# Meet Hex, an AI-Powered Analytics Platform with Notebooks, Apps and more: featuring Rachel Herrera

> This is content from just-tim, the data-and-analytics channel by Tim Ngwena (formerly 'Tableau Tim'). Tim has 12+ years of hands-on BI experience and covers Tableau most of all, plus Power BI, Looker, Hex, SQL and data modelling, the analytics industry, and the craft of doing the job — always tool-agnostic and honest about the trade-offs.

- **Author:** Tim Ngwena (just-tim, https://just-tim.com/about)
- **Published:** 2026-05-04
- **Format:** Video · 53 min watch · transcript available
- **Topics:** Analytics, AI & ML, Tool strategy
- **Tools:** Databricks; Hex (ai, app builder, connections, context studio, notebooks, threads); Python; Snowflake; SQL
- **Canonical:** https://just-tim.com/posts/meet-hex-an-ai-powered-analytics-platform-with-notebooks-apps-and-more-featuring-rachel-herrera
- **Watch:** https://www.youtube.com/watch?v=4RN8HGvY2sM

I sit down with Rachel Herrera, product evangelist at Hex, to explore what the AI-powered analytics platform actually does. She walks through Hex's notebook-first workflow, its data connections, the agentic notebook and visualisation features, the app builder, conversational threads, and the context studio, and we discuss its philosophy on semantic models, SQL quality and what makes an app different from a dashboard.

## Key takeaways

- Hex is a notebook-first platform where everything is a reusable cell, letting you mix SQL and Python in the same place and chain outputs together without separate ETL steps.
- It connects live to cloud warehouses like Snowflake and Databricks with no extract concept; data frame outputs are cached in memory so downstream filters and queries don't re-hit the database.
- Agents sit on every surface, including a notebook agent that plans and writes cells, a visualisation sub-agent for charts, conversational Threads for business users, and a review agent that audits other agents' work.
- Hex deliberately favours a layered context approach over semantic-models-only governance, combining semantic models, endorsements, guides and warehouse metadata so users can move from exploratory to fully governed questions.
- Apps differ from dashboards because Python lets you wire up actions, write back to Salesforce or a database, send emails or generate decks directly from the report.

## Chapters

- 0:01 Meet Rachel and her data journey
- 4:48 What Hex is and its philosophy
- 9:23 Data connections and metadata
- 12:13 Notebook workflow and cells
- 18:17 The notebook agent in action
- 24:38 App builder and inputs
- 30:44 Publishing, refresh and sharing
- 35:20 Threads for conversational analytics
- 37:42 Context studio and observability
- 41:49 Customer fit and ideal workflows
- 44:38 Semantic models, SQL quality and apps

Watch the full video, read the transcript and use chapter deep-links on the page: https://just-tim.com/posts/meet-hex-an-ai-powered-analytics-platform-with-notebooks-apps-and-more-featuring-rachel-herrera

---
just-tim — Data and analytics, with a point of view. · https://www.youtube.com/channel/UC7HYxRWmaNlJux-X7rNLZyw · https://twitter.com/TableauTim · https://www.linkedin.com/in/timngwena