Before the agents: what self-serve analytics actually needs
KOHO's data leaders argue that self-serve analytics with AI only works once you've already built the data culture and the governed dbt foundation underneath it.
Overview
AI-powered self-serve analytics tools look similar on the surface but differ underneath. Presents KOHO's approach: sustainable self-serve depends on a business context layer built from real questions plus solid analytics engineering, comparing analyst-authored vs. AI-generated context.
What you'll take away
- 01
The hard part of self-serve analytics was never the AI: years of data-team culture work and foundational governance made KoDa, KOHO's Claude-powered tool, possible at all.
- 02
KoDa is deliberately scoped: analytics use cases only, certified dbt mart models only, no PII, read-only, and every answer traces back to the same company-wide dbt definitions.
- 03
The real engineering effort went into evaluation, not the model: an "eval council" built a library of about 375 real analyst questions to catch regressions before they reach users.
Session speakers
Célia Bru
Koho FinancialGabriel Gambacorta
KOHO Financial