diff --git a/engage-box/roi_reporting/README.md b/engage-box/roi_reporting/README.md index a779213d..e0341572 100644 --- a/engage-box/roi_reporting/README.md +++ b/engage-box/roi_reporting/README.md @@ -75,8 +75,8 @@ cd workflows/reporting_agent/ │ Treasure Data Tables │ │ ├─ daily_summary │ │ ├─ email_events │ - │ ├─ revenue │ - │ └─ event_master │ + │ ├─ revenue_table │ + │ └─ events_master │ └─────────────────────────────────────────┘ ``` @@ -91,34 +91,32 @@ cd workflows/reporting_agent/ ### Setup Steps -1. **Set up Data Preparation Workflows** - ```bash - cd workflows/reporting_agent/ - # Follow instructions in workflows/reporting_agent/README.md - # This creates the required tables (daily_summary, email_events, revenue, event_master) - ``` +The two components can be set up independently. You can start with either one: -2. **Deploy AI Reporting Agent** - ```bash - cd agent/ - # Follow instructions in agent/README.md - # This sets up the agent in AI Agent Foundry - ``` +**Option A: Set up the Agent first** (if the database and tables already exist) +```bash +cd agent/ +# Follow instructions in agent/README.md +``` + +**Option B: Set up the Workflow first** (to create tables from scratch) +```bash +cd workflows/reporting_agent/ +# Follow instructions in workflows/reporting_agent/README.md +``` -3. **Generate Reports** - - Use the agent via AI Agent Foundry UI - - Or integrate via Form Interfaces (when API available) +> **Note**: The agent requires the `engage_roi_reporting` database with populated tables to function. If the tables already exist (e.g., created by another team), you can deploy the agent without running the workflow. ## Required Tables -The solution requires the following tables to be created by the workflow: +The solution requires the following tables in the `engage_roi_reporting` database: | Table | Description | Created By | |---|---|---| | `daily_summary` | Daily aggregated performance metrics | Workflow | | `email_events` | Email event logs (deduplicated) | Workflow | -| `revenue` | Revenue attribution data | Workflow | -| `event_master` | Campaign/journey metadata | Workflow | +| `revenue_table` | Revenue attribution data | Workflow (sample) or user-provided | +| `events_master` | Campaign/journey metadata | Workflow | ## Use Cases @@ -144,7 +142,6 @@ Deep-dive into specific campaign or journey performance: |---|---| | Agent reports "schema mismatch" | Verify workflow has run successfully and all required tables exist | | No data in reports | Check workflow execution logs, verify date ranges | -| Form Interfaces not available | API support for Form Interfaces is in development | ### Support Resources @@ -160,23 +157,40 @@ Deep-dive into specific campaign or journey performance: roi_reporting/ ├── README.md # This file ├── agent/ # AI Reporting Agent +│ ├── tdx.json # Auto-generated by tdx CLI (not committed) │ ├── README.md │ ├── README_JA.md -│ ├── system_prompt.md -│ ├── system_prompt_JA.md -│ ├── knowledge_base_overall_summary.md -│ ├── knowledge_base_campaign_details.md -│ ├── tools.yml -│ └── forms/ -│ ├── td_managed_overall_summary.yml -│ └── td_managed_campaign_details.yml +│ ├── Dashboard Viz/ +│ │ ├── agent.yml # Agent config (tools/outputs) +│ │ ├── prompt.md # System prompt (English) +│ │ └── prompt_ja.md # System prompt (Japanese, reference) +│ ├── knowledge_bases/ +│ │ ├── engage_roi_reporting.yml +│ │ ├── OverallSummary_Spec.md +│ │ ├── OverallSummary_Spec_ja.md +│ │ ├── CampaignDetails_Spec.md +│ │ └── CampaignDetails_Spec_ja.md +│ └── form_interfaces/ +│ ├── Overall Summary.yml +│ └── Campaign Details.yml └── workflows/ # Data Preparation Workflows └── reporting_agent/ + ├── tdx.json # Auto-generated by tdx CLI (not committed) ├── README.md ├── config.yaml ├── report_preparation.dig + ├── revenue_generation.dig ├── queries/ + │ ├── daily_summary.sql + │ ├── deduplicate_email_events.sql + │ ├── email_events.sql + │ └── merge_summary_data.sql └── scripts/ + └── reporting_agent/ + ├── __init__.py + ├── events_master.py + ├── generate_revenue_data.py + └── setup_test_tables.py ``` ## License diff --git a/engage-box/roi_reporting/agent/README.md b/engage-box/roi_reporting/agent/README.md index ce3c31ae..bf13b973 100644 --- a/engage-box/roi_reporting/agent/README.md +++ b/engage-box/roi_reporting/agent/README.md @@ -52,7 +52,7 @@ cd treasure-boxes/engage-box/roi_reporting/agent # 2. Create project and push agent tdx llm project create "ROI Reporting Agent" -tdx agent push . -y +tdx agent push . -f ``` **That's it!** All components are created: @@ -78,7 +78,7 @@ cd agents/ROI\ Reporting\ Agent echo '{"llm_project": "My New Project"}' > tdx.json # 4. Push to new project -tdx agent push . -y +tdx agent push . -f ``` ### Verify Setup diff --git a/engage-box/roi_reporting/agent/README_JA.md b/engage-box/roi_reporting/agent/README_JA.md index 33e189d5..cdde0aa0 100644 --- a/engage-box/roi_reporting/agent/README_JA.md +++ b/engage-box/roi_reporting/agent/README_JA.md @@ -52,7 +52,7 @@ cd treasure-boxes/engage-box/roi_reporting/agent # 2. プロジェクトを作成してエージェントをプッシュ tdx llm project create "ROI Reporting Agent" -tdx agent push . -y +tdx agent push . -f ``` **これだけです！