HN Explorer

Ask HN: For Enterprise coding agents, what's your company doing to control cost?

1 points by m0rde ↗ HN
For those of you with enterprise pay-as-you-go plans, what's your company doing to keep costs from exploding? Do you have monthly limits? How do those limits spread across vendors? Does everyone have the same limit? What happens if you hit that limit halfway through the month?

My company is a medium size startup trying to support multiple vendors and harnesses. We're thinking of having tiers of limits (tech vs non tech) and allowing users to decide where they want to spend that.

Curious to hear what others are doing as prices and usage get higher and higher.

13 comments

[ 0.30 ms ] story [ 3.7 ms ] thread
steammaho
Looking to what's going on in our company I see that majority of employees doesn't understand efficient usage and how better to use models. Even programmers sometimes do crazy stupid things. I would think twice before allowing users to decide something that may directly influence spends
robertcope
We recently rolled out a dashboard so that you can see your token usage. Looking at my usage vs others on my team, I just cannot imagine what they're doing. I use Claude for literally everything and my usage is 10x smaller. I genuinely do not know how they can use that many more tokens. There's gotta be some kind of curve that shows token vs effectiveness and it is not linear.
[dead] mio_ships
[flagged]
m0rde
Thanks, great ideas to try out here!
anthoniks
The hard part with agent skill is that "read this file and run these tools" basically makes your repo content part of what the agent has to trust. Static inspection is useful, but I wonder how much malicious behaviour can realistically be detected before runtime?
Mohamed_Amineio
i built nexalione.com cause i was tired paying other website for things i could get for free but the most thing that reduced my cost is by hosting it alone with cloudflare it reduces cot of hosting by almost 100% and helps you run a smooth website
khantto
in my experience, i tried to use some Chinese LLM, the package plan is much affordable.
softwaredoug
I personally think the root cause is losing hand coding skills

You can be much more token efficient if you code 5-10% and let the LLM replicate those patterns. You can also maintain an understanding of the system. Avoid needless AI layered complexity. And ship less slop.

I’m simultaneously bullish on human and AI coding.