Redundant semantic recall is buying neither speed nor better answers.
The cache must remove repeated retrieval without letting one session influence another.
Who you’d be doing this for
“My queue was quiet, then every first reply started hanging while customers watched.”
Daiki Xie · Application Developer
Runs a support agent for a web application built on Workers.
What is at stake
P95 first response has risen from 1.1 to 2.4 seconds after redundant retrieval calls appeared. You must weigh a faster cache path against session-safe context and answer quality.
Why it isn’t already fixed
Every obvious fix costs something else. That’s the part you’d have to decide.
- response speed vs session isolation
- cache efficiency vs answer quality
- immediate relief vs recurring retrieval cost
Why Cloudflare
Workers AI agents use Vectorize, Durable Objects, and Workers KV in the request path for customer-facing work.
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.