AI Cortex

An enterprise knowledge platform that turns everything connected to a software project — code repositories, Azure DevOps work items, wikis, and uploaded documents — into a single, queryable knowledge graph, and answers natural-language questions with cited, cross-repository context.

The differentiator is cross-repo retrieval by graph traversal: a client call in repo A is linked to the endpoint it hits in repo B at ingestion time. So a question like "why is the getUser API failing?" reaches the calling service, the endpoint, the wiki page, and the related work item by walking typed edges — not by hoping a vector search surfaces them.

AI Cortex is a substrate, not a single product. It ingests a Journey's sources and exposes one journey-isolated, graph-grounded retrieval layer — and on top of it runs a family of agents (5+ in flight, DocQ AI first), embedded across the SDLC and serving developers, PMs, QA, and TPMs through a unified conversational interface. A tool-use and retrieval layer connects those agents to repositories, logs, APIs, and internal services in real time, grounding LLM outputs in organizational context to keep responses domain-accurate.