データアナリスト向けワークフロー

You: I need to analyze Q1 conversion performance. What data do we have
     related to user signups, purchases, and page views?

AI: [Tool: Bash] tdx databases
    [Tool: Bash] tdx tables marketing_prod
    [Tool: Bash] tdx describe marketing_prod.user_events
    [Tool: Bash] tdx describe marketing_prod.purchases

    I found two relevant tables in marketing_prod:

    | Table | Key Columns | Row Estimate |
    |-------|-------------|-------------|
    | user_events | user_id, event_type, time | ~45M rows |
    | purchases | user_id, amount, product_id, time | ~2.1M rows |

    user_events contains signup, page_view, and add_to_cart events.
    I can calculate conversion as signups → purchases. Shall I proceed?

You: Yes, calculate daily conversion rate (signups to purchases) for Q1.
     Break it down by week and by traffic source.

AI: [Tool: Bash] tdx query -e trino "
      SELECT
        TD_TIME_FORMAT(e.time, 'yyyy-ww') AS week,
        e.source AS traffic_source,
        COUNT(DISTINCT e.user_id) AS signups,
        COUNT(DISTINCT p.user_id) AS purchasers,
        ROUND(COUNT(DISTINCT p.user_id) * 100.0
              / NULLIF(COUNT(DISTINCT e.user_id), 0), 2) AS conversion_rate
      FROM marketing_prod.user_events e
      LEFT JOIN marketing_prod.purchases p
        ON e.user_id = p.user_id
        AND TD_INTERVAL(p.time, '-90d')
      WHERE e.event_type = 'signup'
        AND TD_INTERVAL(e.time, '-90d')
      GROUP BY 1, 2
      ORDER BY 1, 2
    "

    Here are the results:

    | Week | Source | Signups | Purchasers | Rate |
    |------|--------|---------|------------|------|
    | 2026-01 | organic | 1,240 | 186 | 15.0% |
    | 2026-01 | paid | 890 | 98 | 11.0% |
    | ... | ... | ... | ... | ... |

    Conversion rate dropped from 15% in January to 11.2% in March,
    with paid traffic showing the steepest decline.

You: Show me the weekly conversion trend as a line chart,
     with separate lines for each traffic source.

You: The paid drop is steeper than I expected. Can you add a scatter plot
     showing spend vs. conversion for paid traffic?

You: Build a dashboard with:
     - KPI cards for overall Q1 conversion, total signups, and total revenue
     - The conversion trend line chart
     - A bar chart of conversion by source
     - A table of the top 10 underperforming weeks

You: That last query took 3 minutes. Can you optimize it?

AI: The original query scanned all partitions. I've rewritten it with
    explicit TD_TIME_RANGE bounds and moved the join to a CTE:

    [Tool: Bash] tdx query -e trino "WITH signups AS (...) ..."

    Execution time: 12 seconds (was 3 minutes).
    The main improvement was partition pruning — the original WHERE clause
    didn't use TD_INTERVAL on the purchases table.

You: Create a PowerPoint deck with these findings for the leadership meeting.
     Include the charts, key takeaways, and a recommendation slide.

You: Also export the raw data as an Excel file with separate sheets
     for weekly metrics and source breakdown.

You: Audit the customer_profiles table for data quality issues —
     check for nulls, duplicates, and stale records.

AI: 1. [Bash] tdx describe marketing_prod.customer_profiles → スキーマ確認
    2. [Bash] tdx query → 列ごとのNULL件数
    3. [Bash] tdx query → user_idの重複検出
    4. [Bash] tdx query → 鮮度確認（90日以上更新されていないレコード）
    5. [open_file] 列ごとのNULL率の棒グラフ
    6. [Text] 優先度付きの改善手順を含むサマリー

You: The daily_etl workflow failed last night. What happened?

AI: 1. [Bash] tdx wf sessions daily_etl → 失敗したセッションを特定
    2. [Bash] tdx wf attempt logs <session_id> → エラーログを読み込む
    3. [Thinking] 根本原因：テーブルが見つからない（スキーマ変更）
    4. [Write] 修正を加えた.digファイルを更新
    5. [Text] 説明と_retryブロックの追加に関する推奨事項

You: I just got access to the new clickstream_raw table.
     What's in it and is it useful for attribution modeling?

AI: 1. [Bash] tdx describe clickstream_raw → スキーマとサンプル確認
    2. [Bash] tdx query → 行数、日付範囲、イベントタイプ
    3. [Bash] tdx query → 主要ディメンションのカーディナリティ
    4. [open_file] イベントタイプの分布
    5. [Text] 評価：マルチタッチアトリビューションに適している、
             purchasesテーブルとの推奨JOINストラテジー