August 8, 2025
5 min read
Amazon Web Services
Discover how DTDC and ShellKode enhanced DIVA 2.0 using Amazon Bedrock to deliver a smarter, AI-driven logistics assistant with 93% accuracy.
DTDC is India’s leading integrated express logistics provider, operating the largest network of customer access points in the country. DTDC’s technology-driven logistics solutions cater to a wide range of customers across diverse industry verticals, making them a trusted partner in delivering excellence.
DTDC Express Limited receives over 400,000 customer queries each month, ranging from tracking requests to serviceability checks and shipping rates. Their existing logistics agent, DIVA, was based on a rigid, guided workflow that forced users to follow a structured path rather than engaging in natural, dynamic conversations. This lack of flexibility increased the burden on customer support teams, led to longer resolution times, and resulted in poor customer experience.
DTDC sought a more flexible, intelligent assistant capable of understanding context, managing complex queries, and improving efficiency while reducing reliance on human agents. To achieve this, DTDC enhanced DIVA with generative AI using Amazon Bedrock.
ShellKode is an AWS Partner specializing in modernization, security, data, generative AI, and machine learning. ShellKode collaborated with DTDC to build DIVA 2.0, a generative AI-powered logistics agent.
Solution Overview
ShellKode developed an advanced agentic assistant using Amazon Bedrock Agents, Amazon Bedrock Knowledge Bases, and an API integration layer. DIVA 2.0 offers a seamless conversational interface that understands and responds naturally to user queries such as package tracking, shipping rates, and service availability. Users can ask questions in their own words without following a rigid script. The AI’s enhanced capabilities allow it to understand context, manage complex requests, and provide accurate, personalized responses, improving customer experience and reducing human intervention. The solution architecture uses a modular, scalable design integrating AWS services like AWS App Runner, Amazon Bedrock Agents, AWS Lambda, and a vector-based knowledge base. The logistics agent is hosted as a static website using Amazon CloudFront and Amazon S3, integrated into the DTDC website for user-friendly access. User queries are processed by App Runner, which runs the web application and backend API services. It triggers Amazon Bedrock Agents API based on user requests. Amazon Bedrock is a fully managed service offering industry-leading foundation models (FMs) to build generative AI applications with security, privacy, and responsible AI features. Content is not used to improve base models or shared with model providers. Amazon Bedrock Guardrails provide configurable safeguards for safe AI application development. The Bedrock agent interprets user intent using natural language understanding and triggers appropriate Lambda functions for:- Tracking consignments
- Pricing information
- Location serviceability checks
- Support ticket creation These Lambda functions call client APIs to retrieve relevant data:
- Tracking System API: Provides real-time shipment status
- Delivery Franchise Location API: Checks service availability
- Pricing System API: Calculates shipping rates
- Customer Care API: Creates support tickets The agent passes the data to the large language model Anthropic’s Claude 3.0 on Amazon Bedrock, which generates meaningful, context-aware responses. The knowledge base includes web-scraped content from the DTDC website, internal documentation, FAQs, and operational data stored as vector embeddings in Amazon OpenSearch Service. Semantic similarity search retrieves relevant information to enhance response accuracy. If no relevant data is found, a fallback response is provided. Queries and responses are stored in Amazon RDS for PostgreSQL for scalability and relational data handling. App Runner updates the database through the Dashboard API. Monitoring and security are ensured with Amazon CloudWatch Logs, AWS CloudTrail, and Amazon GuardDuty.
- Enhanced conversations and real-time data access: Improved natural language understanding and multi-step reasoning enable accurate, contextually relevant responses.
- Intelligent data processing and accurate FAQ responses: LLMs provide structured answers for complex queries; Knowledge Bases handle FAQs without human support.
- Reduced live agent dependency and continuous improvement: Queries handled by support teams reduced by 51.4%, with analytics enabling ongoing refinement.
- Supports natural language queries with 93% response accuracy
- 71% of inquiries relate to consignments; 29.5% are general
- 51.4% of consignment inquiries did not require support ticket creation
- 60% of ticketed inquiries started with the AI assistant before involving support DTDC’s support team now focuses on critical issues, improving overall efficiency.
- AI Agents: Revolutionizing Business Automation and Customer Engagement
- The Future of Crypto Trading: AI Bots and Market Intelligence
- Understanding Blockchain: A Comprehensive Guide for Beginners
Logistics Agent Dashboard
The dashboard, hosted as a static website via CloudFront and S3, is accessible only to DTDC admins. It uses Amazon API Gateway with Lambda backend to fetch data from Amazon RDS. The dashboard provides real-time insights into agent performance, including accuracy, unresolved queries, query categories, session statistics, and user interactions. Features include heat maps, pie charts, and session logs to enable continuous improvement.Challenges and Benefits
Challenges included integrating real-time data from legacy systems, training AI on complex logistics terminology, transitioning from the old system while maintaining service continuity, and scaling to handle over 400,000 monthly queries. AWS solutions helped overcome these by leveraging Bedrock Agents’ API integration, fine-tuning LLMs with industry data, phased transition strategies, and scalable cloud infrastructure. Benefits realized by DTDC include:Results
DIVA 2.0 has significantly improved customer experience by reducing support burden and resolution times:Summary
This post demonstrates how Amazon Bedrock transforms a traditional chatbot into a generative AI-powered logistics agent that delivers dynamic, context-aware conversations and improved customer experience. This solution serves as a blueprint for businesses seeking to modernize AI assistants while maintaining compliance and scalability. For more information, contact AWS.About the Authors
Rishi Sareen – CIO, DTDC. Experienced technology leader driving AI-driven digital transformation in logistics. Arunraja Karthick – Head of IT Services & Security (CISO), DTDC. Expert in cloud-native, secure IT ecosystems. Bakrudeen K – AI/ML Practice Head, ShellKode. AWS Ambassador focused on generative AI innovation. Suresh Kanniappan – Solutions Architect, AWS. Specialist in cloud security and industry solutions. Sid Chandilya – Sr. Customer Relations Manager, AWS. Passionate about AI-driven business transformation.Source: Originally published at Amazon Web Services Blog on 07 Aug 2025.