Experienced CICS system programmers are often the single best knowledge base their organisation has — but much of that value is scattered across inboxes, chat threads, ticket histories, and, most critically, “tribal knowledge” that never makes it into formal documentation. In this session, “Turbo‑charge CICS knowledge for AI use,” we’ll show how to turn that fragmented expertise into an AI‑ready knowledge layer that can reliably support modern AI assistants and specialised CICS agents. We’ll focus on pragmatic, low-friction techniques for extracting high-signal operational know‑how: structured SME conversations (remote-friendly), capturing real troubleshooting narratives, and using transcripts as raw material to produce curated, reviewable knowledge documents — so your best practices and hard-won lessons become reusable, searchable, and consistently available. You’ll learn how to prioritise what to capture (runbooks, “why we do it this way,” failure modes, and decision heuristics), how to reduce ambiguity and “it depends” answers into context-rich knowledge, and how to establish lightweight validation so the content stays trusted as CICS evolves. The goal: move from ad hoc expert interruption to scalable expertise-on-demand, enabling AI systems to go deep on CICS-specific questions rather than staying generic.