Agentic coding in analytics engineering (w/ Mikkel Dengsøe)

About this episode

Tristan talks with Mikkel Dengsøe about agentic coding in analytics engineering and its practical applications.

Tristan talks with Mikkel Dengsøe, co-founder at SYNQ, to break down what agentic coding looks like in analytics engineering. Mikkel walks through a hands-on project using Cursor, the dbt MCP server, Omni's AI assistant, and Snowflake. They cover where agents shine (staging, unit tests, lineage-aware checks), where they're risky (BI chat for non-experts), and how observability is shifting from dashboards to root-cause explanations. For full show notes and to read 6+ years of back issues of the podcast's companion newsletter, head to https://roundup.getdbt.com . The Analytics Engineering Podcast is sponsored by dbt Labs.

People in this episode

Host: Tristan

Guest: Mikkel Dengsøe

Topics covered

• agentic coding
• analytics engineering
• AI in analytics
• observability
• data lineage
• unit testing

Keywords

• agentic coding
• analytics engineering
• Cursor
• Snowflake
• observability
• unit tests
• AI assistant

Sponsors

dbt Labs

Mentioned in this episode

Organizations: SYNQ, dbt MCP, Omni

Products: Cursor, Snowflake

More episodes of The Analytics Engineering Podcast

• The Iceberg ecosystem today (w/ Anders Swanson) · March 8, 2026 · 55 min
• Apache Iceberg and the catalog layer (w/ Russell Spitzer) · January 25, 2026 · 53 min
• AI and the data lake (w/ Lauren Anderson) · January 11, 2026 · 54 min
• Inside Snowflake's AI roadmap (w/ Chris Child) · December 14, 2025 · 57 min
• Building a multimodal lakehouse for AI (w/ Chang She) · November 23, 2025 · 57 min
• Under the hood of Apache Iceberg (w/ Christian Thiel) · August 24, 2025 · 56 min