PRAXIS: Integrating Program Analysis with Observability for Root-Cause Analysis
📰 ArXiv cs.AI
Learn how PRAXIS integrates program analysis with observability for root-cause analysis of cloud incidents, reducing costs and improving efficiency
Action Steps
- Build a service dependency graph (SDG) to capture microservice-level dependencies
- Deploy an LLM-driven structured traversal over the SDG and program dependence graph (PDG)
- Configure PRAXIS to manage and deploy an agentic workflow for diagnosing code- and configuration-caused cloud incidents
- Test PRAXIS with real-world cloud incident scenarios to evaluate its effectiveness
- Apply PRAXIS to production environments to reduce the cost and time of resolving cloud incidents
Who Needs to Know This
DevOps teams and cloud engineers can benefit from PRAXIS to quickly identify and resolve production cloud incidents, saving time and money
Key Insight
💡 PRAXIS uses LLM-driven structured traversal over SDG and PDG to diagnose cloud incidents, reducing costs and improving efficiency
Share This
💡 Introducing PRAXIS: an orchestrator that integrates program analysis with observability for root-cause analysis of cloud incidents #cloudcomputing #devops
Full Article
Title: PRAXIS: Integrating Program Analysis with Observability for Root-Cause Analysis
Abstract:
arXiv:2512.22113v2 Announce Type: replace-cross Abstract: Unresolved production cloud incidents cost an average of over $2M per hour. This paper introduces PRAXIS, an orchestrator that manages and deploys an agentic workflow for diagnosing code- and configuration-caused cloud incidents. PRAXIS employs an LLM-driven structured traversal over two types of graph: (1) a service dependency graph (SDG) that captures microservice-level dependencies; and (2) a hammock-block program dependence graph (PDG
Abstract:
arXiv:2512.22113v2 Announce Type: replace-cross Abstract: Unresolved production cloud incidents cost an average of over $2M per hour. This paper introduces PRAXIS, an orchestrator that manages and deploys an agentic workflow for diagnosing code- and configuration-caused cloud incidents. PRAXIS employs an LLM-driven structured traversal over two types of graph: (1) a service dependency graph (SDG) that captures microservice-level dependencies; and (2) a hammock-block program dependence graph (PDG
DeepCamp AI