---
title: "Discussion on \"Nobody's talking about what happens when an AI agent does the wrong thing\" | Hashnode"
description: "Discussion on \"Nobody's talking about what happens when an AI agent does the wrong thing\". Every week there's a new video going around. Agent writes the code, agent closes the ticket, agent generates the report, agent does the thing. It's genuinely good stuff. What almost nobody's talking a"
url: "https://hashnode.com/posts/nobody-s-talking-about-what-happens-when-an-ai-agent-does-the-wrong-thing/6a8546e42f4753499e509fee"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Nobody's talking about what happens when an AI agent does the wrong thing](https://blog.krtk.dev/nobody-s-talking-about-what-happens-when-an-ai-agent-does-the-wrong-thing?utm_source=hashnode&utm_medium=feed)

Every week there's a new video going around. Agent writes the code, agent closes the ticket, agent generates the report, agent does the thing. It's genuinely good stuff. What almost nobody's talking a

Aug 19 · 5 min read · blog.krtk.dev  
Read the article

-   [#ai-agents](https://hashnode.com/tag/ai-agents)
-   [#security](https://hashnode.com/tag/security)

## Written by

[Kartik Puri](https://hashnode.com/@chopcoding)

@chopcoding · Pune,India

  
[View profile](https://hashnode.com/@chopcoding)

Backend & AI systems, built to last

I run engineering for Incentivate, an enterprise sales-commission platform — a team of six, four product suites, and nine years of Python, Flask, Redis and ClickHouse. The last two years have gone into agentic AI that actually runs in production, not demos. I also ship products of my own — a live EV-charging map for India, a tool that measures how LLMs talk about brands, and an arena where autonomous AI agents compete.

## Responses 2

Markdown supported · ⌘↵ to post

[Jeff Vyder](https://hashnode.com/@jeffvyder)

[Aug 20](https://hashnode.com/posts/nobody-s-talking-about-what-happens-when-an-ai-agent-does-the-wrong-thing/6a8546e42f4753499e509fee/comment/6a87478ccb7f42299e588abf)

Its why its nice to have an agentic loop. so the agent reviews his work with other agents before anything goes to production

[Kartik N V J K](https://hashnode.com/@kartik-nvj)

[Aug 19](https://hashnode.com/posts/nobody-s-talking-about-what-happens-when-an-ai-agent-does-the-wrong-thing/6a8546e42f4753499e509fee/comment/6a85fd73bfe110760cd65bef)

The blast radius of a wrong action is the part most agent demos skip right past, and it is where the real engineering is. I dug into this on the handoff side, since a wrong artifact passed to the next agent is where a lot of quiet failures start: [kartiknvjk.hashnode.dev/how-i-evaluate-agent-hand…](https://kartiknvjk.hashnode.dev/how-i-evaluate-agent-handoffs-the-part-that-actually-breaks) . Once you score the boundary between steps, the wrong-action cases get much easier to contain.
