Looker Demo Creator (demo-create)

From zero to production Looker demo in minutes. Automated, deterministic orchestrator for creating end-to-end Looker demos, synthetic BigQuery datasets, 3NF Snowflake LookML semantic models, 100% test-verified dashboards, Conversational Analytics (CA) Agents published to Gemini Enterprise (GE), and Embedded Analytics portals.

Overview

demo-create unifies the full-stack Looker demo lifecycle into a deterministic, gated pipeline:

1. Pre-Flight & Skill Sync (pre-check): Audits GCP/Looker credentials, prunes deprecated MCP servers/skills, and installs CLI-first skills into ~/.gemini/config/skills/.
2. Schema Co-Design & Modular DAG Synthesis (data generate): Designs 3NF relational schemas (Mermaid ERD + sample preview) and synthesizes Parquet tables (>7,500 rows/sec) via synthetic-data-authoring.
3. BigQuery Ingestion (data upload): Creates datasets and loads partitioned/clustered Parquet tables into BigQuery.
4. LookML Modeling & QA Deployment (lookml): Introspects BigQuery/Dataplex metadata into SPEC.md, generates views/explores/dashboards, validates 100% of queries, and releases via lkr-dev-cli.
5. Conversational Analytics & Gemini Enterprise (agent / ge): Grounds 1:1 Golden Queries from dashboard tiles, links them to a Looker CA Agent, and publishes to Gemini Enterprise.
6. Embedded Portal Scaffolding (embed): Scaffolds a branded React/Vite looker-embed-demo application.

What Gets Automated: Production Deliverables Inventory

Instead of spending days or weeks stitching together synthetic data scripts, debugging LookML joins, hand-crafting dashboard tiles, writing validation queries, and plumbing AI agent endpoints, demo-create produces a complete, production-grade enterprise demo in minutes:

⚡ Spotlight: From Raw Data to Gemini Enterprise in Minutes

A flagship capability of demo-create is bridging the gap between raw data synthesis and cross-organizational enterprise AI in minutes:

graph LR
    Tiles["Dashboard Query Tiles"] --> Ground["Extract & Ground Golden Queries<br/>(expanded_share_url)"]
    Ground --> LinkAgent["Link to Looker CA Agent<br/>(PATCH /api/4.0/agents/{id})"]
    LinkAgent --> PublishGE["One-Click Publish to GE<br/>(POST /api/4.0/internal/agents/{id}/publish)"]
    PublishGE --> Chat["Natural Language Querying<br/>in Gemini Enterprise Apps"]

1. Deterministic Dashboard-to-Query Extraction: Every query tile from your generated executive dashboard is inspected and translated into an active Looker query.
2. Looker 4.0 Golden Query Grounding: Base queries are created via POST /api/4.0/queries to obtain deterministic expanded_share_url permalinks, then registered as 1:1 Golden Queries (POST /api/4.0/golden_queries).
3. Agent Linking: Golden queries are bound to the Conversational Analytics Agent (PATCH /api/4.0/agents/{agent_id}), establishing high-precision semantic grounding.
4. One-Click Gemini Enterprise Publishing: The agent is published directly to connected Gemini Enterprise apps via POST /api/4.0/internal/agents/{agent_id}/publish.

Within minutes of starting the flow, non-technical users and executives can query the entire domain dataset in natural language directly within Gemini Enterprise.

📄 Inspect a Real Deliverable

Curious what the final output looks like? Inspect real deliverables produced by a completed run:

👉 View Canonical Technical Spec (SPEC.md): IoT Trucking Fleet Analytics 👉 View Canonical Delivery Report (DELIVERY_REPORT.md): IoT Trucking Fleet Analytics

Key highlights from the report:

• BigQuery Summary: 6 relational tables, 21,675 rows across dim_vehicles, fct_trips, fct_sensor_telemetry, etc.
• LookML Architecture: 3NF ERD with Native Derived Table (vehicle_metrics_ndt) eliminating Chasm Traps.
• Quality Audit: 19 / 19 (100%) dashboard tile queries tested with HTTP 200 OK before production release.
• Live AI Agent: 7 pre-seeded Golden Queries and verified Gemini Enterprise publish state.

