Generative AI on AWS with Amazon Bedrock
Delivered by Converg-IN
01Summary
A global life sciences analytics firm partnered with Converg-IN to embed production Generative AI into its proprietary analytics platform on AWS. Using Amazon Bedrock with Anthropic Claude models and retrieval-augmented generation (RAG) over the firm’s curated data, the solution automatically turns large volumes of clinical, regulatory, patent and market data into prioritized competitive-intelligence insights and proactive alerts, and lets business users query commercial and forecasting data in plain language. The solution runs privately within the customer’s AWS environment with enterprise-grade security, client data isolation and auditability.
02About the Customer
The customer is a life sciences consulting and analytics organization that combines pharmaceutical domain expertise, business consulting and technology. It serves pharmaceutical and biotech companies across major therapy areas.
Its services span forecasting, business development and licensing, competitive intelligence, market research, commercial and real-world data analytics, sales and field analytics, data engineering, business intelligence and master data management, delivered through its own proprietary analytics platform and AI-driven analytics solutions.
03The Challenge
The customer’s analysts and its pharmaceutical clients depend on fast, accurate insight from a constantly changing stream of clinical trial results, regulatory approvals, patents, exclusivity data and market news. Reviewing, filtering and summarizing this information was largely manual, which consumed significant analyst time and created a risk that important competitor, clinical or regulatory signals would be identified late. Business users also relied on analysts for routine commercial and forecasting questions, creating bottlenecks.
The customer needed a secure, scalable Generative AI capability, embedded within its existing platform rather than as a separate tool, that could:
- Continuously review clinical trials, approvals, patents, exclusivity and market news to identify important competitive signals.
- Reduce analyst effort spent reading, filtering and summarizing rapidly changing information.
- Give business users self-service access to commercial and forecasting insights through natural-language questions.
- Ground AI responses in the customer’s curated data rather than model memory, with source references.
- Embed Generative AI into its analytics platform and client-facing applications.
- Maintain enterprise-grade security, client data isolation, auditability and responsible AI controls.
04The Solution
Converg-IN designed and implemented production Generative AI capabilities on AWS using Amazon Bedrock with Anthropic Claude models. The capabilities were delivered as part of the customer’s analytics platform and integrated with its existing data and application environment, using retrieval-augmented generation (RAG) over the customer’s curated data. Two Generative AI use cases are in production:
AI Competitive Intelligence Insights
uses Amazon Bedrock to summarize newly loaded market data, rank relevant signals, generate concise insights and send proactive strategy alerts.
AI Analytics & Forecasting Assistant
answers business questions in plain language by querying commercial, sales and forecasting data and explaining the results.
How AWS was used
Foundation models
Amazon Bedrock with Anthropic Claude Opus 4.8 provides primary text generation, summarization and reasoning; Claude Sonnet 5 handles lighter tasks; Claude Opus 5 is evaluated before production use. Models are selected based on output quality, latency, token usage, request volume and cost.
Application and agent tier
Amazon ECS on AWS Fargate runs the GenAI services and application workloads, with read-only, scoped access to approved data sources to retrieve context for grounded responses.
Data intake
AWS Transfer Family (SFTP) lands vendor and client files in an Amazon S3 data lake, with Amazon EventBridge and AWS Lambda triggering processing workflows on Amazon ECS on EC2.
Data foundation
Amazon Redshift and Amazon RDS for PostgreSQL (with RDS Proxy) provide the analytical and curated data used for retrieval, while Amazon ElastiCache caches frequently used results and sessions.
Private model access and security
Amazon Bedrock is accessed privately through a VPC endpoint. AWS WAF, AWS Verified Access, IAM, AWS KMS, AWS Secrets Manager, Amazon GuardDuty, AWS Security Hub, Amazon Macie, AWS CloudTrail and Amazon CloudWatch provide protection, monitoring, audit and client-data isolation.
Delivery automation
AWS CodeCommit, AWS CodeBuild and AWS CodePipeline build and release container images to Amazon ECR for deployment to Amazon ECS, with AWS CloudFormation for infrastructure as code.
05Architecture
The primary production workload runs in AWS US East (Ohio), with a delivery environment in Asia Pacific (Mumbai) and Amazon Redshift snapshot copies in additional Regions for disaster recovery. The GenAI services run on Amazon ECS, retrieve relevant context from Amazon RDS for PostgreSQL and Amazon Redshift through read-only access, and send the prompt with this context privately to Amazon Bedrock to generate grounded responses. Data is securely ingested through AWS Transfer Family into Amazon S3, processed through event-driven workloads, and made available for retrieval.
06Results and Outcomes
Quantitative results
Business outcomes
Faster, prioritized competitive intelligence for pharmaceutical leadership.
Earlier identification of important competitor, clinical, regulatory, patent and market signals, with proactive strategy alerts.
Self-service access to commercial and forecasting insights through natural-language interaction.
AI responses grounded in the customer’s own curated data, with source references and improved traceability.
Generative AI integrated securely into the existing analytics platform and client-facing applications.
Enterprise-grade client data isolation, responsible AI controls, auditability and private model access.
Scalable GenAI consumption with centralized monitoring, security and cost governance.
07AWS Services Used
- Amazon Bedrock (Anthropic Claude Opus 4.8, Claude Sonnet 5 and Claude Opus 5)
- Amazon ECS on AWS Fargate
- Amazon EC2
- AWS Lambda
- Amazon ECR
- Amazon Redshift
- Amazon S3
- AWS Transfer Family
- Amazon RDS for PostgreSQL with RDS Proxy
- Amazon RDS for MySQL
- Amazon ElastiCache (Valkey and Redis)
- Amazon EFS
- Amazon VPC and VPC endpoints
- NAT Gateway
- Application and Network Load Balancers
- AWS Global Accelerator
- Amazon Route 53
- AWS Verified Access
- Amazon EventBridge
- Amazon SES
- Amazon SNS
- Amazon SQS
- AWS CodeCommit
- AWS CodeBuild
- AWS CodePipeline
- AWS CloudFormation
- Amazon WorkSpaces
- AWS Directory Service
- AWS IAM
- AWS KMS
- AWS Secrets Manager
- AWS WAF
- Amazon GuardDuty
- Amazon Inspector
- AWS Security Hub
- Amazon Detective
- Amazon Macie
- AWS Config
- AWS Certificate Manager
- Amazon CloudWatch
- AWS CloudTrail
- AWS Systems Manager
- AWS Cost Explorer
08About Converg-IN
Converg-IN Private Limited is an AWS Advanced Tier Services Partner that delivers cost-effective cloud and Generative AI solutions built on AWS Well-Architected principles. Our team of 15+ certified cloud architects covers the full cloud lifecycle: consulting and cost optimization, migration (including SAP and VMware), security, modernization, DevOps, and 24x7 managed services.
Our Modernization & GenAI practice helps customers move Generative AI from experimentation to production using Amazon Bedrock and the wider AWS AI/ML stack. We have delivered GenAI workloads for customers in sports technology, education, life sciences analytics, and AI-driven contact centers. We design every solution to be simple to deploy, secure by default, and cost-efficient to operate.
We deliver with an automation-first approach, using infrastructure-as-code to stand up environments quickly and repeatably. Security and governance are central to every engagement. With a proven track record across industry verticals, Converg-IN is a trusted partner for organizations adopting Generative AI on AWS.
Not sure what fits your business needs?
Get free consultation!
Experience you can trust, service you can count on.
