Amperity brings vibe coding to data engineers with its first AI agent – News

Customer data cloud startup Amperity Inc. is joining the agentic artificial intelligence party, launching Chuck Data, an AI agent that specializes in customer data engineering.

Announced today, Chuck Data is trained on massive volumes of customer data from more than 400 enterprise brands. This “critical knowledge” base allows it to execute tasks such as identity resolution and personally identifiable information tagging autonomously and instantly resolve customer identities, with minimal input from human developers.

The agent is designed to help companies dig up customer insights much faster. Amperity is the creator of a cloud-hosted data management platform that’s focused on customer records. It helps organize these records so companies can make better sense of them and use it to inform business decisions.

Amperity works by pulling information from customer databases, point-of-sale systems in stores and other sources and stitching it into a more cohesive whole. Its proprietary algorithms then attempt to reconcile this data. So, if there are two customer entries in different systems that have identical personal details, it will combine those records to create a more comprehensive profile of that person.

Chuck Data is designed to aid in this process. The company explains that there’s still a lot of manual coding involved in preparing customer data. This code is based on brittle, rules-based systems and so it takes a lot of effort, and the detailed customer profiles can easily be corrupted if any mistakes are made. Chuck Data makes it possible for data engineers to embrace “vibe coding,” so they can use natural language prompts to delegate these manual coding tasks to an autonomous AI assistant.

The company said Chuck Data connects directly to the customer’s Databricks environment via native compute and large language model endpoints. Then it can quickly execute complex tasks such as identity resolution – which involves pulling data from multiple profiles into one – as well as compliance tagging and data profiling.

Chuck Data is based on a “zero-copy architecture,” which means it never moves customer data from its original location, ensuring compliance through PII tagging within Databricks. It runs inside the developer’s terminal, leveraging the Databricks environment for compute, storage and LLM execution.

One of Chuck Data’s core features is Amperity’s patented identity resolution algorithm, which is based on the proprietary Stitch technology that’s used within its flagship cloud data platform. The company said users can run Stitch on up to 1 million customer records for free, and for those with bigger records, they can sign up to Chuck Data’s research preview program to access free credits. It’s also offering paid plans that unlock unlimited access to Stitch, enabling companies to create millions of accurate, scalable customer profiles.

Amperity founder and Chief Technology Officer Derek Slager said the company built Chuck to get rid of the repetitive and painful work that’s associated with customer data engineering.

“Chuck understands your data and helps you get stuff done faster, whether you’re stitching identities or tagging PII,” Slager said. “There’s no orchestration, no UI gymnastics – it’s just fast, contextual and command-driven.”

Image: News/Microsoft Designer