Who owns the knowledge graph behind the bot?

I keep returning to a simple test: after a week of work on who owns the knowledge graph behind the bot?, can someone outside the room explain what changed and who owns it?

A RAG system without an owner for freshness is a demo with a long half-life of embarrassment.

Connectors and access control are where RAG projects die. Treat them as product work, not glue.

Sustainability shows up as fewer retries, right-sized environments, and CI that does not burn cycles for vanity. Efficiency is operational maturity.

Retrieval quality is an operations problem: stale sources, missing permissions, and chunking that shreds meaning.

Build evals early. Without them you are arguing about vibes while users lose trust.

I watch for two failure modes. First, leaders who disappear into strategy and lose the texture of the work. Second, leaders who never leave the details and never grow successors. Both produce brittle teams.

On who owns the knowledge graph behind the bot?, the leadership move is to make the invisible visible: ownership, verification, and the path for the next person.

Buy-versus-build debates should start from ownership. If nobody on your team can operate the failure mode, you did not buy a capability — you rented a demo.

I prefer written decisions over verbal ones. Memory is a poor archive, and AI tools make fluent improvisation cheap — which raises the value of durable context.

None of this requires a new framework brand. It requires attention, a short feedback loop, and the humility to change process when agents join the workflow.

Lead for continuity. Leave systems and people that still work when you are not in the room.