CrewHu is a corporate engagement platform that leverages people analytics and gamification to enhance team productivity and satisfaction. With integrations to tools like Slack and Microsoft Teams, CrewHu provides real-time data for HR teams and leaders, helping reduce turnover and strengthen organisational culture. The platform’s differentiator lies in the combination of automated surveys, peer-to-peer recognition, and actionable metrics, making it essential for companies that prioritise connected and efficient work environments.
CrewHu needed to convert CSAT metrics into actionable qualitative insights and enable fast identification of critical operational challenges, customer retention risks, and high-impact improvement opportunities that would likely be missed in manual or superficial analyses. The manual process of reading and categorising large volumes of customer feedback was taking days to complete, creating a significant bottleneck. Managers needed clear, data-driven recommendations but were spending excessive time in planning meetings that could be reduced through better data analysis capabilities.
DNX Solutions, an AWS Premier Consulting Partner, designed and implemented a GenAI-powered insights assistant solution for CrewHu. The solution leverages Amazon Bedrock with Anthropic Claude Haiku to automatically analyse customer feedback data and generate actionable recommendations.
The architecture features an AWS Lambda-based AI application that processes feedback data stored in Amazon S3 and Amazon RDS, using Amazon SQS for reliable message queuing. The system connects to CrewHu’s internal services via API Gateway and PrivateLink, ensuring secure integration. Langfuse provides observability for monitoring AI interactions and performance.
DNX implemented the solution using LangChain for chat flow orchestration, with results automatically structured in JSON format for seamless integration with CrewHu’s dashboards and management tools. The infrastructure was built using Pulumi (Infrastructure as Code) with automatic scalability, deployed across development and production environments using CodePipeline for CI/CD.
The implementation delivered a GenAI assistant that transforms how CrewHu analyses customer feedback. The solution converts CSAT metrics into actionable qualitative insights, enabling fast identification of critical operational challenges, customer retention risks, and high-impact improvement opportunities that would likely be missed in manual analyses.
Using AI-powered analysis, the system uncovers hidden strengths within low-volume but high-satisfaction tags, revealing competitive differentiators while eliminating the need for teams to manually read and categorise large volumes of customer feedback. Managers now receive clear, data-driven recommendations—such as the creation of targeted Badges or Contests—reducing time spent in planning meetings and accelerating decision-making.
Results are automatically organised according to the Customer Bill of Rights framework, highlighting areas where customer expectations are being met or are at risk. The solution proactively surfaces critical issues such as response time and resolution failures, enabling preventive action and allowing leaders to focus on initiatives that directly influence customer satisfaction and team performance.
DNX is a systems integrator and trusted advisor for business transformation, focused on democratising modernisation. For us, modernisation is not just about upgrading technology. It is about enabling organisations to adopt modern platforms, architectures and ways of working that drive measurable business outcomes. This includes cloud-native technologies, security and compliance by design, data-driven decision-making, and governance models that support scale, agility and innovation. By democratising modernisation, DNX ensures these capabilities are accessible, practical and aligned to each organisation’s maturity—empowering teams across the business, not just IT, to modernise with confidence and purpose.
GenAI insights assistant leveraging Amazon Bedrock, AWS Lambda, and LangChain for automated customer feedback analysis
| Service | Purpose |
|---|---|
| Amazon Bedrock | Foundation model hosting (Claude Haiku) |
| AWS Lambda | Serverless AI application compute |
| Amazon S3 | Data storage for feedback and logs |
| Amazon RDS | Reports database |
| Amazon SQS | Message queuing for reliable processing |
| API Gateway | API management and integration |
| Amazon EKS | Container orchestration |
| AWS CodePipeline | CI/CD automation |
| Amazon CloudWatch | Logging and monitoring |
| AWS Secrets Manager | Secure credential management |
