Automatic model selection is colliding with the customer’s need to explain every consequential fallback.
The customer needs resilient inference when capacity shifts, while finance and security need costs and routing decisions they can defend.
Who you’d be doing this for
“My CTO wants to know why one request moved models, and I don’t have a clean answer yet.”
Kariuki Tekle · AI Platform Engineer
Runs the customer’s multi-provider inference platform and is accountable for reliable, governed model access.
What is at stake
Fallbacks are changing customer-facing answers while the shared wallet drains faster than forecast. You must weigh resilient routing against the evidence finance and security need to approve it.
Why it isn’t already fixed
Every obvious fix costs something else. That’s the part you’d have to decide.
- fallback resilience vs answer consistency
- shared wallet control vs application demand
- routing automation vs audit evidence
- fast containment vs centralized governance
Why Cloudflare
AI Gateway and Workers AI now share billing and routing behavior at the edge, making the customer’s routing policy central to adoption.
Written with these in mind
Not your kind of problem? 51 more at Cloudflare, or browse every organization.
This is the setup. The work is inside.
Running it puts you in the room: the full situation and its constraints, stakeholders who push back in their own words, and the decisions that are yours to make. What you produce becomes a Day One Plan — work you can show someone instead of describing.