← Data Engineering CopilotCONTENT HISTORY

Update to Data Engineering Copilot

Snapshot Oct 27, 2026 · 00:42 UTC · version 0.1.0

WHAT CHANGED

Package or technical metadata updated

Package or technical metadata updated

Observed in package metadata. These changes alone do not establish a new customer-facing feature.

Save Data Engineering Copilot and check future changes in Following.

Up to 10 plugins free · no card required.

All fields and original values.

Is v2 template

Before

Oct 24, 2026 · 13:26 UTC

Not present

After

Oct 27, 2026 · 00:42 UTC

false

Compare saved observations

Download comparison JSON
Full technical diff · 1 changed fields

added /is_v2_template

BEFORE
Field was absent
AFTER
false
Full snapshot data
{
  "canonical_app_id": null,
  "connector_id": null,
  "created_at": "2026-09-23T19:17:18.763916Z",
  "discoverability": "LISTED",
  "id": "plugins_6ab424ad5b448191b8fede2ebf569333",
  "is_template": false,
  "is_template_instance": false,
  "is_v2_template": false,
  "name": "production-data-engineering-copilot",
  "release": {
    "app_ids": [],
    "app_manifest": null,
    "app_templates": [],
    "description": "Production data engineering architecture, debugging, recovery, and reliability workflows.",
    "display_name": "Data Engineering Copilot",
    "id": "pluginrel_d255d856c2248191bf1362c3046b509c",
    "interface": {
      "brand_color": null,
      "capabilities": [
        "Design reliable batch, CDC, streaming, and lakehouse architectures",
        "Debug failed, slow, duplicated, stale, or backlogged production pipelines",
        "Plan safe replay, backfill, recovery, and checkpoint strategies",
        "Review Delta MERGE logic for keys, ordering, duplicates, updates, and deletes",
        "Diagnose Spark and Databricks performance using plans, shuffle, spill, skew, and file evidence",
        "Design Structured Streaming state, watermark, checkpoint, and sink behavior",
        "Create production-oriented SQL, PySpark, Databricks, and Airflow patterns",
        "Build data-quality gates, reconciliation, freshness checks, and operational runbooks",
        "Evaluate retry safety, idempotency, schema evolution, and downstream contracts",
        "Use current official docs for Spark, Databricks, Delta Lake, Airflow, and runtime-specific behavior"
      ],
      "category": "Data & Analytics",
      "composer_icon_dark_url": null,
      "composer_icon_url": "https://files.openai.com/content?id=file_0000000010dc81fb9a972b5977355f9a",
      "default_prompt": "Debug why this production pipeline is failing or producing wrong data.",
      "default_prompts": [
        "Debug why this production pipeline is failing or producing wrong data.",
        "Design a reliable CDC or streaming pipeline for this use case.",
        "Plan a safe backfill or replay without duplicating or losing data."
      ],
      "developer_name": "Krishna Sathvik",
      "logo_url": "https://files.openai.com/content?id=file_00000000524481f890727a5fa01bd762",
      "logo_url_dark": null,
      "long_description": "Data Engineering Copilot helps you design, debug, recover, and improve production data systems across Spark, Databricks, Delta Lake, SQL, CDC, Structured Streaming, Airflow, backfills, data quality, observability, and lakehouse architectures. It can diagnose failed or slow pipelines, reason about duplicate and late data, plan safe replay and backfill strategies, review checkpoint and streaming-state risks, tune Spark from execution evidence, and create production-oriented SQL, PySpark, and orchestration patterns. It prioritizes correctness, recoverability, SLA, security, and cost before scaling or redesigning.",
      "plugin_category_id": "data & analytics",
      "privacy_policy_url": null,
      "screenshot_urls": [],
      "short_description": "Debug production data systems",
      "terms_of_service_url": null,
      "website_url": null
    },
    "keywords": [
      "data-engineering",
      "spark",
      "databricks",
      "delta-lake",
      "cdc",
      "streaming",
      "airflow",
      "data-quality"
    ],
    "mcp_servers": [],
    "onboarding_skill_name": null,
    "requires_local_executor": false,
    "skills": [
      {
        "description": "Production-focused workflow for designing, debugging, recovering, tuning, and operating data pipelines across Spark, Databricks, Delta Lake, SQL, CDC, Structured Streaming, Airflow, backfills, quality, observability, and lakehouse systems.",
        "interface": {
          "brand_color": null,
          "default_prompt": "Debug why this production pipeline is failing or producing wrong data.",
          "display_name": "Data Engineering Copilot",
          "icon_large_url": null,
          "icon_small_url": "https://files.openai.com/content?id=file_0000000000c081f598f2dfb37f7328b4",
          "iconography": "chart",
          "short_description": "Debug production data systems"
        },
        "name": "data-engineering",
        "plugin_release_skill_id": "pluginrsk_6ab424afaf608191b4c67ed67116dcfc"
      }
    ],
    "version": "0.1.0"
  },
  "scope": "GLOBAL",
  "share_url": "https://chatgpt.com/plugins/plugins_6ab424ad5b448191b8fede2ebf569333?open_in_app",
  "status": "ENABLED"
}

SHA-256 of public snapshot: fd52280e9c1ca574a4836b728eadf931d2c517368968cdb76d68673a7fb71e49