Australia – Amperity has announced the launch of ‘Chuck Data,’ the first AI Agent built specifically for customer data engineering. ‘Chuck Data’ uses Amperity’s years of experience and patented identity resolution models, trained on billions of data sets across over 400 enterprise brands, as critical knowledge behind the AI.
Moreover, ‘Chuck Data’ runs in the terminal and empowers engineers to quickly understand their data, tag it, and resolve customer identities in minutes – all from within their Databricks lakehouse.
As pressure mounts to deliver business-ready insights quickly, data engineers are hitting a wall: while infrastructure has modernised, the work of preparing customer data still relies on manual code and brittle rules-based systems. ‘Chuck Data’ changes that by enabling data engineers to “vibe code” – using natural language prompts to delegate complex engineering tasks to an AI assistant.
‘Chuck Data’ connects directly to a user’s Databricks environment, leveraging native compute and large language model (LLM) endpoints to execute high-impact workflows like identity resolution, compliance tagging, and data profiling.
Chuck Data offers a range of powerful features designed to streamline customer data management. It includes a natural language command interface, allowing users to perform data tasks more intuitively. Identity resolution is handled through Amperity Stitch, operating on Databricks compute, while PII tagging and customer profiling are integrated across Unity Catalog.
The platform also ensures compliance through accurate and user-friendly PII tagging within Databricks. Additionally, Chuck’s zero-copy architecture means it never moves your data, enhancing both security and efficiency.
Derek Slager, co-founder and CTO at Amperity, said, “Customer data engineering is full of repetitive, painful work, so we built Chuck to get rid of it. Chuck understands your data and helps you get stuff done faster, whether you’re stitching identities or tagging PII. No orchestration, no UI gymnastics—it’s just fast, contextual, and command-driven.”
Chuck runs entirely in a user’s terminal, using their Databricks environment for compute, storage, and LLM execution. With a single install, engineers can run natural language commands that eliminate manual code and deliver accurate, scalable customer profiles.
A core capability of Chuck is running Amperity’s patented identity resolution algorithm – the same trusted Stitch technology used in its enterprise CDP. Users can run unlimited free Stitch on datasets up to 1 million records with a generous budget of credits for larger data sets included for free with the research preview program.
Paid plans unlock unlimited runs, access to Amperity’s stable ID algorithm, and enterprise support.