Prerequisites

Before running demo-create, ensure the following tools, cloud roles, and Looker settings are in place. For the full IAM Principal Matrix, copy-paste gcloud setup script, granular Looker role permissions, OAuth client registration, and SSH port-forwarding guide, see docs/PREREQUISITES.md.

👉 Full Setup, IAM Matrix & gcloud Bootstrap Script → docs/PREREQUISITES.md

Getting Started: Two Ways to Build

🚀 Mode 1: AI Agent Pair-Programmer (Primary Hero Flow)

Run interactively with your AI coding assistant (Antigravity, Claude Code, or AgentAPI) using the looker-demo-orchestrator skill.

Step 1: Install Persistent CLI Tools

uv tool install looker-demo-cli

Installs demo-create, looker-demo-cli, and lkr (lkr-dev-cli) globally across terminal sessions.

Step 2: Run Pre-Flight Audit & Auto-Fix

demo-create pre-check --fix

Verifies GCP/Looker credentials, prunes deprecated MCP servers (data-designer, bigquery, knowledge-catalog), and syncs CLI-first skills. Fails fast (exit code 3) if authentication is missing.

Step 3: Configure Authentication (If Blocked)

# 1. Google Cloud & Application Default Credentials (ADC)
gcloud auth login
gcloud auth application-default login
gcloud config set project <PROJECT_ID>

# 2. Looker OAuth Login
lkr auth login

Step 4: Launch the AI Demo Creation Flow

Instruct your AI assistant in chat:

"Create an end-to-end Looker demo for IoT Fleet Analytics (or SaaS ARR, Retail, Fintech)."

The AI agent orchestrates the gated workflow interactively:

• Interactive Schema Co-Design & Modular DAG Synthesis: Proposes a Mermaid ERD and 5–10 row sample preview at Gate 1 before synthesizing Parquet tables (>7,500 rows/sec) via synthetic-data-authoring and loading BigQuery.
• Fast-Path Deterministic CLI Execution: Runs compiled CLI subcommands directly (demo-create data, lookml model, lookml optimize, lookml deploy, agent create, agent publish).
• On-Demand Specialized Subagents: Spawns data-engineer, lookml-snowflake-modeler, lookml-dashboard-designer, lookml-qa-validator, and embed-portal-engineer only when required by the gate.

💻 Mode 2: Standalone CLI (Headless Engine)

Execute demo-create directly from your terminal or CI/CD pipeline, one gate at a time:

demo-create pre-check --fix
demo-create data generate --domain retail --row-count 25000 --output-dir scratch/parquet
demo-create data upload --parquet-dir scratch/parquet --gcp-project my-gcp-project --dataset retail_analytics
demo-create lookml model --looker-project retail_analytics --dataset retail_analytics --connection my_bq_connection
demo-create lookml deploy --looker-project retail_analytics --lookml-dir lookml

State is persisted to .demo-state.json between calls, so later gates inherit earlier answers and you only pass what changes. See docs/COMMANDS.md for ephemeral uvx, .venv, and local editable installation patterns.

Documentation

Commands Quick Reference

Use demo-create status (or demo-create status --json) at any point to inspect completed gates and get the literal next command to run:

$ demo-create status
┏━━━┳━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━┳━━━━━━━━━━━━┓
┃   ┃ Gate ┃ Stage                                    ┃ Status  ┃ Human gate ┃
┡━━━╇━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━╇━━━━━━━━━━━━┩
│ ✓ │    0 │ Environment audit & 4-target confirmation│ done    │ confirm    │
│ ✓ │    1 │ Schema co-design, synthesis & BQ load    │ done    │ confirm    │
│ ▶ │    2 │ Semantic modeling & dashboard generation │ current │ --         │
│ · │    3 │ Optimization, validation & release       │ pending │ confirm    │
│ · │    4 │ Conversational Analytics agent grounding │ pending │ confirm    │
│ · │    5 │ Gemini Enterprise publishing             │ pending │ confirm    │
└───┴──────┴──────────────────────────────────────────┴─────────┴────────────┘
→ Gate 2: Semantic modeling & dashboard generation
    $ demo-create lookml model --looker-project retail_demo --dataset retail \
        --connection acme_bigquery --gcp-project acme-analytics

👉 Exhaustive Command & Flag Reference → docs/COMMANDS.md 👉 Architecture, Gated State & Skill Layout → docs/ARCHITECTURE.md