The DIVA logistics agent, powered by Amazon Bedrock

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. With such a high volume of shipments, their existing logistics agent, DIVA, was operated on a rigid, guided workflow, forcing users to follow a structured path rather than engaging in natural, dynamic conversations. The lack of flexibility resulted in increased burden on customer support teams, longer resolution times, and poor customer experience.

DTDC was looking for a more flexible, intelligent assistant—one that could understand context, manage complex queries, and improve efficiency while reducing reliance on human agents. To achieve a better customer experience, DTDC decided to enhance DIVA with generative AI using Amazon Bedrock.

ShellKode is an AWS Partner, born-in-the-cloud company specializing in modernization, security, data, generative AI, and machine learning (ML). With a mission to drive transformative growth, ShellKode empowers businesses through state-of-the-art technology solutions that address complex challenges and unlock new opportunities. Using deep industry expertise, they deliver tailored strategies that foster innovation, efficiency, and long-term success in an evolving digital landscape.

In this post, we discuss how DTDC and ShellKode used Amazon Bedrock to build DIVA 2.0, a generative AI-powered logistics agent.

Solution overview

To address the limitations of the existing logistics agent, ShellKode built an advanced agentic assistant using Amazon Bedrock Agents, Amazon Bedrock Knowledge Bases, and an API integration layer.

When customers interact with DIVA 2.0, they experience a seamless, conversational interface that understands and responds to their queries naturally. Whether tracking a package, checking shipping rates, or inquiring about service availability, users can ask questions in their own words without following a rigid script. DIVA 2.0’s enhanced AI capabilities allow it to understand context, manage complex requests, and provide accurate, personalized responses, significantly improving the overall customer experience and reducing the need for human intervention. The following high-level architecture diagram illustrates the application flow and the solution architecture with AWS services.

The DTDC logistics agent is designed using a modular and scalable architecture to provide seamless integration and high performance. This streamlined workflow demonstrates how a generative AI-powered serverless logistics agent using AWS App Runner, Amazon Bedrock Agents, AWS Lambda, and a vector-based knowledge base handles user queries ranging from tracking requests to serviceability checks and shipping rates intelligently and efficiently.

The logistics agent is hosted as a static website using Amazon CloudFront and Amazon Simple Storage Service (Amazon S3). The logistics agent is integrated with the DTDC website, which provides an intuitive and user-friendly interface for end-user interactions (see the following screenshot).

An end-user accesses the logistics agent through the DTDC website and submits queries like tracking shipments, checking service availability, calculating shipping rates, FAQs, and so on using natural language.The user requests are processed by App Runner, which helps run the web application (including API services, backend web services, and websites) on AWS. App Runner is hosted with multiple API services, such as the Amazon Bedrock Agents API and Dashboard API. App Runner initiates the Amazon Bedrock Agents API based on the user requests.

Amazon Bedrock is a fully managed service that offers a choice of industry leading foundation models (FMs) along with a broad set of capabilities to build generative AI applications, simplifying development with security, privacy, and responsible AI. With Amazon Bedrock, your content is not used to improve the base models and is not shared with any model providers. Amazon Bedrock Guardrails provides configurable safeguards to help safely build generative AI applications at scale. To learn more, see Build safe and responsible generative AI applications with guardrails. AWS Identity and Access Management (IAM) helps administrators securely control who can be authenticated and authorized to use Amazon Bedrock resources.

The Amazon Bedrock agents are configured in Amazon Bedrock. An Amazon Bedrock agent receives the request and interprets the user’s intent using its natural language understanding capabilities. Based on the interpreted intent, the agent triggers an appropriate Lambda function, such as:

• Tracking consignments
• Pricing information
• Location serviceability check
• Support ticket creation

The triggered Lambda function calls the following client APIs, retrieves the relevant data, and returns the response to the agent:

• Tracking System API – Retrieves real-time status and provides updates on consignment shipment tracking
• Delivery Franchise Location API – Checks the service availability to deliver the parcels between the locations
• Pricing System API – Calculates the shipping rates based on shipment details provided by the user
• Customer Care API – Creates a support ticket for the end-users

The agent passes the response to the large language model (LLM), in this case Anthropic’s Claude 3.0 on Amazon Bedrock, which understands the context of the retrieved data, processes it, and generates a meaningful response for the user.

The knowledge base contains web-scraped content from the DTDC website, internal support documentation, FAQs, and operational data, enabling real-time updates and accurate responses. The knowledge base contents are stored as vector embeddings in Amazon OpenSearch Service, providing quick and relevant responses. For general queries, the logistics agent fetches information from Amazon Bedrock Knowledge Bases, providing accuracy and relevance. Using semantic similarity search, relevant chunks of information are retrieved from the knowledge base based on the user’s query, which Amazon Bedrock then uses to generate a context-aware response. If no relevant data is found in the knowledge base, a fallback response (preconfigured in the Amazon Bedrock prompt) is returned, indicating that the system couldn’t assist with the request.

