Demo Dive Series
Most data teams still bounce between lineage graphs, quality dashboards, and catalog tools just to answer one question: what breaks if I change this field? In this session, you’ll watch a single MCP prompt do the work of all three — and learn how to turn that from a one-off experiment into a workflow your team runs every day.
Coalesce MCPs give AI clients like Claude direct access to your transformations, governance metadata, and quality monitors. Impact analysis, root-cause debugging, and owner assignment happen in a single conversation rather than across five browser tabs. In this recored session, Mikkel Dengsøe (Director of Data & AI Strategy, Coalesce) walks through real examples on live data, so you can see exactly what the prompts look like, where the guardrails sit, and what to watch for in production.
You’ll learn how to:
- Run impact analysis before you touch a field — pull Catalog metadata and check Quality status in a single prompt for a complete downstream picture before you commit.
- Debug anomalies with live root-cause analysis — follow a real investigation as the MCP traces an anomaly upstream, reviews recent commits, and pinpoints the exact change that broke the pipeline.
- Ship MCP workflows your whole team can use — set read vs. write token scopes, chain Coalesce MCPs with Slack and GitHub, and add per-call approval gates so the team moves fast without bypassing governance.
Instructors
