schema_version: "1.1"
id: adtech/bi-insights-orchestrator
name: BI Insights Orchestrator
description: Orchestrate warehouse and ad platform data analysis into standardized BI insights with QA-aware controls.
version: 0.2.0
released_at: "2026-09-26T00:00:00Z"
category: adtech-agents/analytics
tags:
  - bi
  - analytics
  - orchestration
license: MIT
author:
  name: AI Skills Guide Maintainers
  url: https://github.com/ai-knowledge-hub/ai-skills-guide
repository: https://github.com/ai-knowledge-hub/ai-skills-guide
runtimes:
  - codex
  - claude
  - generic
entrypoints:
  spec: AGENT.md
  readme: README.md
  tests: tests/test-prompts.md
  examples_dir: examples
dependencies:
  skills:
    - adtech/analyst-copilot-bigquery-redshift
    - adtech/dashboard-generator
    - adtech/dashboard-qa-checker
  tools:
    - warehouse/bigquery-mcp-query-runner
    - analytics/ga4-mcp-connector
orchestration:
  model:
    selection: runtime-selected
    required_capabilities: [tool-use, structured-output]
  memory:
    mode: bundled
    path: config/memory-profile.example.json
    required: true
  governance:
    mode: bundled
    path: config/governance.example.json
    required: true
  bindings:
    - {name: warehouse_analysis, kind: skill, package: adtech/analyst-copilot-bigquery-redshift, version: 0.1.0, requirement: required, availability: resolved}
    - {name: dashboard_generation, kind: skill, package: adtech/dashboard-generator, version: 0.1.0, requirement: required, availability: resolved}
    - {name: dashboard_qa, kind: skill, package: adtech/dashboard-qa-checker, version: 0.1.0, requirement: required, availability: resolved}
    - {name: bigquery_sql, kind: tool, package: warehouse/bigquery-mcp-query-runner, version: 0.2.0, requirement: required, access: read-only, availability: resolved}
    - {name: ga4_query, kind: tool, package: analytics/ga4-mcp-connector, version: 0.2.0, requirement: required, access: read-only, availability: resolved}
operational:
  role: Analytics orchestration agent for warehouse-backed BI reporting.
  coordinates:
    - Warehouse and platform metric collection
    - KPI normalization across sources
    - Dashboard and insight generation
  autonomy_level: semi-autonomous
  approval_boundary: May coordinate read-only data analysis and draft reporting outputs; require human approval before any publish or stakeholder-distribution decision.
  outputs:
    - Normalized KPI table
    - Anomaly summary with evidence
    - Publish recommendation
    - Risks and data limitations
usability:
  availability: setup-required
  execution: orchestrator
  limitations:
    - GA4 and BigQuery credentials and provider targets must be configured before data collection.
  quickstart: Install the agent, then configure each provider named by the generated runtime contract.
verification:
  tests_min_prompts: 5
  security_reviewed: false
deprecated: false