Expedia Uses AI Driven Service Telemetry Analyzer to Accelerate Incident Investigation
Quick Answer
Expedia has launched the Service Telemetry Analyzer (STAR), an AI-assisted platform that streamlines incident investigations by analyzing service telemetry and generating structured root cause assessments.
Quick Take
By integrating operational metrics with , STAR aims to minimize time to know (TTK) and time to recover (TTR) while maintaining human oversight in decision-making.
Key Points
- STAR integrates with Datadog to analyze operational metrics from Kubernetes and JVM applications.
- The platform uses a deterministic workflow with prompt chaining for structured analysis.
- Expedia transitioned to a Celery-based architecture for asynchronous processing of telemetry data.
- STAR has been utilized for production incident investigations and Kubernetes troubleshooting.
- Future enhancements include service dependency information and conversational interfaces.
DeepSignal Analysis
What happened
Expedia Group has launched the Service Telemetry Analyzer (STAR), an AI-assisted platform designed to aid engineers in investigating production incidents. By analyzing service telemetry and generating structured root cause assessments, STAR aims to reduce the time engineers spend on identifying service degradation sources while ensuring human oversight in decision-making.
Key evidence
- STAR integrates operational metrics with large language models (LLMs) and follows a deterministic workflow, which includes collecting telemetry, analyzing it with domain-specific prompts, and summarizing findings into a final report.
- The platform is built as a FastAPI application that connects with Datadog for service metrics retrieval and employs a Celery-based asynchronous architecture to handle multiple analysis tasks concurrently.
- Expedia reports that STAR has been utilized for various purposes, including production incident investigations and Kubernetes troubleshooting, with engineers reviewing generated findings before taking action.
Why it matters
The introduction of STAR reflects a growing trend in the tech industry to leverage AI for operational efficiency. By streamlining incident investigations, Expedia aims to enhance its response times and overall service reliability. However, the emphasis on human oversight suggests a cautious approach to AI integration, prioritizing accuracy and accountability in critical operational processes.
Source Excerpt
Expedia Group has introduced STAR, an internal AI-assisted observability platform that helps engineers investigate production incidents using service telemetry and . Built with FastAPI, Datadog, C
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from InfoQ AI, ML & Data Engineering
See more →Google Cloud Workbench Notebooks Extension Connects VS Code to Google Cloud's Jupyter Notebooks
The Google Cloud Workbench Notebooks extension for VS Code allows developers to seamlessly connect their local IDE to managed Jupyter notebook environments on Google Cloud, enhancing ML workflow efficiency. This integration eliminates context switching, enabling smooth transitions from local experimentation to high-performance cloud computing.
