knowledge graph

Evidence (14)

• 7InfoQ·10/9/2026research
  Netflix Builds Ontology-Driven Observability with Knowledge Graphs

  Netflix describes an observability approach for handling 38 million events per second by replacing reactive monitoring with an AI-driven operational ontology. The system unifies MELT telemetry into queryable knowledge graphs to support automated triage, root-cause analysis, and self-healing workflows using Claude and graph databases.

• 5InfoQ·9/23/2026open_source
  Graphify Unifies Codebase Context with Knowledge Graphs

  Graphify is an open-source tool that converts codebases and unstructured data into queryable knowledge graphs to improve multi-file reasoning for AI coding assistants. Recent updates expanded parser capabilities and cross-file resolution, though community feedback notes integration remains challenging in everyday workflows.

• 4Hacker News·9/23/2026product_launch
  Stripe Launches Knowledge AI Platform

  Stripe introduced its Knowledge AI Platform, an internal AI system aimed at helping engineers access and use company knowledge across the engineering organization. The article also highlights related internal AI tooling at Stripe and broader developer resources, but does not provide many implementation specifics in the excerpt.

• 5InfoQ·9/12/2026research
  Building Production-Ready Agentic AI with Knowledge Graphs

  Cassie Shum argues that knowledge graphs provide a strong foundation for production-ready agentic AI systems, especially beyond basic retrieval-augmented generation. She outlines four architectural patterns—context bundling, decision provenance, code as truth, and agent visibility—and shows how a knowledge-graph-based engineering harness can improve feedback loops, token efficiency, and reliability.

• 6InfoQ·9/11/2026research
  LinkedIn Uses Multi-Teacher Distillation to Speed Job Search Ranking

  LinkedIn described the training pipeline behind its AI-powered job search, centered on multi-teacher distillation. The approach compresses knowledge from larger teacher models into a 0.6B-parameter ranking model, enabling the system to train about 8x faster.

• 6Martin Fowler·8/27/2026framework_update
  Making Data Ready for Agentic AI

  The article argues that autonomous AI agents need data systems designed for machine consumption, not human analysts. It proposes a stack built around trusted data foundations, a context layer for meaning, and controlled access plus observability for governance and auditability.

• 7Hugging Face Blog·8/10/2026research
  Hugging Face shows cheaper large-scale knowledge distillation for LLMs

  The article presents a method for making knowledge distillation for large language models much cheaper by caching the teacher model’s top-K logits offline and using a fused chunked KL loss. The approach reduces VRAM usage enough to make distillation experiments feasible on a single GPU in some cases, instead of requiring large multi-GPU setups.

• 8Ars Technica AI·7/6/2026security
  Anthropic removes hidden Claude Code tracking after backlash

  Anthropic removed a hidden tracker in Claude Code after a researcher found code that quietly flagged some users in China and sent related signals back to the company. The company said the feature was an experiment aimed at preventing abuse and unauthorized reselling, but critics described it as a serious breach of user trust.

• 4InfoQ·7/1/2026research
  GraphRAG Presentation on Smarter Retrieval with Knowledge Graphs

  Cassie Shum presents the architectural evolution of GraphRAG and argues that strong data foundations are essential for advanced AI workflows. The talk contrasts GraphRAG with traditional vector RAG, highlighting its strengths in global context, multi-hop reasoning, and provenance through semantically structured knowledge graphs.

• 8The New Stack·6/30/2026funding
  AWS commits $1 billion to embedded enterprise AI engineers

  Amazon Web Services is creating a forward deployed engineering organization and plans to invest $1 billion to embed engineers with enterprise customers building AI applications. AWS says the teams will work inside customer environments with their data, governance controls, and infrastructure to speed production deployment and transfer operational know-how.

• 5Hacker News·6/28/2026research
  Knowledge Distillation for Black-Box Large Language Models

  This paper studies how to distill knowledge from black-box large language models, where the internal weights and architecture are not accessible. It evaluates methods for transferring capabilities into smaller student models while preserving performance and reducing inference cost. The work is a research contribution focused on model compression and efficient deployment.

• 5Hugging Face Blog·6/1/2026research
  IBM argues enterprise AI needs agent logic beyond LLMs

  IBM discusses how enterprise AI adoption depends on agentic logic, not just large language models, to better fit long-running, policy-constrained workflows. The post describes agents for mainframe code understanding, test generation, incident response, and compliance modernization that use program analysis and structured retrieval to improve accuracy and reduce cost.

• 4Martin Fowler·4/8/2026framework_update
  Feedback Flywheel for AI-Assisted Development

  The article proposes a structured feedback practice for AI-assisted development, where teams capture useful prompts, missing context, recurring failures, and successful patterns from AI sessions. Those learnings are then fed back into shared artifacts such as priming documents, runbooks, and review checklists so the team improves over time instead of repeating the same mistakes.

• 8Anthropic News·2/2/2026research
  Anthropic teams up with Allen Institute and HHMI for scientific AI

  Anthropic announced two flagship partnerships with the Allen Institute and Howard Hughes Medical Institute to apply Claude to biological and biomedical research. The collaborations will focus on multi-agent systems, lab workflows, data analysis, and experimental design to speed discovery while keeping scientists in control.