Show HN: AgentShield – Stop AI agents from spending money unsupervised

(agentshieldv2-dashboard-production.up.railway.app)

2 points | by lucarizzo1010 6 hours ago ago

1 comments

  • kramit1288 6 hours ago ago

    what happens when the semantic layer is uncertain or unavailable? For payments, “LLM could not decide” is itself a policy case. Failing open is risky, failing closed may create too much friction and routing everything uncertain to HITL can become noisy fast.

    I think the valuable part here is the audit trail behind it: why this spend was allowed, blocked or escalated.