Urgent.News

What's breaking now, across thousands of outlets.

AI

How AvioBook builds turnaround insights from operational data with Amazon Bedrock AgentCore

AvioBook, a Thales Group Company, prototyped Connected Analytics on Amazon Bedrock AgentCore to turn AvioBook Connect's operational data into plain-language, evidence-based answers for airline managers and dispatchers, helping them find and act on the causes of flight turnaround delays.

AvioBook, a Thales Group Company, has developed a software solution to help airlines optimize their turnaround times through data analysis. Turnarounds are critical for airlines as even a few minutes of delay can have significant financial implications, with an average cost of $20 per minute. For a mid-size carrier flying 200 flights daily, improving turnaround times by just 2 minutes could save the airline around $240,000 monthly.

AvioBook's Connect platform, in service since 2018 and launched with its current API in 2025, serves as the communication platform for flight and ground operations teams. It organizes work around flightrooms, where live chats for each flight facilitate coordination among crew, cabin crew, dispatch, and station operations. The platform captures both hard data from automated messages and soft conversational data from the operational teams.

AvioBook's Connected Analytics is designed to turn the rich data collected through AvioBook Connect into actionable insights for airline managers and operations control center dispatchers. The system enables users to ask questions in plain language, eliminating the need to sift through an archive of timestamped events and messages. Two specialized agents, one for each role, are responsible for digging through the data, verifying it against the flightroom records, and providing direct answers along with supporting evidence.

By providing airlines with a fast, human-readable, and evidence-based way to analyze turnaround data, AvioBook Connected Analytics helps airlines improve their on-time performance (OTP) and manage disruptions more effectively. The system addresses the challenges of data accessibility and the need for real-time insights, ultimately helping airlines save millions of dollars in lost revenue and compliance issues.

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.

Also reported by 2 other outlets

Read the original at aws.amazon.com →

More in AI

Agent Evaluation Metric for multi-turn conversations

Multi-turn agents fail in ways single-turn evaluation misses: one early mistake corrupts every later turn. This post introduces the Agent Evaluation Metric (AEM), a decomposable, turn-level way to…

  • Agent Evaluation Metric (AEM) assesses multi-turn agent performance
  • AEM breaks down agent quality into named, measurable sub-metrics
  • Correctness sub-metrics: Truthfulness and Completeness evaluated turn by turn

More from Thursday 10 September →