Clearly AI wins the AWS Bedrock Builder's Challenge
What is the AWS Bedrock Builder's Challenge?
Amazon Web Services (AWS) invited startups to test the limits of what generative AI can do—introducing the Amazon Bedrock Builders’ Challenge.
Startups that could demonstrate advanced technical implementation, adoption of AWS services, innovation, and potential customer impact would be rewarded with US$100,000 in AWS credits.
Alongside US$5,000 in AWS credits for experimentation and iteration, contestants were given just one rule: their production workloads had to be powered by AWS generative AI primitives—Amazon Bedrock, Amazon SageMaker, and Amazon EC2 Capacity Blocks. At the end of the contest, 5 companies were announced as winners.
How did Clearly AI win?
Winning solutions required major technical advancements leveraging AWS AI infrastructure
From the AWS blog post:
" For its entry, Clearly AI migrated from OpenAI GPT 4.0 to Claude 3.5 Sonnet and built a custom orchestration layer to help break down complicated assessments into logical stages, while maintaining context throughout the process. Migrating to Claude 3.5 Sonnet also allows Clearly AI to support its enterprise customers’ bring-your-own-cloud (BYOC) requirements with the use of Amazon Bedrock."
As former Amazon engineers, we've always proudly built on top of AWS. The Bedrock Builder's Challenge allowed us to expand our AI workflows on AWS.
Through our work with Claude on Bedrock, we developed several innovations during the challenge: a staged assessment engine that processes complex security reviews through a DAG workflow system, an intelligent document processing pipeline that analyzes various file types (code, documentation, diagrams, PowerPoints, spreadsheets) to extract security implications, and a novel questionnaire authoring system that allows security experts to rapidly encode their knowledge into AI-powered templates. Additionally, we built an LLM translation layer to convert existing questionnaires into our custom format, making automation of existing processes as easy as an upload. Finally, we incorporated function calling to empower our agent to fetch up-to-date information and proactively fill out reports for our users.
Winners also needed to have high-impact production use cases
In addition to evaluating our technical implementation, AWS also evaluated our business model and the overall impact of our product. Winning this competition is a nod from AWS about the value of the solution we're delivering.
Clearly AI is production-ready with proven results from enterprise customers, including a major US automaker, where we've helped teams complete more reviews in a matter of days than they previously did in 6 months. Thus far we’ve demonstrated 90% time savings on security reviews, while maintaining high-quality results. Clearly AI differentiates itself by focusing on structured, multi-stage assessments rather than simple Q&A, bringing security to where teams already work with deep knowledge integrations and automating the entire review lifecycle from initial triage to real-time monitoring. Clearly AI fits into security teams’ existing tools and workflows.
