---
title: "Comment by Dr Srinivas Padmanabhuni on \"Testing AI Agents Before Deployment\" | Hashnode"
description: "A readiness gate that only asks whether each tool call was allowed can still pass a bad run. I looked at a travel-planner agent where the guard refused a hotel"
url: "https://hashnode.com/posts/testing-ai-agents-before-deployment/6afd7281c3b20584bb31a192/comment/6afed44d6cda2eb6b3706fe5"
---

[Discussion](https://hashnode.com/posts/testing-ai-agents-before-deployment/6afd7281c3b20584bb31a192)

Comment [Testing AI Agents Before Deployment](https://hashnode.com/posts/testing-ai-agents-before-deployment/6afd7281c3b20584bb31a192)

[Dr Srinivas Padmanabhuni](https://hashnode.com/@srinivaspadmanabhuni)

[2d ago](https://hashnode.com/posts/testing-ai-agents-before-deployment/6afd7281c3b20584bb31a192/comment/6afed44d6cda2eb6b3706fe5)

A readiness gate that only asks whether each tool call was allowed can still pass a bad run. I looked at a travel-planner agent where the guard refused a hotel hold because the price didn't match any search result, yet the flight hold had already gone through, and the final answer said "Infeasible". Half a trip was held. Checking the final state after a failed step is the gate I'd add.