The logistics agent queries and associated responses are stored in Amazon Relational Database Service (Amazon RDS) for PostgreSQL for enhanced scalability and relational data handling. App Runners initiates the Dashboard API call to update the queries and associated responses in Amazon RDS. We discuss this in more detail the following section.

Throughout the process, Amazon CloudWatch Logs captures key events such as intent recognition, Lambda invocations, API responses, and fallback triggers for auditing and system monitoring. AWS CloudTrail records and monitors activity in the AWS account, including actions taken by users, roles, or AWS services. It logs these events, which can be used for operational auditing, governance, and compliance.

Amazon GuardDuty is a threat detection service that continuously monitors, analyzes, and processes AWS data sources and logs in your AWS environment. GuardDuty uses threat intelligence feeds, such as lists of malicious IP addresses and domains, file hashes, and ML models to identify suspicious and potentially malicious activity in the AWS environment.

Logistics agent dashboard

The following high-level architecture diagram illustrates the logistics agent dashboard, which captures the end-user interactions and its associated responses.

The logistics agent dashboard is hosted as a static website using CloudFront and Amazon S3. Dashboard access is allowed only for the DTDC admin team.

The dashboard is populated through API calls using Amazon API Gateway with Lambda as a backend, which retrieves the dashboard data from Amazon RDS for PostgreSQL.

The dashboard provides real-time insights into the logistics agent performance, including accuracy, unresolved queries, query categories, session statistics, and user interaction data (see the following screenshot). It provides actionable insights with features such as heat maps, pie charts, and session logs. Real-time data is logged and analyzed on the dashboard, enabling continuous improvement and quick issue resolution.

Solution challenges and benefits

When implementing DIVA 2.0, DTDC and ShellKode faced several significant challenges. Integrating real-time data from multiple legacy systems was crucial for providing accurate, up-to-date information on tracking, rates, and serviceability. This was likely addressed through the robust API integration capabilities of Amazon Bedrock Agents. Another major hurdle was training the AI to understand complex logistics terminology and multi-step queries, which was overcome by using Amazon Bedrock LLMs and Amazon Bedrock Knowledge Bases, fine-tuned with industry-specific data. The team also had to navigate the delicate process of transitioning from the old rigid DIVA system while maintaining service continuity and preserving historical data, potentially employing a phased approach with parallel systems. Finally, scaling the solution to handle over 400,000 monthly queries while maintaining performance was a significant challenge, addressed by using the cloud infrastructure of Amazon Bedrock Agents for optimal scalability and performance. These challenges underscore the complexity of upgrading to an AI-powered system in a high-volume, data-intensive industry like logistics, and highlight how AWS solutions provided the necessary tools to overcome these obstacles. DTDC realized the following benefits from powering the logistics agent with generative AI using Amazon Bedrock:

• Enhanced conversations and real-time data access with customer support agents – Powered by Amazon Bedrock Agents, the solution improves natural language understanding, enabling more fluid and engaging conversations. With multi-step reasoning, it can handle a broader range of queries with greater accuracy. Additionally, by integrating seamlessly with DTDC’s API layer, the logistics agent provides real-time access to vital information, such as tracking shipments, service availability, and calculating shipping rates. The combination of advanced conversational capabilities and real-time data provides fast, accurate, and contextually relevant responses.
• Intelligent data processing and accurate FAQ responses – For complex queries, the logistics agent uses LLM technology to process raw data and deliver structured, tailored responses. This makes sure users get clear, actionable insights. For frequently asked questions, the logistics agent uses Amazon Bedrock Knowledge Bases to deliver precise answers without requiring human support, reducing wait times and enhancing the overall user experience.
• Reduced live agent dependency and continuous improvement – Although the logistics agent hasn’t eliminated the need for customer support, the number of queries handled by the customer support team has reduced by 51.4%. The system provides valuable insights into key performance metrics like peak query times, unresolved issues, and overall engagement through integrated real-time analytics, helping refine and improve the assistant’s capabilities over time.

Results

The generative AI-powered logistics agent has reduced the burden on customer support teams and shortened resolution times, resulting in better customer experience:

• Powered by Amazon Bedrock, DIVA 2.0 understands queries in natural language and supports dynamic conversations with a response accuracy of 93%
• Based on the last 3 months of dashboard metrics data, they observed the following:
  • 71% of the inquiries were related to consignments (256,048), whereas 29.5% were general inquiries (107,132)
  • 51.4% of consignment inquiries (131,530) didn’t result in a support ticket, whereas 48.6% (124,518) led to new support ticket creation
  • Of the inquiries that resulted in tickets, 40% started with the customer support center before moving to the AI assistant, whereas 60% began with the assistant before involving the customer support center

DIVA 2.0 has reduced the number of queries handled by the customer support team by 51.4%. DTDC’s support team can now focus on more critical issues, improving overall efficiency.

