CRED announced on May 28 the launch of CRED codelens, an intelligence layer designed to provide full context for every line of code across its platform. The system leverages Amazon Bedrock to route tasks to appropriate models and offers enterprise-grade controls as part of CRED’s AI labs initiative.
With more than 20 business verticals, over 2,000 repositories, and 500 microservices, CRED said engineering complexity outpaced documentation processes. CRED codelens distributes context gathered from tools such as Slack, Confluence, Jira, and the codebase itself. The platform generates end-to-end request call graphs mapping how applications and services connect. Each code commit triggers analysis that produces documentation and indexes it into a vector database within half an hour.
An agentic layer orchestrates over 400 specialized agents for tasks including codebase question-and-answer functions, pull request review, code generation, infrastructure debugging, and test creation. According to the company statement, “Today, CRED codelens works alongside team members on every line of code in the organisation, reducing what would take weeks to build, test, troubleshoot, and deploy into hours.” Amazon Bedrock provides a governed API across models with compliance controls built in; supporting infrastructure includes Amazon Elastic Kubernetes Service for storage and observability.
Within one year of launch there are more than 500 active users utilizing over 400 agents across engineering and business teams. Productivity improvements include engineers shipping features four times faster and CI/CD pipeline debugging showing a forty percent reduction in effort. Evaluation metrics indicate seventy-four percent code segment coverage with ninety-two percent endpoint coverage.
Kiran Jagannath said, “CRED has reimagined how engineering teams operate at scale by building CRED codelens on Amazon Bedrock — turning their entire codebase into living knowledge. What stands out is how CRED has moved beyond isolated AI use cases to create an enterprise-wide intelligence layer… This is a powerful example of how India’s most innovative companies are using AWS’s generative AI capabilities to fundamentally transform how software is built and shipped.” Swamy Seetharaman said, “When every team member has instant accurate knowledge of how the system works decisions improve before a single line of code is written… Amazon Bedrock gave us the flexibility to build this at scale across models while maintaining strong controls around security governance cost and measurable ROI.”
Amazon strives to be Earth’s most customer-focused company while providing services including online shopping, cloud computing, streaming entertainment, digital devices, advertising, and retail offerings, according to its official website.