Client Name : TNBT Tech

TNBT Tech partnered with DevOps TechLab to modernize operational data analysis using Generative AI and Agentic AI capabilities on AWS.

The Challenge

TNBT Tech needed a faster and more efficient way to investigate operational data and identify unusual changes or patterns.

Traditional analysis required technical teams to manually identify relevant data, prepare SQL queries, execute multiple queries, and interpret the results. This made complex investigations time-consuming and increased dependency on technical resources.

The key requirement was to enable users to ask operational questions in natural language and receive data-backed insights without having to write SQL.

Key challenges included:

• Manual investigation of operational data
• Dependency on technical teams for SQL analysis
• Multiple queries required to investigate a single issue
• Difficulty identifying relationships between operational data points
• Limited ability to perform conversational follow-up analysis

Discovery

DevOps TechLab worked with TNBT Tech to understand its operational investigation requirements, available data sources, and the types of questions users needed to answer.

The discovery process focused on identifying scenarios where an AI agent could autonomously explore data, evaluate results, and determine the next appropriate investigation step.

The discovery included:

• Understanding operational investigation requirements
• Identifying relevant databases and data structures
• Understanding relationships between operational data
• Identifying multi-step investigation scenarios
• Defining secure, read-only access to production data
• Defining the AI agent workflow and autonomy boundaries

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

Onboarding

DevOps TechLab onboarded TNBT Tech onto the QueryDash Agentic Investigation Platform.

The platform enables users to describe an operational objective in natural language while the AI agent performs the required multi-step investigation.

For example:

“Identify unusual operational changes and determine their likely causes.”

The agent interprets the objective, discovers the required data, generates and executes validated queries, analyzes the results, and determines whether additional investigation is required.

The onboarding included:

• Database connectivity configuration
• Amazon Bedrock and Amazon Nova Pro configuration
• Secure database credential configuration
• Read-only SQL validation
• Conversational investigation context
• AWS application deployment
• Validation of representative operational investigation scenarios

Operations & Support

DevOps TechLab provides ongoing operational support for the application and its AWS environment to maintain reliable, secure operation.

Operations and support activities include:

• Application and infrastructure monitoring
• AI agent execution monitoring
• Database connectivity and query support
• Investigation workflow troubleshooting
• Production issue resolution
• Application log and system monitoring
• Secure database access management
• AWS infrastructure support and maintenance

Production database access is controlled through application-level validation. SQL statements are validated before execution, while write and schema-changing operations are rejected.

Optimisation & Advisory

DevOps TechLab continuously evaluates the solution to improve agentic investigation quality, AWS infrastructure efficiency, security, and operational reliability.

Optimisation and advisory activities include:

• Optimisation of AI agent investigation workflows
• Improvement of query generation and validation
• Optimisation of multi-step reasoning and recovery
• AWS infrastructure performance and utilisation reviews
• Security and access-control reviews
• Application performance monitoring and optimisation
• Advisory for new operational investigation scenarios
• Identifying opportunities to extend AI-assisted analytics

The architecture is designed to support additional business and operational use cases without requiring a separate analytics platform for each scenario.

Summary

DevOps TechLab helped TNBT Tech introduce an AI-powered agentic investigation capability for operational data analysis.

Instead of relying only on predefined queries or dashboards, users can provide an investigation goal in natural language. The AI agent autonomously plans and performs multiple investigation steps, analyzes available evidence, recovers from failed queries, and presents actionable findings.

The solution combines Amazon Bedrock, Amazon Nova Pro, AWS compute, managed databases, secure access controls, and conversational AI to provide a scalable and controlled approach to operational intelligence.

Key Benefits

• Goal-based operational investigation
• Autonomous multi-step data analysis
• Natural-language interaction
• Dynamic data discovery
• Evidence-based findings
• Automatic recovery and replanning
• Controlled read-only production access
• Reduced dependency on manual SQL analysis

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 transform manual processes, improve operational efficiency, and build production-ready intelligent applications on AWS.