I used the o word last week and it hit a few nerves. Ontologies bring context. But then context engineering is very poorly understood. Agent engineers speak about it, expect everyone is doing it, know but almost everyone is winging it. Here's what context engineering is definitely not - ie. longer prompts. What it actually is - the right information, with the right meaning, at the right time. Not more but the right information with the right meaning. Sounds super abstract. That's why a brief video that actually breaks down how to load context. Okay. Not brief. but context needs context.

Ever heard of "knowledge engineering"? It’s what we called AI before AI was cool. I just pulled this out of the deep archives, Stanford University, 1980. Feigenbaum’s HPP report. The bones of modern context engineering were already there. ↳ What they did: ➤ Curated knowledge bases, not giant prompts ➤ Rule “evocation” to gate relevance ➤ Certainty factors to track confidence ➤ Shells + blackboards to orchestrate tools ➤ Traceable logic so humans could audit decisions ↳ What we do now: ➤ Trimmed RAG context instead of bloated prompts ➤ Retrieval + reranking + policy checks for gating ➤ Scores, evals, and guardrails to manage uncertainty ➤ Tool calling, MCPs, workflow engines for execution ➤ Logs + decision docs for explainability ↳ The through-line for UX: ➤Performance comes from shaping context, what to include, when to include it, and how to prove it worked. If you're building AI agents, you're standing on those shoulders. Start with context, not cleverness. Follow for human-centered AI + UX. Reshare if your team ships with context discipline. | 41 comments on LinkedIn