[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"raw-en-use-cases\u002Fsoftware-engineering":3},"---\ntitle: IQ:NS for Software Engineering\ndescription: How engineering teams integrate structured AI knowledge into development workflows and agent architectures.\nlang: en\nnavigation:\n  section: use-cases\n  label: Software Engineering\n  order: 50\n---\n\n# IQ:NS for Software Engineering\n\n## The challenge\n\nEngineering teams build and deploy AI systems but often lack clarity on what compliance actually means in code — which tests to run, what to document, which controls matter for their specific system.\n\n## What the ontologies provide\n\n- **Requirements as structured data** — framework obligations queryable via SPARQL, not buried in PDFs\n- **Pipeline integration** — embed ontology queries in CI\u002FCD to surface relevant requirements at build time\n- **Agent-ready knowledge** — MCP server lets AI coding agents reason about institutional rules directly\n- **Shared vocabulary with compliance** — same concepts, same definitions, no translation overhead\n\n## How it fits\n\nThe ontologies sit alongside your existing tools — Jira, CI\u002FCD, model registries. They provide structured context so engineering decisions connect to institutional requirements without manual handoffs.\n\n[Explore the ontologies](https:\u002F\u002Fgithub.com\u002Fiqns-org\u002Fontologies) · [Get started](\u002Fgetting-started)\n",1776235632437]