Re:Ask HN: How are you monitoring AI agents in production?
by mej2020 on Wednesday March 11, 2026 @04:39PM
(#47341291)
We built Lava to handle the surprise bills part. It has two products that work well for agents. The gateway is a proxy you point your agent at instead of calling APIs directly, and every request gets logged with usage and costs automatically. Spend keys are pre-funded API keys with hard spend limits, so you can hand one to an agent and it physically can't exceed the budget you set. Only posting because I think it could be helpful for what you are describing!
[ Parent
| on HN ]
Re:Ask HN: How are you monitoring AI agents in production?
by dreadpirates on Tuesday March 17, 2026 @06:27AM
(#47410785)
Your observation about the real failure mode being 'agent makes 10,000 correct $0.02 decisions that collectively don't make sense' is spot on. That's why per-call rate limits don't work, you need policy that evaluates context and aggregate state. We built nornr.com for exactly this: agents request a mandate before spending, policy evaluates (budget, intent, history), returns approved/queued/blocked with a signed receipt. Works with existing payment rails. Happy to compare notes on what you've learned running this in production.