ChatGPT Gmail Connector | 分析我所有SaaS訂閱與API token usages

Gmail SaaS 訂閱分析的 Prompt 解析

這個 prompt 是一個結構化的指令集,用途是指引 ChatGPTGmail connector 去讀取我授權的 Gmail帳號內的資料並進行分析來實驗性的建立 SaaS 訂閱管理報表。

核心架構設定

我嘗試在 prompt 開始就建立了明確的執行環境:「你已連到我的 Gmail」。這個設定直接告訴 LLM 目前已經成功的透過 ChatGPT connector 綁定 Gmail 帳號,並且定義了三個主要任務目標:收集 SaaS、API、Web 服務的財務記錄,建立訂閱清單,以及專門針對 LLM API 進行 token 用量分析。分析範圍我精確限定在 2025-01-01 到當前日期,語系和時區設定為台灣地區標準。特別重要的是幣別處理原則:「若出現多幣別,請分別彙整,不要自行換匯」,這避免了匯率變動對分析準確性的影響。

搜尋策略層級設計

我實驗性的為 prompt 寫了多層次的搜尋策略。基礎層是 Gmail 查詢語法,混合中英文關鍵詞來確保涵蓋範圍:「(subject:(receipt OR invoice OR payment OR subscription OR paid OR 使用量 OR 扣款 OR 計費 OR 收據 OR 發票 OR 續訂)」。關鍵詞被分為三個專業領域:Token 用量關聯詞涵蓋了 AI 服務的專業術語,金額與計費關鍵詞針對財務相關的詞彙,LLM 廠商名稱則直接對應到具體的服務提供商和其郵件地址格式。這種分類設計確保了不同類型的訂閱服務都能被準確識別。

資料結構定義

我也在 prompt 中定義了兩套資料結構。第一套是「訂閱與 API 使用清單」,包含了 merchant(商家)、service(服務名稱)、plan(方案名稱)等 11 個基本欄位。每個欄位都有明確的資料類型和格式要求,例如 email_date 要求特定日期格式,billing_cycle 包含月、季、年、一次性、計量制等標準化選項。第二套是「LLM Token 詳細分析」,專門處理 AI 服務的計費資料。這套結構包含 model_name、prompt_tokens、completion_tokens 等 8 個欄位,反映了現代 LLM API 服務按 token 計費的複雜性。prompt 特別要求區分輸入和輸出 token,因為它們通常有不同的計費標準。

智慧分析機制

我同時也在 prompt 中要求系統進行多層次的資料分析。基礎層是資料收集和分類,進階層包含統計摘要功能:月度總支出、季度總支出、年度總支出,以及預警機制如「未來 60 天內續訂或試用到期清單」。資料清理與去重機制被明確定義:「同一商家同方案重複扣款,保留資訊最完整者」、「無續訂線索、一次性購買者可歸入一次性工具區塊」。這些規則處理了實際資料分析中常見的重複和分類問題。

輸出格式規範

我同時也透過 prompt 規定了三種主要輸出格式:訂閱主清單依照「有效中」與「月費等值」排序,統計摘要提供分析洞察,檔案下載則包含 CSV、Markdown 等不同格式選項。這種多格式設計滿足了不同使用場景的需求。回覆格式被詳細規範:使用繁體中文、日期格式 YYYY-MM-DD、金額保留兩位小數並標示幣別。這些格式要求確保了輸出結果的一致性和可讀性。

特殊情況處理

prompt 還包含了針對特定廠商的處理邏輯。例如「OpenAI 通常會於每月月初寄送 Monthly Usage Report 主旨的郵件」、「Anthropic 會以 Stripe 代收並開發票」。用這些特殊規則明確說明不同 AI 服務商的實際營運模式差異。對於預儲值帳戶,prompt 要求「比對儲值金額與實際用量金額差異」,這處理了某些 AI 服務採用預付費模式的計費複雜性。

