If you’re a data engineer working in Databricks, chances are your days are packed with manual data wrangling, complex SQL, and reactive requests for things like identity resolution or privacy compliance. Despite all the advancements in compute and storage, shaping messy customer data into something business-ready still takes time—and a lot of code.
So we built Chuck Data to change that.
What is Chuck Data?
Chuck is the first AI agent built specifically for customer data engineering. It lives right in your terminal and runs natively on your Databricks lakehouse. Chuck helps you do the work that slows you down—like tagging PII, resolving customer identities, and profiling tables—using natural language prompts.
You tell Chuck what you want to do. Chuck figures out the best way to do it, writes the SQL, and gets it done.
And it’s fast. Really fast.
"Customer data engineering is full of repetitive, painful work, so we built Chuck to get rid of it," said Derek Slager, co-founder and CTO of Amperity. "Chuck understands your data and helps you get stuff done faster—no orchestration, no UI gymnastics, just fast, contextual, command-driven work."
Why now?
Because customer data engineering has become the bottleneck for business impact.
The business wants faster insights.
Marketing wants cleaner profiles.
Legal wants GDPR compliance.
And you’re writing regex and stitching IDs by hand?
No thanks.
AI is transforming how software gets built with the rise of “vibe coding”—where developers describe what they want in natural language and let AI do the heavy lifting. With Chuck, we’re bringing that to customer data engineering.
What can Chuck do?
Here’s a quick snapshot of what Chuck helps you handle today:
Identity resolution using Amperity’s patented Stitch algorithm (same as in our enterprise CDP)
PII tagging and profiling using Unity Catalog metadata
Natural language command execution right from your terminal
Zero-copy architecture — your data never leaves Databricks
LLM-powered assistance with your model of choice
And it’s just getting started. Chuck will continue evolving based on what real data teams tell us they need most.
Built by experts. Backed by Databricks.
Chuck isn’t just another plug-in or bolt-on tool. It was built with a deep understanding of customer data from the team behind Amperity’s identity resolution technology—used by over 400 brands across retail, travel, and financial services.
And it’s designed from the ground up to run natively in your Databricks environment, using your compute and your data structures. No new UIs to learn. No duplicative pipelines to manage. No context-switching required.
Free to use—with room to grow
Chuck is available now as a free research preview. You get:
Unlimited Stitch runs on datasets up to 1 million records
A generous credit budget for larger data volumes
The ability to pick your preferred LLM
CLI-native operation—just install and go
Need more scale or advanced capabilities? Paid plans unlock our stable ID algorithm, enterprise support, and unlimited Stitch at any scale.
See Chuck in action
We’ll be live at the Databricks Data + AI Summit, June 9–12 in San Francisco, demoing Chuck at Booth #704. Come by and see how Chuck:
Resolves millions of identities in seconds
Builds customer ID graphs with transparency
Speeds up data engineering without adding tools