Talking to customers · Independent · 22 Oct 2026

aws-samples/sample-voice-of-customer-datalake

Serverless AWS platform for ingesting, processing, and analyzing customer feedback from multiple sources using AI-powered insights with Amazon Bedrock — built as part of the AI-assisted Product Development Lifecycle Initiative (AI PDLC).

← Talking to customers

In simple English

This tool collects customer feedback from app stores, web forms, and scraped sites. It stores all the feedback in one place on Amazon Web Services (AWS, a company that rents out computer servers). An artificial intelligence model reads the feedback and sorts it by mood and topic. You get a dashboard to view charts, chat with your data, and turn complaints into product plans. It costs money to run the cloud services it uses, and it takes time to set up.

What it is

A serverless application built with the AWS Cloud Development Kit (CDK, a framework for defining cloud infrastructure using code) that deploys a feedback data lake, processing pipeline, and React dashboard. It uses Amazon Bedrock (a managed service that runs large language models) to analyze customer sentiment and generate product requirement documents.

What it is good for

Product managers and solo builders who want to collect user feedback from many channels and let artificial intelligence summarize what users want. It removes the manual work of reading and categorizing hundreds of reviews.

Stars32
LicenceMIT-0
Latestv0.3.0 (2026-09-10)checked 22 Oct 2026
Last code change2026-10-21
Written inPython
Setup effort
4 / 5
Payoff
4 / 5
Good
  • Automatically categorizes feedback and detects sentiment using language models.
  • Includes a React dashboard with charts, AI chat, and project research workspaces.
  • Extensible plugin architecture lets you add custom data sources.
Watch for
  • Requires an active AWS account and familiarity with cloud infrastructure deployment.
  • Running cloud services and language models will incur ongoing costs on your AWS bill.
  • Complex setup involving Node.js, Python, and Docker.
Replaces

Manually reading app store reviews and customer support emails into a spreadsheet.

Works well with

AWS CDK

Also reviewed on Repo Radar
  • botpress/botpress15k stars

    The command-line tool, software kit and integrations for the Botpress cloud service, rather than a chatbot you host.

  • heyform/heyform9.0k stars

    A form and survey builder you can run yourself, with conversational one-question-at-a-time forms.

  • Notifuse/notifuse2.2k stars

    Self-hosted newsletters, automations and transactional email, built on a delivery service you supply.

Install
git clone https://github.com/aws-samples/sample-voice-of-customer-datalake.git
cd sample-voice-of-customer-datalake
npm run install:all
npm run build:layers
npm run cdk:bootstrap
npm run deploy:all

Independent: reviewed for Repo Radar outside the daily editions. Every independent repository

On Stack Radar: Data & Research › Market & Competitive Research › Review Mining.

Get the next edition in your inbox

A dozen repositories, opened and checked. The licence read, the last release dated, and the ones that did not make it named with the reason. It is the half most lists leave out.

No tracking pixels. One click to leave. The archive stays free either way.

We use your address to send the edition and nothing else. Confirm by email, leave in one click. How we handle it.