Dan Pechi

Samsara faced a critical bottleneck: sales reps spent 60 minutes researching each prospect, yet meeting booking rates stagnated at 0.18%. To solve this, we built 'Smart Flows' on Databricks—a multi-agent system orchestrating Agent Bricks AI agents, AI/BI Genie and a custom MCP server for deep web research. This architecture moves beyond simple automation to agentic reasoning. A supervisor agent routes tasks: the MCP server gathers account intelligence, while Genie agents query CRM data to hyper-personalize outreach. The state is managed via Lakebase (Serverless Postgres) and reusable Unity Catalog functions. The results were transformative. Prospecting time dropped to under five minutes—12x productivity—and agentic personalization drove meeting booking rates to 6.49%—a massive 36x uplift. We will demonstrate this live, generating a fully researched outreach sequence in real-time to show how agents can drive hard revenue metrics.

Vibe coding is fun until it hits production. In this session, we benchmark two agents running the identical LLM on identical enterprise workloads — one armed with raw SQL and good intentions, one grounded in the Databricks Data Intelligence stack: a Unity Catalog semantic layer, governed metric views, UC functions with LLM-readable docstrings, and Vector Search over enriched business context. We run the benchmark live, on real questions including the ambiguous, multilingual ones your users actually ask. Then we step back and look at what the trajectories tell us about where production agent cost actually comes from — and why the platform underneath your agents matters more than the model running on top of it.

The rise of GenAI has led to a complete reinvention of how we conceptualize Data + AI. In this breakout, we will recontextualize the rise of GenAI in traditional ML paradigms, and hopefully unite the pre- and post-LLM eras. We will demonstrate when and where GenAI may prove more effective than traditional ML algorithms, and highlight problems for which the wheel is unnecessarily being reinvented with GenAI. This session will also highlight how MLflow provides a unified means of benchmarking traditional ML against GenAI, and lay out a vision for bridging the divide between Traditional ML and GenAI practitioners.