Skip to main content

Example prompts

Use these example prompts to explore assets, trace lineage, generate SQL, and get step-by-step guidance—all from a natural-language chat.

Prerequisites​

Before you begin, make sure you have:

Understand your data assets​

Get quick answers about what a table, column, or dataset represents without opening the asset page or asking a teammate. Useful when exploring unfamiliar datasets or verifying a column's meaning before using it in a query.

Give me a high-level map of our data estate: how many assets per connector, how many are governed (certified, owned, documented), and where are the biggest gaps?
Find all tables related to payments, transactions, or accounting. Break them down by system (Snowflake vs Databricks vs Postgres) so we can map our financial data landscape.
Find all tables related to revenue, billing, or invoicing across all our systems. Show which ones are verified and who owns them.
Compare these two assets: SALES_DAILY_AGG and SALES_MONTHLY_AGG and highlight differences in purpose, freshness, and downstream usage. What does the `churn_flag` column in SALES_DAILY_AGG mean?

Trace lineage and impact​

Understand where your data comes from and what happens if something changes. Use these prompts to walk through upstream sources, downstream dependencies, and assess the blast radius before making schema changes or deprecating a column.

Find the upstream lineage for our main customer table. I need to trace where customer data originates and what transformations happen along the way.
What is the end-to-end lineage of the supply_chain_inventory table? Which upstream assets haven't been refreshed recently or have data quality issues? What dashboards or reports does it ultimately power downstream?
Show me all dbt models and their downstream Snowflake tables. I need to understand the blast radius of a pipeline failure and which dashboards are affected.

Generate SQL queries​

Generate SQL without writing it from scratch. Conversational AI uses your catalog metadata to produce queries grounded in your actual table and column names.

Write a SQL query to find all tables whose name contains 'order' or 'transaction' across Snowflake, Databricks, and Postgres. I'm scoping out what transactional data we already have before building a new orders pipeline.
Write a SQL query to find the 'riskiest' tables: tables in the top 25% by popularity score that are missing two or more of: owner, description, certification, and lineage.

Explore your glossary​

Your business glossary holds the agreed-upon definitions for metrics, terms, and concepts across the organization. Use these prompts to look up definitions, clarify similar terms, or find which data assets are linked to a specific glossary entry.

Find all terms related to churn, retention, or customer lifecycle. Also check if we have a specific glossary term that defines 'churn rate' so I use the right business definition.
Tell me about the most referenced business term in our catalog: how it's defined, what powers it, and all reports, dashboards, and assets linked to it across the organization.
What does 'MRR' mean in our organization? Check the glossary for a definition, then find all tables and dashboards linked to that term so I know where to find MRR data.

Check data quality and freshness​

Before building a report or making a decision, verify your data is reliable. Use these prompts to check refresh timestamps, quality flags, and staleness so you know whether the data is current and trustworthy.

Find tables whose source was last updated over 6 months ago but are still certified, so we can flag them for review.
Are there any data quality issues flagged on @dim_products? Which tables in the analytics schema haven't been updated in over 7 days?

Find data owners and experts​

Conversational AI uses ownership and stewardship metadata from your catalog to point you to the right person, whether you need to report a data issue, request access, or understand a business decision behind a dataset.

I have questions about the MONTHLY_RECURRING_REVENUE table in Snowflake. Who owns it, and who else frequently uses it that I could reach out to?
A new VP of Engineering has joined and wants to meet our key data stewards. Who are the top 10 people who own the most assets? Show their names, asset counts, and which connectors they cover.
A team member is leaving next Friday. Find every asset they own—tables, views, dashboards, dbt models, glossary terms—so we can reassign ownership before they lose access. Their username is jane.smith.

Learn how to do things in Atlan​

Conversational AI can answer questions about how to use Atlan itself, pulling answers from Atlan's documentation so you get step-by-step guidance without leaving the product or searching through help articles.

How do I link a glossary term to a specific table or column in Atlan? I want to tag our 'Monthly Active Users' table with the 'MAU' business term.
Our governance process requires that tables go through Draft to Verified status. How do I certify a table in Atlan and what's the step-by-step workflow?