[flagged]
Show HN: Policy enforcement for Claude Code, Cursor, and Codex
11–14 of 14 posts
Re: Show HN: Policy enforcement for Claude Code, Cursor, and Codex
#12[flagged]
Re: Show HN: Policy enforcement for Claude Code, Cursor, and Codex
#13after one of our Cursor agents almost executed DELETE FROM customers WHERE status='test' against a production database Allowing agentic to touch production is a significant oversight. We would love feedback from anyone building multi-agent systems Sandbox everything, individually, including the orchestrator and operator, short agent lifecycle with agent specific credentials that die with the agent and multi-pass vali…
Yes, you are right. This example is exactly why we built Kastra. And we agree that you approach of having sandboxes and short-lived credentials is the right one. We just see policy enforcement as another layer alongside those protections. But I'm curious about your approach, how do you deal with the extra latency and disagreements between agents?
Short answer: trade off of accuracy vs latency vs deterministic.
Latency is built into good decision making while disagreements can be managed through hierarchy, weights, and more decisions.
Decisions should be made at the original intent and carried downstream to the implementation with expected outcome to be near deterministic if the desired outcome is weighed.
Re: Show HN: Policy enforcement for Claude Code, Cursor, and Codex
#14[flagged]