** すべてのコンポーネントが作成されます: @@ -78,7 +78,7 @@ cd agents/ROI\ Reporting\ Agent echo '{"llm_project": "My New Project"}' > tdx.json # 4. 新しいプロジェクトにプッシュ -tdx agent push . -y +tdx agent push . -f ``` ### セットアップの確認 diff --git a/engage-box/roi_reporting/agent/knowledge_bases/CampaignDetails_Spec_ja.md b/engage-box/roi_reporting/agent/knowledge_bases/CampaignDetails_Spec_ja.md index 3eef44b2..18526b5c 100644 --- a/engage-box/roi_reporting/agent/knowledge_bases/CampaignDetails_Spec_ja.md +++ b/engage-box/roi_reporting/agent/knowledge_bases/CampaignDetails_Spec_ja.md @@ -108,7 +108,7 @@ SQLエージェントは、指定されたcampaign_idまたはjourney_idの利 - クエリ構築: 1. email_eventsテーブルから直接email_titleでGROUP BY 2. campaign_idまたはjourney_idでフィルタ - 3. event_masterテーブルとのJOINは不要 + 3. events_masterテーブルとのJOINは不要 - SQLエージェントはLIMIT 51でクエリする必要があります。 - 51行が返された場合、VIZエージェントは注記を表示する必要があります: '上位50件のみ表示しています。追加の件名が表示されていない可能性があります。' - 最初の50行のみを表示します。 diff --git a/engage-box/roi_reporting/agent/knowledge_bases/OverallSummary_Spec_ja.md b/engage-box/roi_reporting/agent/knowledge_bases/OverallSummary_Spec_ja.md index 4ba39717..e6872a56 100644 --- a/engage-box/roi_reporting/agent/knowledge_bases/OverallSummary_Spec_ja.md +++ b/engage-box/roi_reporting/agent/knowledge_bases/OverallSummary_Spec_ja.md @@ -6,7 +6,7 @@ - purpose: "指定された期間における主要パフォーマンス指標（KPI）、トレンド、上位キャンペーン/ジャーニーを可視化する。" - source_tables: - "daily_summary" - - "event_master" # ランキングでの名前検索に使用 + - "events_master" # ランキングでの名前検索に使用 ## 2. フィルタ - filter: @@ -46,7 +46,7 @@ - component_id: "campaign_performance_ranking" - component_type: "table" - title: "Top 5 Campaigns" - - source_tables: ["daily_summary", "event_master"] + - source_tables: ["daily_summary", "events_master"] - dimensions: - { id: "campaign_name", display_name: "Campaign Name" } - { id: "campaign_id", display_name: "Campaign ID" } @@ -68,7 +68,7 @@ - component_id: "journey_performance_ranking" - component_type: "table" - title: "Top 5 Journeys" - - source_tables: ["daily_summary", "event_master"] + - source_tables: ["daily_summary", "events_master"] - dimensions: - { id: "journey_name", display_name: "Journey Name" } - { id: "journey_id", display_name: "Journey ID" } diff --git a/engage-box/roi_reporting/workflows/reporting_agent/README.md b/engage-box/roi_reporting/workflows/reporting_agent/README.md index 750a0ee0..6c83a87b 100644 --- a/engage-box/roi_reporting/workflows/reporting_agent/README.md +++ b/engage-box/roi_reporting/workflows/reporting_agent/README.md @@ -54,8 +54,6 @@ The `config.yaml` file allows you to configure: 1. Create Database named `engage_roi_reporting` -1. Prepare Revenue data table named `revenue_table` under `engage_roi_reporting` database - 1. Edit the `config.yaml` file to match your environment after you download this example 1. Set email_domains When you send emails using Engage Studio, a database with a name beginning with "delivery_email_" is generated. Please list that database name under `email_domains` instead of the existing database name, `delivery_email_example_com`. @@ -63,11 +61,21 @@ The `config.yaml` file allows you to configure: 1. Set endpoint Please set the endpoints that matches the Treasure Data region you are using. In this example, the US region endpoints are set. If you are using the Tokyo region, please comment out the US region endpoints and use the commented out endpoints. + 1. Set revenue generation settings + The workflow can generate sample revenue data for testing by setting `revenue_generation.generate_sample: true` in config.yaml. This creates realistic dummy data for verifying report output. **Note**: Sample data is for testing only. For production use, you must prepare your own `revenue_table` with actual conversion and revenue data from your systems, and set `generate_sample: false`. + + 1. Create `tdx.json` in the workflow directory (if it doesn't exist): + ```json + { + "workflow_project": "reporting_agent" + } + ``` + 1. Upload your project - Upload the project using `td workflow push` command in the same directory as `report_preparation.dig`. + Upload the project using `tdx wf push` command in the same directory as `report_preparation.dig`. 1. Register Master Key(API Key) to Secret - Please register Master Key to the secret of uploaded project. The name of the Secret is `td.apikey`. + Register Master Key to the secret of the uploaded project using `tdx wf secrets set reporting_agent "td.apikey=ACCOUNT_ID/YOUR_MASTER_API_KEY"`. The name of the Secret is `td.apikey`. ### Scheduled Execution @@ -236,7 +244,6 @@ scripts/reporting_agent/generate_revenue_data.py ## Important Notes -- This workflow is designed to be run by the PS team - The workflow should be implemented as a user-defined workflow - Handle API keys with appropriate security measures