# What’s still hard about controlling agent spend?

**URL:** <https://community.crewai.com/t/what-s-still-hard-about-controlling-agent-spend/7745>\
**Category:** General\
**Created:** [August 23, 2026, 8:08pm UTC](https://community.crewai.com/t/what-s-still-hard-about-controlling-agent-spend/7745 "2026-08-23T20:08:34Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Debo\_Jolaosho](https://avatars.discourse-cdn.com/v4/letter/d/e274bd/32.png) [@Debo\_Jolaosho](https://community.crewai.com/u/Debo_Jolaosho)\
**Post date:** [August 23, 2026, 8:08pm UTC](https://community.crewai.com/t/what-s-still-hard-about-controlling-agent-spend/7745/1 "2026-08-23T20:08:34Z")

</div>

For people running agents that call paid tools.

What’s still painful about spend control?

Not the ideal setup the part that still breaks or stays manual.

Examples:

- one agent looping and burning budget
- no hard per-agent limit
- hard to see what each agent spent
- no clean way to pause one agent fast

What’s the messy part in your current setup?

---

<div class="post-metadata">

**Author:** ![ranareebaal](https://sea1.discourse-cdn.com/flex025/user_avatar/community.crewai.com/ranareebaal/32/5338_2.png) [@ranareebaal](https://community.crewai.com/u/ranareebaal)\
**Post date:** [October 15, 2026, 1:35pm UTC](https://community.crewai.com/t/what-s-still-hard-about-controlling-agent-spend/7745/2 "2026-10-15T13:35:50Z")

</div>

The messy part for me was always attribution inside the agent tree. I’ve built multi-agent orchestration setups for clients, and the same thing kept happening at the end of the month: the bill showed a total, but nobody could say which agent in the chain burnt it. We tracked it with Excel sheets and shell scripts, and even then we only had an after-the-fact audit trail, never real control.

In CrewAI specifically, max\_iter and max\_rpm bound loops and call rate but not dollars, so one agent dragging a big accumulated context can still get expensive while staying inside its limits. And a per-agent cap only really works if the check happens before the call goes out, not in a callback after the response comes back.

Curious what prompted the question, are you hitting this in your own crews or building something for it?