Introducing the Agentic CDP: A New Species of CDP for a New Era of Agents

Summary

Traditional customer data platforms (CDPs) were built for human-managed, batch-based campaigns, but the post argues that agentic buying requires millisecond speed, hyper-personalization, and richer context. It contrasts the familiar Golden Record with Golden Context, which combines customer data with current business goals and the history and outcomes of prior decisions. The proposed Agentic CDP uses “Infinity Campaigns,” always-on engagement loops that use LLMs and agents to adapt messaging, timing, and channels for individuals. It is also embedded in the data foundation, bringing customer, business, and decision context together under existing governance, and is designed for agents and humans from the outset. Databricks presents CustomerLake as an implementation of these principles for its platform.

Context

The post describes a mismatch between traditional CDPs and agentic buying. Autonomous agents operate in milliseconds, filter out irrelevant content, and require live customer, business, and decision context rather than only a unified customer profile.

Approach / What changed

It proposes an Agentic CDP centered on Infinity Campaigns, embedded in the data foundation, and designed from the beginning for agents and humans to operate together. CustomerLake is presented as Databricks’ implementation of these principles on its platform.

Takeaways

• Golden Context extends the Golden Record with current business objectives and the history of decisions made for a customer, including the customer’s responses.
• Infinity Campaigns are always-on engagement loops that use LLMs and agents to continuously adapt message, timing, and channel based on new context signals.
• Embedding the CDP in the data foundation allows customer, business, and decision context to share governance, security boundaries, identity resolution, and data-quality processes.

Related reading