錯誤處理與驗證

最後 prompt 中也加入了資料品質控制機制。包含完整性檢查(「若郵件未直接列出 token 數與費率,請嘗試從文字或表格中萃取;若完全無法判讀,請列入待補資料」)和互動確認機制(「若遇模糊資訊,請在報告底部列出需要我補充的欄位」)。這個設計承認了自動化分析的限制,預先建立了人工介入的管道,確保最終結果的準確性。整個 prompt 結構反映了對現代 SaaS 和 AI 服務使用場景的深度理解,以及對資料分析準確性的嚴格要求。

目前使用的 Prompt

注意事項:要驅動 ChatGPT connector 你必須使用 Deep Research 模式讓 ChatGPT可以運作長時間的背景任務

# Complete Gmail SaaS Subscription & API Billing Analysis Guide

## Task Overview

You are connected to my Gmail. Please analyze receipts, invoices, and renewal notifications related to "SaaS, API, Web services" to create a comprehensive subscription and usage billing list, including token usage and rates for LLM APIs.

---

## Analysis Scope Configuration

- **Period:** 2025-01-01 to today
- **Language & Region:** English (US), timezone America/New_York (UTC-5)
- **Currency:** If multiple currencies appear, **consolidate separately** without currency conversion

---

## Analysis Rules & Advanced Search Strategy

### Core Gmail Query Expressions (combinable)

```
(subject:(receipt OR invoice OR payment OR subscription OR paid OR usage OR billing OR renewal) OR "auto-renew" OR "token usage" OR "API usage" OR "LLM usage") after:2025/01/01
```

### Advanced Specialized Search Queries

```
# Third-party payment platforms
(from:(*stripe.com OR *paddle.com OR *paypal.com OR *chargebee.com OR *recurly.com OR *fastspring.com) AND (subject:(payment OR invoice OR receipt))) after:2025/01/01

# Trial expiration & upgrade reminders
(subject:(trial OR expire OR upgrade) AND from:(*@*.com)) after:2025/01/01

# Usage limit warnings
(subject:(limit OR exceeded OR quota OR usage) after:2025/01/01

# Price change notifications
(subject:(price OR pricing OR rate OR plan) AND (change OR update OR increase)) after:2025/01/01
```

### Key Search Keywords

#### Token Usage Related Terms
- token usage, prompt tokens, completion tokens, usage summary, monthly usage report
- model: gpt-4, gpt-3.5, claude, mistral, llama, llamaindex, embedding, context window, usage tier

#### Billing & Cost Keywords
- cost, charged, unit price, total usage, rate, per 1k tokens
- USD, billing, payment, invoice, receipt

#### LLM Provider Names (sender or subject)
- **OpenAI** (*@openai.com)
- **Anthropic** (*@anthropic.com)
- **Mistral** (*@mistral.ai)
- **Cohere** (*@cohere.com)
- **Google Vertex AI** (*@google.com)
- **Azure OpenAI** (*@microsoft.com)
- **Together.ai** (*@together.xyz)
- **Perplexity / LlamaIndex / LangChain** (if API/paid)
- **API Gateways:** Stripe, Paddle, FastSpring, Chargebee, Recurly, PayPal, etc.

---

## Smart Service Classification System

### Service Category Tags

- **AI/ML Tools**: LLM APIs, machine learning platforms, automation tools
- **Development Tools**: IDEs, CI/CD, code repositories, API management
- **Infrastructure**: cloud services, CDN, databases, storage
- **Productivity Tools**: project management, design software, communication, document collaboration
- **Marketing Tools**: email marketing, analytics, CRM, advertising platforms
- **Security Tools**: authentication, VPN, security monitoring, backup services
- **Business Tools**: accounting software, HR systems, legal tools
- **Creative Tools**: image editing, video production, audio processing

---

## LLM Token Cost Analysis (Enhanced Requirements)

For emails containing "token usage," "model names," "token pricing," "total amounts," extract the following fields:

- **model_name** (e.g., gpt-4-turbo)
- **prompt_tokens / completion_tokens**
- **unit_price_per_1k_tokens (USD)**
- **total_tokens / total_price (USD)**
- **billing_month** (usage period)
- **usage_tier** (usage tier if applicable)
- **source_email_date**

If emails don't directly list token counts and rates, attempt extraction from text or tables; if completely unreadable, list under "Data Pending."

