---
title: "You’ve built the media products, now make them personalized"
description: "Media companies may have launched streaming services, digital editions, and mobile apps, yet still face a digital product intelligence gap: product teams must answer behavioral data questions quickly enough to personalize experiences and improve engagement. Databricks Genie gives nontechnical product leaders a conversational interface that translates natural-language questions into SQL queries, visualizations, and actionable insights over governed enterprise data, without requiring code or analyst handoffs. The agent queries governed Delta Lake tables fed by streaming clickstreams, views, and session signals, combining event-level behavior, A/B tests, audience segments, and cross-platform data in conversational answers. The source says internal benchmark accuracy improved from 32% to over 90% through multi-LLM orchestration, specialized knowledge search, and parallel reasoning, and presents Genie as reliable enough for production personalization decisions."
---

# You’ve built the media products, now make them personalized

[Databricks](https://yomu.fyi/company/databricks) · Elena Tesser · May 21, 2026

**Type:** Explainer

## Summary

Media companies may have launched streaming services, digital editions, and mobile apps, yet still face a digital product intelligence gap: product teams must answer behavioral data questions quickly enough to personalize experiences and improve engagement. Databricks Genie gives nontechnical product leaders a conversational interface that translates natural-language questions into SQL queries, visualizations, and actionable insights over governed enterprise data, without requiring code or analyst handoffs. The agent queries governed Delta Lake tables fed by streaming clickstreams, views, and session signals, combining event-level behavior, A/B tests, audience segments, and cross-platform data in conversational answers. The source says internal benchmark accuracy improved from 32% to over 90% through multi-LLM orchestration, specialized knowledge search, and parallel reasoning, and presents Genie as reliable enough for production personalization decisions.

## Context

Media companies have digital products and audience data in place, but product teams may wait for analyst responses before answering behavioral questions. The source frames this delay as a digital product intelligence gap that slows experimentation, product improvement, engagement optimization, and personalization.

## Approach / What changed

Databricks Genie converts natural-language questions into SQL queries, visualizations, and insights over governed enterprise data. It queries Delta Lake tables fed by streaming event data, incorporates clickstreams, views, session signals, A/B tests, and audience segments, and supports cross-platform analysis. It can also help generate targeted audience segments or promotional copy.

## Takeaways

- Genie lets CDOs, product leads, and other business users query clickstream data, A/B test results, and audience segments conversationally without writing SQL or filing analyst requests.
- Unity Catalog provides role-based access controls, data lineage, and audit logging for Genie queries, supporting permissioned and traceable access to governed data.
- Internal benchmark accuracy for Genie improved from 32% to over 90% through multi-LLM orchestration, specialized knowledge search, and parallel reasoning.

**Tags:** [Data Analytics](https://yomu.fyi/topic/data-analytics), [Delta Lake](https://yomu.fyi/topic/delta-lake), [Genie](https://yomu.fyi/topic/genie), [Streaming](https://yomu.fyi/topic/streaming), [Unity Catalog](https://yomu.fyi/topic/unity-catalog)

- Source: [Databricks](https://www.databricks.com/blog/youve-built-media-products-now-make-them-personalized)
- Source URL: https://www.databricks.com/blog/youve-built-media-products-now-make-them-personalized
- Ingested by Yomu: 2026-08-31T03:33:36.918Z

[Read original post](https://www.databricks.com/blog/youve-built-media-products-now-make-them-personalized)