LatestMachine LearningLets Build an AI On-Call Buddy: An MVP Using AWS Bedrock to Supplement Incident Response 0 like January 21, 2025Share this postAuthor(s): Asif Foysal Meem Originally published on Towards AI. This member-only story is on us. Upgrade to access all of Medium.Source: Image by MidjourneyImagine a system where an on-call engineer can simply ask a chatbot Whats wrong with the checkout service? and receive a concise, actionable response complete with logs, metrics, and insights.Hot take Being on-call is already a unique brand of excitement a mix of firefighting and waiting for the next alarm to ruin your dinner plans Why not add the fun of debugging log retrieval systems to the mix?Thats the vision that drove this experiment: to integrate AWS Bedrock, AWS Lambda, and CloudWatch logs into a seamless support system. But like any ambitious project, it came with its share of challenges, particularly a pesky 25 KB payload limit.AWS Bedrock, AWS Lambda, and CloudWatch logs are powerful tools in modern cloud architecture. However, combining these services to achieve seamless functionality can reveal some surprising limitations. This article recounts an experiment to integrate these AWS services for an on-call support chatbot and explores solutions to overcome the challenges encountered, specifically a 25 KB payload limit.The project started with a clear objective: to build a functional MVP for a DevOps chatbot using AWS Bedrock. Read the full blog for free on Medium.Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming asponsor. Published via Towards AITowards AI - Medium Share this post