Amperity Launches First AI Agent for Data Engineers

Amperity, a customer data cloud startup, has entered the realm of AI-driven agents with the launch of Chuck Data, an AI agent focused on customer data engineering.

Announced today, Chuck Data has been trained on vast amounts of customer data from over 400 enterprise brands. This foundational "core knowledge" empowers it to independently perform tasks like identity resolution and personally identifiable information tagging, resolving customer identity issues in real-time without requiring significant input from human developers.

This agent is designed to help businesses extract customer insights more quickly. Amperity, known for its cloud-hosted data management platform, focuses on organizing customer records so that companies can better understand them and use them to guide business decisions.

Amperity extracts information from customer databases, point-of-sale systems, and other sources, integrating it into a more cohesive whole. Its proprietary algorithms then reconcile this data. For instance, if two customer entries with matching personal information exist across different systems, they will be merged to create a more comprehensive profile for that individual.

Chuck Data aims to facilitate this process. The company explains that preparing customer data still involves a significant amount of manual coding. These codes rely on fragile rule systems, making them labor-intensive and prone to errors, which could easily disrupt detailed customer profiles. Chuck Data enables data engineers to adopt "ambient coding," allowing them to delegate these manual coding tasks to an autonomous AI assistant using natural language prompts.

The company states that Chuck Data connects directly to customers' Databricks environments via native compute and large language model endpoints. It can swiftly execute complex tasks such as identity resolution—merging multiple profiles into one—as well as compliance tagging and data analysis.

Chuck Data operates on a "zero-copy architecture," meaning it never moves customer data from its original location, ensuring compliance through PII tagging within Databricks. It runs inside developers' terminals, leveraging the Databricks environment for computation, storage, and LLM execution.

One of Chuck Data's core features is Amperity's patented identity resolution algorithm, built on its proprietary Stitch technology used in its flagship cloud data platform. The company says users can run Stitch on up to 1 million customer records for free. For larger datasets, users can sign up for Chuck Data's research preview program to receive free credits. Paid plans are also available, unlocking unlimited access to Stitch, enabling companies to create millions of accurate, scalable customer profiles.

According to Derek Slager, Amperity’s founder and CTO, the company developed Chuck to eliminate repetitive and painful tasks associated with customer data engineering.

"Chuck understands your data and helps you get things done faster, whether it's consolidating identities or tagging PII," Slager said. "No orchestration, no UI gymnastics—it’s just fast, context-driven, and command-driven."