Sarah Fischbach

Chat interfaces and coding agents are quickly becoming the primary way people consume analytics inside organizations. The new world lowers the barrier to access and shortens the path from question to insight. But what does this mean for how data teams operate? Data leaders share how they’re adapting, how teams across the business are using AI to get answers, how data leaders build trust in AI over time, and what iterative feedback and tuning look like when AI becomes the front door to your data. AI may be the new interface, but dashboards, models and even Excel still matter. The challenge is connecting these foundations to AI without losing trust.

Analytics engineers built transformations to define metrics and share them in the data warehouse. But AI agents need more than definitions. They need context. At Checkr, the analytics engineering team treats context engineering as the next evolution of their practice. This session covers what it looks like to engineer context, organizational knowledge and governance into AI systems — including what semantic layers usually miss; how to accelerate with LLM-assisted tooling; how to build a feedback loop that makes AI smarter over time; and why this discipline is becoming the core of the analytics engineering role, not a side project.