Accelerating aircraft IFEC diagnostics with agentic AI on AWS
Machine Learning Blog
This article describes how Panasonic Avionics Corporation built an agentic AI diagnostic system on AWS to accelerate in-flight entertainment and connectivity (IFEC) system troubleshooting across its global fleet.
- Multi-agent workflow uses Trend Analyzer, Correlation Analyzer, System Checks, and Log Analyzer agents to diagnose issues in parallel
- Amazon Bedrock synthesizes findings into diagnostic reports with root cause analysis and remediation recommendations
- Amazon SageMaker orchestrates agents using LangGraph; AWS Glue and Amazon EMR handle ETL pipeline
- Vector search in Amazon RDS with pgvector retrieves similar past incidents for contextual insights
- Achieved 20-40 percent improvements in operational efficiency and reduced manual investigative burden significantly
- System moved from reactive ticket-based detection to proactive anomaly identification across fleet configurations
The solution demonstrates how agentic AI can scale institutional knowledge and reduce diagnostic time from hours to minutes while maintaining accuracy and human oversight.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
2026
2026
2026
2026
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.