https://vbonnet.ai/tags/guardrails/ Recent content in Guardrails on Valentin Bonnet Hugo en-us Fri, 13 Mar 2026 00:00:00 +0000 https://vbonnet.ai/blog/death-by-a-thousand-tests/ Fri, 13 Mar 2026 00:00:00 +0000 https://vbonnet.ai/blog/death-by-a-thousand-tests/ Not every check belongs in the synchronous path. The right amount of enforcement isn't the maximum — it's where the cost of checking balances the cost of missing. https://vbonnet.ai/blog/oops-i-did-it-again-i-forgot-dry-run/ Fri, 27 Feb 2026 00:00:00 +0000 https://vbonnet.ai/blog/oops-i-did-it-again-i-forgot-dry-run/ Agent permissions aren't about distrusting the agent. They're about acknowledging that even a capable actor will occasionally make mistakes. Build so mistakes don't take down the building. https://vbonnet.ai/blog/most-rules-exist-for-a-reason/ Fri, 13 Feb 2026 00:00:00 +0000 https://vbonnet.ai/blog/most-rules-exist-for-a-reason/ An AI agent encountering a constraint it doesn't understand will do what any capable new hire would: question it. Unlike a new hire, it might remove the fence without asking.