Summary

This post demonstrated how Amazon Bedrock can transform a traditional chatbot to a generative AI-powered logistics agent that provides better customer experience through dynamic conversation. For businesses facing similar challenges, this solution offers a blueprint for modernizing your AI assistant while maintaining compliance with industry standards.

To learn more about this AWS solution, contact AWS for further assistance. AWS can provide detailed information about implementation, pricing, and how to tailor the solution to your specific business needs.

About the authors

Rishi Sareen – Chief Information Officer (CIO), DTDC is a seasoned technology leader with over two decades of experience in driving digital transformation, enterprise IT strategy, and innovation across the logistics and supply chain sector. He specializes in building agile, AI-driven, and secure technology ecosystems that enhance operational efficiency and customer experience. Rishi leads initiatives spanning system modernization, data intelligence, automation, cybersecurity, cloud, and artificial intelligence. He is deeply committed to aligning technology with business outcomes while fostering a culture of continuous improvement and purposeful innovation. A strong advocate for people-centric leadership, Rishi places high emphasis on nurturing talent, building high-performing teams, and mentoring future-ready technology leaders who can thrive in dynamic, AI-powered environments. Known for his strategic vision and disciplined execution, he has led large-scale digital initiatives and transformation programs that deliver lasting business impact.

Arunraja Karthick – Head – IT Services & Security (CISO), DTDC is a strategic IT and cybersecurity leader with over 15 years of experience driving enterprise-scale digital transformation. As the Head of IT Services & Security (CISO) at DTDC Express Limited, he leads the organization’s core IT, cloud, and security programs—transforming legacy environments into agile, secure, and cloud-native ecosystems. Under his leadership, DTDC has adopted a hybrid cloud architecture spanning AWS, GCP, and on-prem colocation, with a vision to enable dynamic workload mobility and vendor-neutral scalability. Arunraja has led critical modernization efforts, including the migration of key business applications to microservices and containerized platforms, while ensuring high availability and regulatory compliance. Known for his deep technical insight and execution discipline, he has implemented enterprise-wide cybersecurity frameworks—from Email DLP, Mobile Device Management, and Conditional Access to Hybrid WAF and advanced SOC operations. He has also championed secure access transformation through Zero Trust-aligned Secure WebVPN, redefining how internal users access corporate apps. Arunraja’s leadership is grounded in platform thinking, automation, and a user-first mindset. His recent initiatives include the enterprise rollout of GenAI copilots for customer experience and operations, as well as unified policy-based DLP and content control mechanisms across endpoints and cloud. Recognized as an Influential Technology Leader, Arunraja continues to challenge conventional IT boundaries—aligning security, agility, and innovation to power business evolution.

Bakrudeen K an AWS Ambassador, leads the AI/ML practice at Shellkode, focusing on driving innovation in artificial intelligence, especially in Generative AI. He plays a key role in building teams and advanced AI solutions, Agentic Assistants, and other next-gen technologies. Bakrudeen has made notable contributions to AI/ML research and development. In 2023 and 2024, he received the Generative AI Consulting Excellence Partner Award at the AI Conclave and the Social Impact Partner of the Year Award for Generative AI at AWS re:Invent 2024, both on behalf of Shellkode reflecting the team’s strong commitment to innovation and impact in the AI space.

Suresh Kanniappan is a Solutions Architect at AWS, handling Automotive, Manufacturing and Logistics enterprises in India. He is passionate about cloud security and Industry solutions that can solve real world problems. Prior to AWS, he worked for AWS customers and partners in consulting, migration and solution architecture roles for over 14 years.

Sid Chandilya is a Sr. Customer Relations Manager at AWS, responsible for tech led business transformation with Automotive, Manufacturing and Logistics enterprises in India. Sid is peculiarly passionate about challenging status quos, building a joint “Think Big” vision with customer CXOs and leveraging Ai infused tech to accelerate outcomes. He is known for his deep understanding of industry imperatives (working backward from customer) and translating the business pain points into tech solution.

Transform your cleaning routine with the Shark AI Ultra Voice Control Robot Vacuum! This high-tech marvel boasts over 32,487 ratings, an impressive 4.2 out of 5 stars, and has been purchased over 900 times in the past month. Perfect for keeping your home spotless with minimal effort, this vacuum is now available for the unbeatable price of $349.99!

Don’t miss out on this limited-time offer. Order now and let Shark AI do the work for you!

Help Power Techcratic’s Future – Scan To Support

If Techcratic’s content and insights have helped you, consider giving back by supporting the platform with crypto. Every contribution makes a difference, whether it’s for high-quality content, server maintenance, or future updates. Techcratic is constantly evolving, and your support helps drive that progress.

As a solo operator who wears all the hats, creating content, managing the tech, and running the site, your support allows me to stay focused on delivering valuable resources. Your support keeps everything running smoothly and enables me to continue creating the content you love. I’m deeply grateful for your support, it truly means the world to me! Thank you!