Skip to main content

Metadata enrichment

Common questions about how context agents work, what they support, and how enrichment is tracked.

Does AI overwrite my existing metadata?​

No. Context agents only enrich assets that are missing the target metadata attribute. If an asset already has a description, README, or linked terms, the agent skips it. Existing values are never overwritten.

How long does enrichment take?​

Enrichment can take up to a few hours for large collections (1,000+ assets). You can monitor progress live from the collection overview without leaving the page.

Do agent runs cost AI credits?​

Yes. Each agent run consumes AI credits based on the number of assets processed.

These collections are only created when a supported BI source is connected to Atlan. If no BI source is connected, these collections don't appear.

Which sources are supported for each default collection?​

CollectionSources
Popular SQL AssetsSnowflake, Databricks, BigQuery
Popular BI ReportsAll supported BI sources
Gold LayerBI + SQL sources
Upstream of Popular BIBI + SQL sources
DQ Connected AssetsAll sources with connected DQ tools
Assets with OwnersAll sources
Assets with Product or DomainAll sources
Assets with TermsAll sources

What assets does each agent support?​

AgentSupported assets
DescriptionAll asset types
READMEAll asset types
SQL IntelligenceTables and views with query history
Link Terms (coming soon)Tables, columns, BI assets
note

Broader asset type support is enabled by the Atlan Lakehouse Gold Layer, which provides the usage signals agents rely on across all connected sources.

SQL Intelligence requires associated query history from connected data warehouse sources, so it applies to SQL assets only.

How often do collections refresh?​

Collections refresh periodically based on usage signals from your connected sources: query logs, lineage relationships, and BI usage data. They update automatically as your usage patterns change.

How's metadata coverage calculated?​

Coverage % is the percentage of assets in a collection that have a given attribute filled in. For example, if 60 out of 100 assets have a description, the coverage for Description is 60%.

How many assets can be enriched per run?​

Each collection has an enrichment limit of 500 assets per agent run. When a collection contains more than 500 assets, the first 500 are selected based on popularity. If popularity data isn't available, assets are selected alphabetically.

Can I create my own collections?​

Yes. Custom collections are available now. Click + New collection in Context Agents Studio to create one.

Filter assets using:

  • Atlan-native tags: source-synced tags from connectors aren't selectable
  • Custom metadata: first-level attributes only; nested boolean/enum filtering isn't yet supported

Tags with more than 500 assets are greyed out at selection time. Once created, run any agent—Description, README, or SQL Intelligence—on your custom collection.

Collections track parent assets, not columns

Custom collections filter and count parent assets (tables, views, BI reports) only—not columns. You don't need to include columns in your filter. When an agent enriches a table, it automatically enriches all child columns as part of that table. The asset count shown in a collection reflects parent assets only.

See Custom collections for full details.

Can I track additional metadata attributes beyond defaults?​

Yes. Click + Track metadata in the collection detail view to add or remove the attributes shown in the coverage overview.

Who can use Context Agents Studio?​

Users with the Admin or Governance Admin role can use Context Agents Studio—running agents, managing collections, and configuring settings. Other roles can view enriched metadata on assets but can't run agents or manage collections.

How does README agent choose which template to use?​

When README templates are configured in Atlan, the agent evaluates all available templates and selects the best match for each asset based on its type, domain, and context. Template selection is automatic—you can't manually assign a template to a specific asset.

If no template is a strong match for an asset, the agent falls back to default README generation. Creating more targeted or domain-specific templates gives the AI better options to choose from.

In what order can I run agents?​

Agents can run in any order, but the recommended sequence is:

  1. Description: Establishes per-asset semantic context first
  2. README: Can incorporate AI-generated descriptions as additional context
  3. SQL Intelligence: Independent of descriptions and READMEs, but benefits from existing description context

There are no hard dependencies. Running in a different order still produces good output.

What are custom instructions and how do they work?​

Custom instructions let you guide agent output across your organization. They're configured in the Settings section of Context Agents Studio. Key things to know:

  • Org-level only: Custom instructions apply to all agents and all collections globally—not per-collection or per-agent
  • Plain text only: No markdown or rich formatting
  • Prepended to all prompts: Your instructions are added to every AI prompt, shaping output across the board

Use them to reflect your organization's terminology, preferred description style, or business context the AI wouldn't otherwise have.

Are credits charged per asset or per child asset?​

Credits are charged for all assets enriched, including both the parent asset and each of its child assets.

Example: Enriching a table with 50 columns using the Description agent costs 510 credits. This includes 10 credits for the parent table and 10 credits for each of the 50 columns.

See Credit usage for full pricing details.

See also​