1 · Identify
Tag each supported call
Your integration adds the customer and workflow to each supported model call.
Projects / KazenAI Agent FinOps
KazenAI Agent FinOps checks every supported model call against the customer’s limit before it runs, and ties the cost to the customer and workflow behind it.
You work with the person who built it. The first 30 minute call is free, and if I can’t help, I say so before you pay anything.
Over budget$0.00
Automated test on PostgreSQL, not customer traffic.
Agent FinOps connects each supported model call to the customer and workflow behind it, then applies the agreed limit before the next call.
“Which customer or workflow drove this cost?”
Cost records carry the customer and workflow your integration supplies, so you can see which customer facing work caused the cost.
“What stops the next call from going over?”
The agreed limit is checked before the next supported provider call. Over the limit, the call doesn’t run.
“What did we expect to spend, and what did we spend?”
Expected exposure and recorded actual cost stay separate in the record.
“Why was this run stopped?”
Limit decisions and run receipts refer to the same run, so allow versus deny is visible and reviewable.
Make agent spend controllable before it hurts.
Adoption starts narrow. One existing workflow is evaluated before any wider rollout.
1 · Identify
Your integration adds the customer and workflow to each supported model call.
2 · Check
The agreed rule runs before the call. Where configured, expected exposure is reserved first.
3 · Settle
Recorded actual cost settles the reservation, and the decision is preserved in a run receipt.
Illustrative evidence from a budget denial before a supported provider call.
HTTP 402 Payment Requiredavailable_budget_usd:0.20projected_spend_usd:0.50allowed:falseavoided_cost_usd:0.50provider_call:not executedevent:budget_reservation_denied
OpenAI Chat Completions and Anthropic Messages, sync and async, with or without streaming, verified against the live provider APIs. Other paths require separate verification.
The hosted demo uses sample data. Customer production deployment, shared policy behavior and your safe response after a denial require separate verification.
The first 30 minute call is free, and I reply within one business day.