Summary
Modeling Gong call transcripts directly in the warehouse with dbt, instead of hitting Gong's API on every AI call, cut token costs by 20x. The takeaway: for AI workloads, model the data at the token level, not just the table level.
Summary generated by brickster.ai. For the full article, follow the source link above.
More from dbt Labs Blog
Databricks processes your data. dbt defines what it means
Databricks handles compute while dbt governs the transformation logic that defines what the data actually means — yet organizations routinely bundle these as a single approval decision. The post argues executives should treat the platform choice and the transformation-logic choice as separate decisions, not one.
Why agentics projects fail and how to fix them
Why do some Databricks agentic AI deployments succeed while so many fail? The data points to specific, identifiable failure patterns—and this post breaks down what they are and how teams can fix them.
How dbt State cuts warehouse compute and speeds up every run
How Fanatics cut warehouse compute by only rebuilding what's changed
dbt Summit 2026: the keynotes and product sessions
The dbt Summit 2026 keynotes and the product sessions behind them.
From analytics engineer to context engineer
Analytics engineers are evolving into context engineers as the focus shifts from modeling data for dashboards to modeling context for AI agents. The first entry in a new series explores this transition by putting the approach into practice with