Urgent.News

What's breaking now, across thousands of outlets.

AI

How Circle K accelerated DevOps incident triage to under 15 minutes with Amazon Bedrock

Circle K's DevOps team cut incident triage from 45-60 minutes to under 15 by building an agentic triage system on Amazon Bedrock. This post walks through the architecture, the initial Amazon Bedrock Flows implementation, the migration to Amazon Bedrock AgentCore, and the lessons learned from scaling it.

At Circle K, a cloud-native infrastructure supports various applications across 17,200 stores in 27 countries. An automated triage system was developed using Amazon Bedrock to reduce incident triage time to under 15 minutes, a 67-75% reduction. The system uses an agentic AI architecture to investigate incidents autonomously and deliver structured summaries to Slack.

Instead of manual steps like reviewing logs, checking service health, and correlating symptoms, on-call engineers now receive actionable context to act immediately.

Written by urgent.news from AWS Machine Learning's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at aws.amazon.com →

More in AI

Agentic engineering intelligence with Amazon Nova Multimodal Embeddings and Amazon Bedrock AgentCore

Learn how to build a multi-agent engineering assistant that compresses aerospace component substitution evaluation from days to minutes, using Amazon Nova Multimodal Embeddings, Amazon Bedrock…

  • Amazon Bedrock AgentCore orchestrates three specialist agents for part substitution evaluation
  • Amazon Nova Multimodal Embeddings embed diverse content types for semantic similarity retrieval
  • Human-in-the-loop ensures engineers retain final decision-making authority

Build efficient agents with knowledge distillation on Amazon SageMaker AI

Agentic assistants built on frontier models run a multi-step tool loop, and paying frontier prices on every step is hard to sustain at production scale.

  • Knowledge distillation transfers larger model's behavior to smaller model
  • Sequence-level distillation uses teacher's text outputs for training
  • Amazon SageMaker AI enables serverless training of knowledge distilled models

More from Monday 2 November →