How Samsara Built a Multi-Agent System to Drive a 36x Lift in Meeting Bookings on Databricks

Summary

• Samsara built Smart Flows on Databricks, a multi-agent system that reduced sales prospecting time from 60 minutes to under 5 minutes per prospect by orchestrating Agent Bricks AI agents, AI/BI Genie, and a custom MCP server.
• The architecture routes tasks through a supervisor agent — the MCP server gathers account intelligence from the web while Genie agents query CRM data — with state managed in Lakebase and reusable Unity Catalog functions.
• Smart Flows increased meeting booking rates from 0.18% to 6.49%, a 36x uplift, representing transformative revenue impact alongside a 12x productivity gain for sales reps.

How Samsara Built a Multi-Agent System to Drive a 36x Lift in Meeting Bookings on Databricks

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.
Talk By: Dan Pechi, AI Product Specialist, Databricks ; Vipul Panwar, Senior AI Engineer, Samsara ;

FAQs

What is Samsara's Smart Flows and what problem does it solve?

Smart Flows is a multi-agent system built on Databricks that automates sales prospecting research. It was created to address the bottleneck where sales reps were spending 60 minutes per prospect while meeting booking rates stagnated at 0.18%.

How does the multi-agent architecture in Smart Flows work?

A supervisor agent routes tasks between specialized agents: a custom MCP server gathers account intelligence through deep web research, while Genie agents query CRM data to hyper-personalize outreach. State is managed via Lakebase and shared through reusable Unity Catalog functions.

What results did Samsara achieve with Smart Flows on Databricks?

Prospecting time dropped from 60 minutes to under 5 minutes per prospect, a 12x productivity gain. Agentic personalization drove meeting booking rates from 0.18% to 6.49%, a 36x uplift in a key revenue metric.

What technologies did Samsara use to build the Smart Flows system?

Samsara built Smart Flows using Agent Bricks AI agents, AI/BI Genie for CRM data exploration, and a custom MCP server for web research. Lakebase (Serverless Postgres) manages state and Unity Catalog functions handle reusable business logic.

Learn more about the Databricks Data and AI platform.