Skip to content

Data Lineage Agents Guide

This guide covers both lineage agents in Alation AI: the Lineage Agent for exploring lineage and generating documentation, and the Lineage Builder Agent for creating, deleting, and debugging lineage.


What you want to doWho can do itAgent
View upstream/downstream lineageAny userLineage Agent
Trace column transformationsAny userLineage Agent
Generate lineage documentationAny userLineage Agent
Create manual lineageServer/Catalog/Source AdminLineage Builder Agent
Delete lineageServer/Catalog/Source AdminLineage Builder Agent
Debug missing lineageServer/Catalog/Source AdminLineage Builder Agent

The Lineage Agent helps you understand how data flows through your pipelines. It can find dependencies, trace column transformations, and save analysis as catalog documentation.

  • message (string, required): Your lineage question or documentation request.

Find dependencies: “What tables feed into the orders table?” “Show me upstream dependencies for table ID 1234” “What uses this table downstream?”

Trace transformations: “How is the revenue_total column calculated?” “What transformations happen to this table’s data?”

Create documentation: “Create lineage documentation for table ID 1234” “Generate a lineage document for the orders table”

ToolWhat It Does
get_search_contextFind tables or columns by name in the catalog
get_filter_contextRetrieve the content of an existing lineage document by ID
get_lineageFetch upstream or downstream lineage graph
generate_lineage_documentationAnalyze SQL transformations for a table’s columns
get_document_templatesList available templates for creating documents
update_catalog_objectLink a document to a table’s custom field
  1. Finds the object you’re asking about by searching the catalog.
  2. Checks whether lineage documentation already exists and answers from it before regenerating.
  3. Chooses the right approach:
    • For “what feeds / what depends on this?” questions, it fetches the lineage graph.
    • For “how is this column calculated?” questions, it analyzes upstream SQL to trace column-level transformations.
  4. When explicitly asked to save documentation, it creates a catalog document and links it back to the table.

Retrieves the lineage graph showing what objects are connected upstream (sources) or downstream (consumers).

Supports:

  • Table-level lineage (otype="table")
  • Column-level lineage (otype="attribute" with column IDs)
  • Filtering by direction (upstream or downstream)

Analyzes SQL dataflows to trace how each column in a table is derived from source columns.

Important: This tool only works for tables.

What it returns:

  • Executive summary of what the table represents
  • Column transformations (calculations, aggregations, renames)
  • Passthrough columns (unchanged from source)
  • Untraced columns (where SQL couldn’t be analyzed)
  • Data quality notes (filters, joins, conditions)
  • Source tables and downstream consumers

You can optionally save the analysis as a document by providing folder_id, document_hub_id, and template_id.

To save lineage documentation, you need a document template with these custom fields:

Field NameField TypeDescription
Source TablesOBJECT_SETLeaf tables where data originates
Downstream TablesOBJECT_SETTables that consume this table’s data
Upstream LayersRICH_TEXTVisual representation of the data pipeline layers
Downstream Tables DetailRICH_TEXTDownstream tables with links
Downstream BI ObjectsRICH_TEXTBI reports and dashboards using this table
Column TransformationsRICH_TEXTHow each column is calculated
Passthrough ColumnsRICH_TEXTColumns that pass through unchanged from source
Untraced ColumnsRICH_TEXTColumns where lineage couldn’t be determined from SQL
Data Quality NotesRICH_TEXTFilters, joins, and conditions that affect data quality

The Lineage Builder Agent helps data stewards and catalog administrators manage lineage end-to-end. It can view existing lineage, create manual lineage paths, delete incorrect lineage, and diagnose why lineage is missing.

  • message (string, required): Your lineage request or question.

Create lineage: “Create lineage from staging.orders to analytics.orders” “Link the customers table as upstream of customer_metrics” “Add lineage between this BI report and its source table”

Delete lineage: “Remove the lineage between staging.orders and analytics.orders” “Delete the manual lineage I created for this table”

Debug missing lineage: “Why is there no lineage for the orders table?” “Lineage is missing for analytics.revenue — help me figure out why” “The lineage for this table looks incomplete”

View lineage: “What feeds the orders table?” “Show downstream for table ID 1234” “What columns feed into revenue_total?”

SkillWhat It Does
lineage-readFetch upstream/downstream lineage graphs, view SQL for edges, trace column transformations
lineage-createCreate or delete manual lineage between tables, columns, or BI objects
lineage-debugStaged diagnostic: QLI status, warehouse probes, parser checks
exploreSearch the catalog to resolve object names to IDs
  1. Identifies what you want to do (view, create, delete, or debug).
  2. Resolves object names to IDs via catalog search when needed.
  3. Routes to the appropriate skill.
  4. For create/delete operations, shows exactly what will change and waits for your approval before executing.

When you ask to create lineage, the agent asks two questions:

Discovery method:

  • Warehouse auto-discovery (Snowflake only) — Queries your warehouse to find actual data flows automatically
  • Manual — You specify the source and target objects directly

Scope:

  • One level — Immediate parents/children only
  • Full upstream — Trace back to root source tables
  • Full end-to-end — Complete upstream and downstream

The agent then finds the objects, shows you the proposed lineage as a diagram, and waits for confirmation before creating it.

Supported object types: tables, columns, BI reports, BI report columns, BI datasources, BI datasource columns.

The agent finds the lineage path, shows you what will be removed, and confirms before deleting. You can delete a specific edge or all lineage between two objects.

The agent runs a staged diagnostic, reporting findings at each step:

StageWhat It Checks
Find tableConfirms the table exists in the catalog
Lineage existenceChecks if any lineage exists, including through temp objects
QLI job statusChecks if QLI has run successfully and when
Warehouse probesQueries the warehouse for write operations to the table
QLI windowVerifies writes fall within the QLI ingestion window
Parser issuesChecks for SQL patterns that the parser can’t handle

The agent stops when it identifies the root cause and recommends a fix.

Supported warehouses for debug: Snowflake, BigQuery, Databricks, Redshift, Oracle.


LimitationAgentNotes
Tables only for transformation analysisLineage Agentgenerate_lineage_documentation only works for tables
Max 1000 nodes per lineage queryBothLineage graph queries cap at 1000 nodes
Max depth of 20 levelsBothLineage traversal stops at 20 hops
Admin permissions for mutationsLineage BuilderCreate/delete require Server, Catalog, or Source Admin
Warehouse support for debugLineage BuilderDebug probes only support Snowflake, BigQuery, Databricks, Redshift, Oracle
BI lineage requires registered datasourceLineage BuilderBI objects must already exist in the catalog
One table at a time for debugLineage BuilderDiagnostic flow runs per table