The short version
Most Identity Resolution tools require you to move your data into someone else's platform before you can do anything useful with it. Chuck Data was built to work the other way around: it runs Identity Resolution where your data already lives.
Until now, that meant Databricks. Now it means Amazon Web Services (AWS), too.
Chuck Data is a free, open-source, CLI-based AI agent that orchestrates Amperity's Identity Resolution engine. It accepts natural language prompts, generates SQL, and resolves fragmented customer records into unified profiles. Identity Resolution runs directly inside your own environment at no cost. No platform contract. No data migration. No new line items in your cloud budget.
What's new
Chuck Data now supports three AWS services:
Amazon Redshift serves as the data warehouse layer. You can run Identity Resolution directly against your Redshift tables, whether you're on Serverless or provisioned clusters. Customer records stay where they are.
Amazon Elastic MapReduce (EMR) handles compute. Identity Resolution workloads can now run on EMR, which integrates with the Identity and Access Management (IAM) policies, networking, and governance your team has already built out.
Amazon Bedrock provides Large Language Model access for Chuck's natural language capabilities. During setup, you choose from 60+ foundation models across six providers: Amazon, Anthropic, Mistral, Cohere, Meta, and Writer. Pick the model that fits your cost, performance, and compliance requirements, including older, previous versions no longer accessible anywhere else but AWS Bedrock.
The result is a fully AWS-native path through Chuck Data. If your team runs on Redshift, EMR, and Bedrock, you can add Identity Resolution to your stack without introducing a single external dependency.
How setup works
Run the /setup command, and Chuck walks you through a guided configuration. You'll select your data provider (Databricks or AWS Redshift); enter your AWS profile, region, and account ID; pick your compute layer (Databricks or EMR); and choose an LLM.
An AWS practitioner who knows their account configuration can finish in a few minutes. Chuck Data’s GitHub repo has video tutorials, demos, and step-by-step install guides for anyone who wants a more detailed walkthrough.
Security and data privacy
Chuck runs locally on your machine, and Identity Resolution executes inside your own AWS account. Amperity never accesses your data, your credentials, or your security configuration.
Usage telemetry is opt-in. During setup, Chuck clearly discloses what it shares (prompts you type, tool context, errors you encounter) and what it never shares (your data, credentials, and account security details). The entire codebase is open source and available for review on GitHub.
For teams operating under strict compliance and governance frameworks, this architecture means there's nothing new to vet beyond your existing AWS security posture.
Who this is for
Data engineers and platform teams on AWS who need to unify customer identities across fragmented sources but don't want to adopt a new platform to do it. If you've ever looked at Identity Resolution vendors and thought "I'm not signing a contract to deduplicate my customer table," Chuck Data is worth 15 minutes of your time.
It's also a starting point for teams evaluating Customer Data Platform (CDP) capabilities who aren't ready for a full platform purchase. You get production-grade Identity Resolution, running on infrastructure you already pay for, at no additional cost. From install to your first unified customer table in under 30 minutes.