Snowflake-Labs/automated-intelligence-dev-day-2026-hol

Snowflake-Labs/automated-intelligence-dev-day-2026-hol

Description: 75-minute hands-on lab: Automated Intelligence with Snowflake

Language: Python

License: Apache-2.0

Stars: 5

Forks: 5

Open issues: 0

Created: 2026-04-29T14:22:15Z

Pushed: 2026-06-04T16:53:40Z

Default branch: main

Fork: no

Archived: no

README:

Build an End-to-End Application Using CoCo on Snowflake

Overview

In this hands-on lab, you'll build a complete AI-powered retail analytics platform entirely within Snowflake — no external infrastructure required. Using Snowflake CoCo as your AI-assisted development environment, you'll work through the full data lifecycle: stream real-time orders via Snowpipe Streaming, MERGE them into production tables with Gen2 Warehouses, transform them through a 3-tier Dynamic Tables pipeline, and serve them with Interactive Tables for low-latency point lookups.

You'll build analytical models with dbt, monitor data quality with Data Metric Functions, and create custom CoCo skills for reusable workflows. Tie it all together with Snowflake CoWork — a conversational AI interface where a Cortex Agent orchestrates Cortex Analyst and Agentic Search to answer "what happened" and "why" from both structured and unstructured data. Finally, evaluate your agent with ground-truth datasets, implement row-level security, and expose your agent as a managed MCP server for external AI clients.

What You'll Learn

• Accelerate development with Snowflake CoCo (AI-assisted SQL, deployment, and data exploration)
• Stream real-time data with Snowpipe Streaming and transform with Dynamic Tables
• Serve low-latency queries with Interactive Tables and Gen2 Warehouses
• Build analytical models with dbt
• Monitor data quality automatically with Data Metric Functions
• Create and query managed Iceberg V3 tables (deletion vectors, row lineage) *(optional)*
• Create custom CoCo skills for reusable team workflows
• Build a Cortex Agent with Cortex Analyst (semantic view + verified queries) and Agentic Search (multi-index Cortex Search)
• Evaluate agent quality with ground-truth datasets and LLM judges
• Expose agents as managed MCP servers for external AI clients
• Implement transparent row-level security with Row Access Policies

What You'll Build

A production-grade AI-powered retail analytics platform on Snowflake — from raw data to conversational AI insights, entirely within a single platform. You'll create dynamic transformation pipelines, interactive low-latency tables, dbt analytical models, a Cortex Agent that answers questions across structured and unstructured data, row-level security that works transparently through AI, and an MCP server that exposes your agent to external clients.

Prerequisites

• Access to a Snowflake account
• Python 3.8+ installed locally
• Git installed locally
• Basic familiarity with SQL and command-line tools

---

Table of Contents

1. [Setup](#setup) 2. [Explore Your Data](#explore-your-data) 3. [Data Quality](#data-quality) 4. [Dynamic Tables Pipeline](#dynamic-tables-pipeline) 5. [dbt Analytics](#dbt-analytics) 6. [Gen2 Warehouse: Optima Indexing](#gen2-warehouse-optima-indexing) 7. [Interactive Tables](#interactive-tables) 8. [CoCo Custom Skill](#coco-custom-skill) 9. [Snowflake CoWork](#snowflake-cowork) 10. [Security and Governance](#security-and-governance) 11. [Streamlit Dashboard](#streamlit-dashboard) 12. [Agent Evaluation](#agent-evaluation) 13. [MCP Server](#mcp-server) 14. [Optional: Iceberg V3 Features](#optional-iceberg-v3-features) 15. [Optional: Streaming Ingestion](#optional-streaming-ingestion) 16. [Cleanup](#cleanup) 17. [Resources](#resources)

---

Setup

Install Snowflake CLI

The Snowflake CLI (snow) lets you run SQL, deploy apps, and manage Snowflake objects from your terminal.

macOS (using Homebrew):

If you don't have Homebrew installed, first install it by opening Terminal and running:

/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"

Then install Snowflake CLI:

brew install snowflake-cli

Windows:

pip install snowflake-cli

Linux:

pip install snowflake-cli

Verify the installation:

snow --version

You should see output like Snowflake CLI version: 3.x.x.

Install Snowflake CoCo

Snowflake CoCo is an AI-powered coding assistant that runs in your terminal. It helps you write SQL, build pipelines, deploy apps, and explore your data using natural language prompts.

macOS (using Homebrew):

brew install cortex

Windows / Linux:

pip install cortex

Verify the installation:

cortex --version

Alternative: Snowflake CoCo Desktop (Preview)

If you prefer a visual IDE experience, download CoCo Desktop instead of (or alongside) the CLI. It's a native Mac/Windows app with a file editor, integrated terminal, agentic browser, and the same AI capabilities.

> Note: CoCo Desktop is currently a Preview Feature available to all accounts.

On first launch, follow the onboarding wizard: 1. Click Next on the Welcome screen 2. Add your connection (same account identifier and credentials from above) or select an existing one detected from connections.toml 3. Choose Agent mode 4. Pick your theme, then click Get Started

> Tip: If you already configured a connection with snow connection add (below), CoCo Desktop detects it automatically — just select it from the list.

See CoCo Desktop documentation for full details.

Configure Snowflake Connection

Before you can run any commands against Snowflake, you need to configure a connection. This tells the CLI which Snowflake account to connect to and how to authenticate.

Run the interactive connection wizard:

snow connection add

You'll be prompted for the following values (enter them one at a time):

| Prompt | What to enter | Example | |--------|---------------|---------| | Connection name | A short name for this connection | hol | | Account identifier | Your Snowflake account URL (without .snowflakecomputing.com) | myorg-myaccount | | User | Your…