# Meet ThoughtSpot Analytics Platform with CEO Ketan Karkhanis & SVP Francois Lopitaux

> 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:** 2026-05-05
- **Format:** Video · 64 min watch · transcript available
- **Topics:** Analytics, AI & ML, Data visualisation
- **Tools:** Databricks; Python; Snowflake; ThoughtSpot (analyze studio, embedding, liveboards, mcp, muse, search tokens, semantic model, spotter)
- **Canonical:** https://just-tim.com/posts/meet-thoughtspot-analytics-platform-with-ceo-ketan-karkhanis--svp-francois-lopitaux
- **Watch:** https://www.youtube.com/watch?v=kfRKVddwzxc

I sit down with ThoughtSpot CEO Ketan Karkhanis and SVP of Products Francois Lopitaux to rediscover the platform as part of my exploration of new analytics tools. We cover their backgrounds and vision for the AI enterprise, then Francois gives a live demo of data loading, agentic semantic modelling, Spotter-generated dashboards, conversational analysis, external tool actions, machine learning and embedding.

## Key takeaways

- ThoughtSpot now positions itself as an enterprise data and AI company built around agentic analytics, with Spotter agents for modelling, visualisation and conversational analysis rather than just traditional BI dashboards.
- You can bring data in two ways: caching via Analyze Studio (the Mode acquisition tech, including merging Google Sheets and Snowflake via SQL) or direct query against Snowflake, Databricks Unity Catalog, dbt and more.
- Spotter Model can auto-build a semantic model from a live warehouse connection, selecting fact and supporting tables, suggesting joins with cardinality and direction, and layering in AI context, instructions and memory.
- Search tokens are an abstraction layer that the LLM generates instead of raw SQL, so the same token always produces the same deterministic query, while features like why-analysis use ThoughtSpot's own algorithms rather than the LLM.
- Agentic workflows can reach beyond the warehouse via MCP servers, pulling tasks from Asana, running Python clustering, posting to Slack and embedding into apps through Spotter Code in any IDE.

## Chapters

- 0:00 Welcome and why this conversation
- 0:49 Meet Ketan and Francois
- 2:23 Paths into data and AI
- 8:06 What ThoughtSpot is today
- 18:28 Loading data with Analyze Studio
- 21:37 Agentic semantic modelling
- 28:54 Liveboards and search tokens
- 30:35 Generating dashboards with Spotter
- 35:25 Conversational follow-up analysis
- 40:28 Search tokens and why-analysis
- 43:41 Acting across tools with Asana and Slack
- 45:16 Machine learning clustering with Python

Watch the full video, read the transcript and use chapter deep-links on the page: https://just-tim.com/posts/meet-thoughtspot-analytics-platform-with-ceo-ketan-karkhanis--svp-francois-lopitaux

---
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