​

Ask Collate

​

What you can do

• Navigate your data with plain-language and understand what’s the best asset to handle your use case.
• Run SQL queries, discover insights and visualize results.
• Dive deep into assets’ lineage and health.
• Understand your company’s language with the glossary, create new terms, and apply metadata changes.

​

Prerequisites

• Collate AI is installed and enabled in your workspace.
• Metadata, lineage, and usage ingestion jobs are running so Ask Collate has context.
• You have permissions to view and act on the assets you are asking about.

​

Core Capabilities

• Discover: Search certified datasets, BI assets, and databases with metadata filters.
• Analyze: Translate business questions into executable SQL for warehouses like Snowflake or Redshift.
• Visualize: Create charts (bar, pie, donut, etc.) and refine them with follow-up prompts.
• Test: Detect anomalies and suggest data quality tests using profiling and lineage context.
• Lineage: Visualize upstream and downstream dependencies to perform impact analysis.
• Govern: Create or edit glossary terms, assign owners, and tag assets from the chat.

​

Use cases

​

Data steward: glossary and tagging

• Prompt: “Do we have a definition for revenue?”
• Result: Searches glossary terms and suggests creating one if missing.
• Prompt: “Create a term for revenue calculation and tag relevant Snowflake tables.”
• Result: Adds the term, links it to assets such as order_items, and tracks ownership.

​

Data analyst: assess eco-friendly product performance

• Prompt: “Give me total market share for eco vs non-eco products by revenue. Only Tier 1 data.”
• Result: Finds certified Snowflake tables (products, orders, customers), generates SQL, and returns the split with a chart.
• Follow-up: “Use a donut chart with dark green for eco.” Ask Collate updates the styling and summary.

​

Data analyst: customer segmentation

• Prompt: “What percent of customers bought eco products, grouped by customer tier?”
• Result: Produces SQL, groups by tier, and surfaces the insight that higher-tier customers engage more with eco products.

​

Data analyst: product-level checks

• Prompt: “List eco-friendly products with total revenue.”
• Result: Returns a ranked list and flags anomalies (for example, a product with unexpected zero revenue) for follow-up with engineering.

​

Data engineer: troubleshoot data quality

• Prompt: “Show lineage for the customer report dashboard.”
• Result: Maps upstream tables (including customer_360) and downstream impacts.
• Prompt: “Search for anomalies in these tables: nulls, negatives, duplicates.”
• Result: Surfaces outliers (for example, negative unit_price values).
• Prompt: “Create test cases for the products table.”
• Result: Suggests completeness, uniqueness, range, and integrity tests and records who requested them.

​

Best practices

• Be specific with filters (time ranges, owners, schemas) to narrow results.
• Paste failing SQL when asking for fixes and include error context if available.
• Review the explanation that accompanies generated SQL to confirm intent.
• Use follow-up prompts to iterate instead of starting new threads.

​

Troubleshooting

• If answers seem incomplete, verify recent metadata and lineage ingestion runs succeeded.
• If you cannot see certain assets, confirm your Collate permissions for those services.
• For inconsistent results, restate the question with the relevant schema or service name.