Client Name : Dexlyn

Dexlyn partnered with DevOps TechLab to enhance business intelligence and data analysis with an AI-powered agentic investigation solution running on AWS.

The Challenge

Dexlyn needed a more efficient way to investigate business performance and understand the factors driving changes in revenue and other key business metrics.

Traditional business analysis often required users to identify the appropriate data, create SQL queries, run multiple analyses, and manually combine the results before reaching a conclusion.

This created dependency on technical resources and made complex business investigations slower than desired.

Key challenges included:

• Manual investigation of business performance data
• Dependency on technical teams for SQL-based analysis
• Multiple queries required to investigate business questions
• Difficulty connecting findings across different data points
• Limited ability to perform follow-up analysis conversationally
• Time required to move from a business question to actionable insight

Discovery

DevOps TechLab worked with Dexlyn to understand its business intelligence requirements and identify scenarios where an AI agent could perform multi-step data investigations.

The discovery process focused on understanding the business questions users wanted to answer, the available data sources, and how the investigation process could be automated while maintaining controlled access to production data.

The discovery included:

• Understanding business intelligence and reporting requirements
• Identifying relevant business data and database structures
• Understanding relationships between different data points
• Identifying multi-step investigation scenarios
• Defining secure, read-only database access
• Designing the agent’s investigation and recovery workflow
• Identifying opportunities to reduce manual data-analysis effort

Based on these requirements, DevOps TechLab designed the QueryDash Agentic Investigation Platform using Amazon Bedrock and Amazon Nova Pro.

Onboarding

DevOps TechLab onboarded Dexlyn onto the QueryDash Agentic Investigation Platform, enabling users to investigate business questions using natural language.

A typical investigation can begin with a goal such as:

“Determine the main factors affecting quarterly revenue.”

Instead of generating a single query and stopping, the AI agent determines what information is required, discovers relevant data, executes multiple validated queries, evaluates the results, and decides what should be investigated next.

The onboarding included:

• Database connectivity configuration
• Amazon Bedrock and Amazon Nova Pro configuration
• Secure database credential management
• Read-only SQL validation
• Conversational investigation context
• Multi-step agentic investigation workflow
• AWS application deployment
• Validation of representative business intelligence scenarios

Operations & Support

DevOps TechLab provides ongoing operational support for the Dexlyn solution and its AWS environment.

The support model focuses on maintaining application reliability, secure data access, and consistent AI-agent operation.

Operations and support activities include:

• Application and AWS infrastructure monitoring
• AI agent execution monitoring
• Database connectivity support
• Investigation workflow troubleshooting
• Query execution and validation support
• Production issue resolution
• Application logging and monitoring
• Secure credential and access management
• AWS infrastructure maintenance

The solution maintains controlled access to production databases. SQL generated by the agent is validated before execution, with write and schema-changing operations rejected.

Optimisation & Advisory

DevOps TechLab works with Dexlyn to continuously improve the efficiency and reliability of the agentic investigation platform.

Optimisation and advisory activities include:

• Improving agent investigation workflows
• Optimising multi-step reasoning and planning
• Improving SQL generation and validation
• Enhancing error recovery and replanning
• Reviewing AWS infrastructure performance
• Monitoring application and agent performance
• Reviewing security and access controls
• Advising on additional business intelligence use cases
• Identifying opportunities to automate additional data-analysis workflows

The reusable architecture allows Dexlyn to extend the agent to additional business questions and investigation scenarios without creating separate solutions for each requirement.

Summary

DevOps TechLab helped Dexlyn move from traditional, manually driven business intelligence analysis toward an AI-powered agentic investigation model.

Users can describe a business objective in natural language, and the AI agent autonomously determines the information required, performs multiple data-analysis steps, evaluates the evidence, and continues the investigation when additional analysis is needed.

The solution combines Amazon Bedrock, Amazon Nova Pro, AWS compute, managed databases, conversational context, and controlled data access to provide a flexible approach to business intelligence investigation.

Key Benefits

• Autonomous business intelligence investigation
• Goal-based data analysis
• Natural-language interaction
• Multi-step investigation and reasoning
• Dynamic data discovery
• Evidence-based business insights
• Automatic error recovery and replanning
• Conversational follow-up analysis
• Controlled read-only production access
• Reduced dependency on manual SQL analysis

Note: Any specific time savings, percentage improvements, or other quantitative business outcomes should be added only after they are validated with Dexlyn.

About DevOps TechLab

DevOps TechLab is a cloud and DevOps technology company focused on helping businesses design, deploy, secure, and operate modern applications on cloud platforms.

Our expertise spans cloud infrastructure, DevOps automation, application modernisation, cloud security, managed services, Generative AI, and Agentic AI solutions.

By combining cloud engineering with AI capabilities, DevOps TechLab helps organisations automate manual processes, improve operational efficiency, and build production-ready intelligent applications on AWS.