The new solution allows for faster identity resolution and the labeling of sensitive data, eliminating manual work and embracing ‘vibe coding’ through natural language prompts.
Amperity, a company specializing in cloud-based customer data platforms powered by artificial intelligence, has announced the launch of Chuck Data, the first AI agent specifically designed for customer data engineering within the Databricks ecosystem. The announcement took place during the Databricks Data + AI Summit held in San Francisco, where the company demonstrated the capabilities of this new intelligent assistant live.
AI Applied to Real Data Engineering Challenges
Despite advancements in datainfrastructure and platforms, much of the work involving customer data preparation and management continues to rely on manual tasks, repetitive code, and fragile rule-based systems. Chuck Data breaks onto the scene to revolutionize the daily routine of data engineers: it enables the execution of complex tasks, such as identity resolution or the labeling of personally identifiable information (PII), using simple commands in natural language directly from the Databricks terminal.
The agent utilizes Amperity’s proprietary algorithms, trained on billions of records and used by over 400 major brands globally, to provide precise identity resolution, sensitive data labeling, and advanced customer profiling. All of this leverages the native computing and storage power of Databricks without the need to move data or duplicate processes.
Key Features of Chuck Data
- Natural language command interface for data engineering tasks.
- Identity resolution using Amperity’s Stitch technology, directly within the Databricks environment.
- Automatic labeling of PII and customer profiling through the Unity catalog.
- Simplified regulatory compliance thanks to precise labeling of personal data.
- Zero-copy architecture: Chuck does not extract or move customer data.
According to Derek Slager, co-founder and CTO of Amperity: “Chuck understands your data and helps you move faster, whether it’s merging identities or tagging sensitive information. No orchestration or complexity in the interface. Just speed and context.”
A New Paradigm: ‘Vibe Coding’
Chuck Data promotes the concept of vibe coding, meaning delegating complex data engineering tasks to an AI through natural prompts, eliminating the need to manually code each process. This allows engineers to focus on extracting insights and ensuring data quality, accelerating the generation of business value.
Users can install Chuck on their terminal and start working immediately within their Databricks environment. The agent takes advantage of LLM endpoints and native computation, facilitating workflows such as large-scale identity resolution or compliance with data protection regulations.
Access Models and Usage Plans
Chuck Data is offered free for datasets of up to one million records, including credits for larger executions during the preview program. Paid plans provide unlimited access, Amperity’s stable ID algorithm, and enterprise support.
Demonstration and Use Cases
During the Databricks Data + AI Summit, attendees witnessed how Chuck Data resolves millions of identities in seconds, generates customer ID graphs, and simplifies data engineering workflows, reducing the traditional bottlenecks in customer data management.
Brands currently utilizing Amperity’s platform, such as Alaska Airlines, DICK’S Sporting Goods, and Wyndham Hotels & Resorts, highlight improvements in speed, accuracy, and data monetization capabilities.
Amperity, a Leader in Customer Data Cloud
Founded in 2016, Amperity has offices in Seattle, New York, London, and Melbourne, and has established itself as a leading solution in transforming customer data into strategic assets through personalized AI models, intelligent automation, and advanced identity resolutions.