www.linkedin.com/in/yaronbeen/ And check out my Youtube channel: https://www.youtube.com/@YaronBeen/videos
外部リンク
n8n.ioで表示 →
このワークフローを共有