---

## Complete Field Extraction Definitions

### A. Subscription & API Usage List

| Field Name | Description | Example |
|------------|-------------|---------|
| `merchant` | Merchant name | OpenAI, Notion, Slack |
| `service` | Service name | ChatGPT Plus, Notion Pro, Slack Pro |
| `plan` | Plan name | Individual, Team, Enterprise |
| `category` | Service category | AI/ML Tools, Productivity Tools |
| `email_date` | Email date | 2025-01-15 |
| `amount` | Amount | 20.00 |
| `currency` | Currency | USD, EUR |
| `billing_cycle` | Billing cycle | Monthly/Quarterly/Annual/One-time/Usage-based |
| `next_renewal` | Next renewal date | 2025-02-15 |
| `payment_method_hint` | Payment method hint | *1234 |
| `status` | Status | active/canceled/trial |
| `usage_info` | Usage information | If usage data available |
| `source_message_id` | Source email ID | Gmail message ID |

### B. LLM Token Detailed Analysis

| Field Name | Description | Example |
|------------|-------------|---------|
| `model_name` | Model name | gpt-4-turbo |
| `prompt_tokens` | Input token count | 15000 |
| `completion_tokens` | Output token count | 3000 |
| `total_tokens` | Total token count | 18000 |
| `unit_price_per_1k_tokens` | Price per 1K tokens | 0.01 |
| `total_price` | Total cost | 0.18 |
| `billing_month` | Billing month | 2025-01 |
| `usage_tier` | Usage tier | Tier 1, Tier 2 |

---

## Data Validation & Quality Assurance

### Automated Quality Validation

- **Amount reasonableness check**: Flag unusually high (>$500) or low (<$1) transactions
- **Date logic validation**: Ensure renewal dates are within reasonable ranges
- **Duplicate transaction detection**: Multiple transactions same day, same merchant
- **Currency consistency**: Currency changes for same service over time
- **Missing data alerts**: Identify common services potentially not found

### Data Cleaning & Deduplication Rules

- For duplicate charges from same merchant/plan, keep most complete information
- Non-renewal, one-time purchases go to "One-time Tools" section
- Incomplete token usage information goes to "Pending Fields List"
- Auto-identify test transactions, refunds and mark accordingly

---

## Interactive Confirmation Process

### User Confirmation Workflow

Before generating final report, display:

1. **Suspected Services List**
   - Let user confirm if these are subscription services
   - Distinguish one-time purchases vs recurring expenses

2. **Category Confirmation**
   - User can adjust service categories
   - Custom tags and notes

3. **Exclusion List**
   - One-time purchases, gift cards, non-recurring expenses
   - Personal vs business expense classification

---

## Complete Output Requirements

### 1. Service Health Dashboard

#### A. Main Subscription List
- Sorted by "Active" and "Monthly Equivalent"
- Include usage frequency assessment (based on email interactions)
- Preliminary ROI evaluation markers

#### B. Category Statistics
- Expense breakdown by category
- Service overlap analysis
- Integration opportunity identification

### 2. Smart Analysis & Alerts

#### A. Spending Trend Analysis
- **Monthly spending trend chart** (including YoY growth rate)
- **Quarterly spending statistics** (calendar quarters Q1-Q4)
- **Annual spending total** (year to date)
- **Anomaly detection** (months exceeding average by 20%+)

#### B. Renewal & Alert System
- **Renewals within 30 days**
- **Renewals within 60 days**
- **Trial expiration reminders** (7/14/30 days prior)
- **Price change tracking** (same service rate comparisons over time)

### 3. Cost Optimization Recommendations

#### A. Cost-saving Opportunity Analysis
- **Usage rate analysis**: Identify low-usage subscriptions
- **Duplicate service detection**: List of functionally overlapping tools
- **Annual payment discount opportunities**: Calculate savings from switching to annual
- **Plan optimization suggestions**: Recommend suitable plans based on usage

#### B. Budget Planning Assistance
- **3-6 month spending forecast** (based on historical data)
- **Budget allocation suggestions for different scenarios**
- **Cost control target setting**

