Snowflake vs BigQuery: AI features compared

Metadata about the conversation, such as the agent and data sources used.

Reach for Deep Research when you need to understand why something happened, when the answer likely spans multiple tables or domains, or when you want a citable report you can hand to stakeholders.

Conversational analytics supports the following AI and ML functions in response to chats with data agents and data sources, and in verified SQL queries that you create.

CoCo infers everything else (task type, target column, evaluation metric, train/test split strategy) and asks you to confirm before proceeding.

- "Using SQL, forecast the future traffic of my website for the next month based on bigquery-public-data.google_analytics_sample.ga_sessions_. Then, plot the historical and forecasted values."

Each time the automation runs, Snowflake CoWork re-executes the original question against current data and delivers the result to your email.

Schedule a query by providing the following details in your prompt:

With MCP connectors, your agents can go beyond answering questions to taking action across enterprise systems, such as creating Jira tickets, updating Salesforce records, or posting to Slack, all within Snowflake’s governed environment.

The Data Engineering Agent cannot execute pipelines. You must review and run or schedule pipelines.

Custom agents let you pre-configure a name, description, allowed tools, model, and system prompt — useful when you have a recurring kind of task you want to delegate to a specialized agent.

Seamless orchestration: Ask a general analytical question (for example, "How is our sales pipeline trending in the last 3 months?") and Gemini Enterprise automatically routes the query to the relevant data agent.

Instead of writing a YAML specification by hand, you describe what you want and Autopilot generates the logical tables, relationships, and metrics for you.

You can review, edit, and publish these descriptions to Knowledge Catalog to improve data discoverability and documentation.

Build semantic views for Cortex Analyst with verified query representations, metrics, and dimensions

Open a chat session with the app context loaded for making changes.

You can prompt Gemini in BigQuery to explain a SQL query in natural language.

For other chart types, ask Snowflake CoWork to change the chart.

You can generate SQL in the query editor by describing the query that you want in a comment.

These interfaces return metadata, not content.

Artifact administration SQL manages existing artifacts; it doesn’t create artifacts or edit their content.

You can ask follow-up questions about a saved chart or table.

The assistant works with new or existing data canvases.

The saved artifact preserves the underlying query, visualization specification, and a cached snapshot generated with the viewer’s credentials.

As the plan runs, generated code and text appear in the notebook.

Create a new Streamlit application, or replace an existing one.

To manage BigQuery Studio saved queries by using the BigQuery API:

Each viewer’s chart or table snapshot is generated under that viewer’s credentials.

All viewers see the rendered Data Apps based on the author's access.

Screenshot capture for the agent to verify its own work

CoCo Desktop scaffolds working applications connected to your Snowflake data, runs a local development server for live iteration, and deploys the finished app to Snowflake.

To save time, use the integrated agent to generate the code for you.

Push committed changes from the Streamlit back to its connected Git repository.

Create a new Streamlit application, or replace an existing one.

An MCP connector in Snowflake connects Snowflake CoWork and Cortex Agents to a remote Model Context Protocol (MCP) server, letting the agent discover and invoke tools hosted by providers such as Atlassian Jira, Salesforce, or your own custom applications.

Given a Snowflake object, returns data lineage information upstream or downstream from that object.

VIEW: A virtual table defined by a SQL query.

Skill invocations are surfaced in the thinking steps during Snowflake CoWork interactions.

Matches are always marked as verified.

This preserves the business logic you’ve already built in Power BI, including metric definitions, table relationships, and column descriptions, and makes it available to Cortex Analyst and other Snowflake tools.

Create BigQuery custom glossary terms for each agent or import business glossary terms from Knowledge Catalog.

You can pick a specific model, or one of these Auto options that choose a model for you:

In the Model section, choose which types of models are available to users in a conversation with the agent.

When the user’s question is similar to a query in the Verified Query Repository (VQR), Cortex Analyst uses that query to generate the SQL query in its response.

If the response is not what you expect, change the settings in the Editor section to refine the data agent configuration until you get satisfactory responses.

When the user’s question is similar to a query in the Verified Query Repository (VQR), Cortex Analyst uses that query to generate the SQL query in its response.

If an agent can use a verified query to answer a question that you ask it, to ensure a trustworthy answer, the agent invokes the query exactly as written.

A shared resource budget lets you track and control credit consumption for AI features (such as AI Functions, Cortex Agents, Cortex Code, Snowflake CoWork, and the AI Gateway) broken down by the team or cost center consuming them.

Filter your billing report by label to understand agent costs.

Data stays within Snowflake’s governance boundary. By default, Cortex Analyst is powered by Snowflake-hosted LLMs from Mistral and Meta, ensuring that no data, including metadata or prompts, leaves Snowflake’s governance boundary.

When a user uses Gemini in BigQuery, a prompt and its relevant context are sent to Google's large language models (LLMs) for processing.

Admin-managed RSS: An administrator sets AGENT_RESTRICTED_SESSION_SCOPE on a session policy, then attaches that policy to the account or to specific users.

Table selection isn't a security setting.

Both the developer and the reviewer can now inspect the DCM changeset from the plan to confirm that all changes are as expected.

If you need to roll back, you point the alias to a previous named version.

BigQuery lets you query and restore data stored in BigQuery that was changed or deleted within your time travel window.

This topic covers how to see what the gateway is spending and how to limit it.

You are still subject to the quotas enforced by the APIs called by the MCP server tools.