Knowledge Graphs as the Backbone of AI-First Software Delivery
summary
Claims a production Knowledge Graph powers AI agents to query CI/CD, security, observability and ticket systems, using HQL queries over connected nodes (services, pipelines, deployments) to find hotspots. Demo shows agents scanning across orgs to surface pipelines with the highest failure rates (example: a project with two pipelines showing ~200% increase), auto-generating remediation suggestions and building a 13-widget dashboard from 30 days of data, with integrations to Jira, ServiceNow, GKE and AWS.
AI-written summary · about
chapters (11)
- 0:00Welcome and Theme
- 0:21Why Context Matters
- 1:46Enterprise Context Challenges
- 2:52AI Assisted vs Operational DevOps
- 3:54Knowledge Graph Basics
- 5:10Building the Graph Layer
- 6:00Where Graphs Fail
- 7:06Harness Demo Querying Pipelines
- 9:36Insights on Failures and Actions
- 10:32Auto Dashboards and Agent Orchestration
- 12:39Integrations and Wrap Up
related talks
19mKnowledge Graphs in Litigation Agents
29mKnowledge graph based chatbots
19mMulti Agent AI and Network Knowledge Graphs for Change
42mMaking OSS AI Real with Knowledge Graphs
19mWisdom-Driven Knowledge Augmented Generation at Scale
21mAgentic GraphRAG: Autonomous Knowledge Graph Construction and Adaptive Retrieval
15mGraphRAG-Powered AI Agents: Transforming Corporate Metadata into Intelligent Knowledge
12mAgentic GraphRAG: Autonomous Knowledge Graph Construction and Adaptive Retrieval