#### C. Competitive Pricing Reference
- Same-category service price comparisons
- Market average price reference
- Alternative solution recommendations

### 4. Data Export Options

#### A. Standard Format Files
- `subscriptions_2025.csv`
- `token_usage_2025.csv` (if applicable)
- `subscriptions.md` (Markdown tables)

#### B. Integration Export Formats
- **Accounting software compatible formats** (QuickBooks, Xero)
- **Google Sheets auto-update templates**
- **Tax category label files** (business expense categories)
- **Multi-account consolidated analysis files** (if applicable)

---

## Response Format Requirements

### Format Specifications
- Use US English
- Date format: YYYY-MM-DD
- Amounts: Two decimal places, clear currency indication
- Service names: Keep original, add English descriptions if needed

### Report Structure
1. **Executive Summary** (key findings and recommendations)
2. **Data Dashboard** (visualized statistics)
3. **Detailed Lists** (complete service listings)
4. **Optimization Recommendations** (specific action plans)
5. **Pending Data List** (items requiring user confirmation)

---

## Additional Notes & Special Cases

### Vendor-Specific Identification Rules
- **OpenAI**: Monthly "Monthly Usage Report" + Stripe payment notifications
- **Anthropic**: Stripe billing invoices + Claude Credits top-ups
- **Google Workspace**: Multi-service integrated billing
- **Microsoft**: Azure + Office 365 may bill separately
- **AWS**: Detailed usage reports, note multi-service breakdown

### Special Situation Handling
- **Prepaid accounts**: Compare top-up amounts vs actual usage differences
- **Multi-currency transactions**: Separate statistics, mark exchange rate impact
- **Enterprise accounts**: Note unified invoices and multi-user licenses
- **Trial-to-paid conversions**: Track conversion timing and price changes

### Quality Assurance Checkpoints
- Total amount summation verification
- Service category completeness check
- Time series logic validation
- Anomaly flagging and explanation

---

OpenAI deep research Result(錯誤很多,但未來可期?)

以下為 ChatGPT的回應:

了解,我將從你的 Gmail 中分析 2025 年至今的 SaaS、API、Web 服務相關訂閱與計費郵件,排除 Shopify,並將 LLM API token 使用與費率獨立列出,不納入一般月費統計中。完成後我會提供清單、統計摘要與可下載的 CSV/Markdown 報告。

根據 Gmail 收據與通知整理,目前 有效 的 SaaS/API 訂閱與用量服務如下(依月費等值由高至低排序):

商家/平台服務名稱方案/類型最近通知日期金額幣別計費週期下次續訂/扣款付款方式狀態
OpenAIOpenAI API用量制(即時扣款)2025-07-3040.88USD計量制(使用量)N/A(用量扣款)8597有效
Anthropic, PBCClaude API(用量)自動儲值點數(用量扣款)2025-07-2840.58USD計量制(使用量)N/A(用量扣款)7059有效
Pinecone Systems, Inc.Pinecone 向量資料庫Serverless 用量方案2025-07-0169.27USD每月(用量計費)N/A(按月結算)8597有效
LlamaIndex IncLlamaIndex 資料庫接口Starter 訂閱方案2025-07-3150.00USD每月2025-08-30Link有效
JetBrainsAll Products Pack 開發工具套件年費授權(多人)2025-07-13待補USD每年2026-07-13信用卡有效
Cohere Inc.Cohere 大語言模型 API用量制2025-07-0136.86USD每月(用量計費)N/A(按月結算)8597有效
Landing AILanding AI 平台(電腦視覺 API)儲值帳戶餘額購買(用量)2025-07-2425.00USD (NT$763.93)一次性儲值 / 用量N/A(用量扣款)7059有效
Every.toEvery 訂閱(AI 工具套件)Pro 內容訂閱2025-06-2320.00USD每月2025-07-23信用卡有效
Anthropic, PBCClaude Pro (AI 聊天)專業方案訂閱2025-07-0120.00USD每月2025-07-31Link有效
Google Workspace商務入門版 (公司信箱與雲端)GWS 商務入門訂閱2025-07-02待補TWD每月2025-08-01信用卡有效
Eleven Labs Inc.ElevenLabs 語音合成 APIStarter 訂閱方案2025-07-055.00USD每月2025-08-05Link有效
Amazon Web ServicesAWS 雲服務帳戶按使用付費2025-06-30待補USD每月(用量計費)N/A(按月結算)8597有效

