Data Product Recommender
The Data Product Recommender is an unattended agent that runs the same evidence pipeline as the Data Product Generator — identify, reconfirm, synthesize, prioritize — but never creates a product. Instead, it writes recommendation cards to the Alation Opportunities Inbox so data stewards can review and claim them at their own pace.
This agent is designed to run without a human in the loop. It does not stop to ask for approval; it runs the full pipeline and writes the results.
How it works
Section titled “How it works”- Reads the current Opportunities Inbox to avoid re-proposing already-active clusters
- Identifies candidate table clusters from relational database query usage and catalog metadata
- Reconfirms each cluster against BI usage data and per-table usage detail
- Groups tables into coherent clusters and ranks them by impact
- Writes all candidates to the Opportunities Inbox in a single batch
Input parameters
Section titled “Input parameters”Required:
message(string): Describes the scope — “scan all active datasources” or “recommend data products for the SALES schema”
Optional:
datasource_id(integer): Scope the evidence pipeline to a single datasource
Output format
Section titled “Output format”The agent produces thinking, tool call, tool return, and text blocks as it runs. It does not pause for input. The final message reports the outcome: how many cards were inserted, how many already existed, and how many were skipped.
Recommendation card fields
Section titled “Recommendation card fields”Each card written to the Opportunities Inbox contains:
| Field | Description |
|---|---|
title | Business-outcome name (e.g. “Sales Orders”), not a schema or table name |
short_description | One line leading with business value and the BI reports it supports |
source | The primary signal: query_history (default) | bi_usage | strategic_insights |
confidence | high | medium | low based on usage strength and BI coverage |
member_tables | Non-empty list of fully-qualified table names |
evidence | Usage context, BI consumers, confidence rationale, and suggested example questions |
Behavior notes
Section titled “Behavior notes”- Checks the inbox first — skips any candidate that substantially overlaps an existing active card
- Writes all candidates in a single batch; skipped candidates are not retried
- Individual query details and user identities from usage data are never exposed
- Gaps in BI usage data are noted in the evidence rather than being treated as confirmation that no consumers exist
Related
Section titled “Related”- Data Product Generator — the interactive companion that creates and enriches products in a supervised session
- Recommend data products recipe
- All built-in agents