Every 訂閱下次續訂日期依用戶方案而定,此處假設為月付方案的預估日期(實際可能已轉為年付方案)。

說明:上述清單列出 2025 年以來與 SaaS、API、雲服務相關的各項支出。大部分交易以美元計價,另有部分以台幣收取(如 Google Workspace,金額待補)。同一服務多次扣款者,已保留資訊最完整或代表性的紀錄。例如 OpenAI 與 Anthropic API 均為用量計費,多次小額扣款已合併表示。Landing AI 於 7 月24日先儲值 US$25(折合 NT$763.93),當日隨後觸發兩次自動扣款 US$10.24 與 US$10.71;此處以儲值紀錄代表總體用量扣款情形。JetBrains 開發工具的實際費用需參見發票附件(金額與授權用戶數量待補)。


📈 統計摘要

  • 月度總支出:2025 年各月的已知支出金額如下(未含台幣計價部分):
    • 1 月:US$65(OpenAI首筆扣款 US$40.01,加上 Anthropic Claude Pro US$20 等)※台幣計費的 Google Workspace 月費未計入
    • 2 月:US$90(Anthropic Pro US$20;Pinecone 用量約 US$64.93;ElevenLabs US$5 等)
    • 3 月:US$220(OpenAI 約 US$80.38;Anthropic Pro US$20;Cohere 約 US$44.25;Pinecone US$71.51;ElevenLabs US$5)
    • 4 月:US$400(OpenAI 約 US$200.85;Anthropic Pro US$20;Cohere US$42.19;LlamaIndex 用量 US$65.39;Pinecone 約 US$70;ElevenLabs US$5)
    • 5 月:US$187(Anthropic Pro US$20;Cohere US$40.38;Pinecone US$72.08;LlamaIndex 訂閱 US$50;ElevenLabs US$5;OpenAI 該月無扣款)
    • 6 月:US$261(OpenAI US$80.41;Anthropic Pro US$20;Cohere US$36.86;Pinecone US$69.27;LlamaIndex US$50;ElevenLabs US$5)
    • 7 月: US$400~500+(OpenAI 約 US$166.18;Anthropic Pro US$20 + 用量約 US$120.94;LlamaIndex US$50;Landing AI 約 US$46;Every 約 US$20;ElevenLabs US$5;Cohere 7 月帳單、Pinecone 7 月用量發票與部分年訂閱費用尚待統計
  • 季度總支出:
    • Q1 2025:US$370+(1~3 月,小計約 US$376,未含台幣計價項目)
    • Q2 2025:US$850+(4~6 月,小計約 US$851,未含台幣計價項目)
    • Q3 2025:US$500+(僅含 7 月,目前部分用量尚未出帳)
  • 2025 年度累計(截至 7 月底): 已知約 US$1,700 (不含台幣計價服務;年度總額待所有項目補充後更新)
  • 未來 60 天內即將續訂/到期:
    • Google Workspace 商務入門版: 下期扣款日 2025-08-01(每月自動扣款)
    • Anthropic Claude Pro 專業版: 下期扣款日 2025-07-31(月租 US$20)
    • LlamaIndex Starter 訂閱: 下期扣款日 2025-08-30(月租 US$50)
    • ElevenLabs Starter 訂閱: 下期扣款日 2025-08-05(月租 US$5)
    • Every 訂閱服務: 若為月付方案,下一帳單日約 2025-08-23(或依實際週期)

(註:以上統計未計入台幣計價的服務。台幣支出主要為 Google Workspace 月費(金額視使用者數量而定)等。若需精確數字,請參考各服務帳單附件或管理後台。)


Leave a Comment

Your email address will not be published. Required fields are marked *