---
format: "aidr-story-markdown/v1"
id: "47f7e8228e0b9c7f9965f475e8cd05e5cfb743f23560d3d912333cb734fc94b6"
canonical_url: "https://aidr.today/47f7e822?lang=en"
title: "Hacking AI customer service agents"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-09-14T16:26:03.000Z"
category: "Agents"
topics: ["agent","multi-agent","safety","harness"]
source_urls: ["https://www.intigriti.com/researchers/blog/hacking-tools/hacking-ai-customer-service-agents","https://news.ycombinator.com/item?id=49699526"]
summary: "As AI agents are deployed to automate more tasks, they become more capable. And as the famous quote goes: \"With great power comes great responsibility.\" Assuming that humans in the loop can mitigate t..."
---

# Hacking AI customer service agents

> [Open the canonical story](<https://aidr.today/47f7e822?lang=en>)

**Published:** 2026-09-14T16:26:03.000Z
**Category:** Agents
**Topics:** agent, multi\-agent, safety, harness

## Summary

As AI agents are deployed to automate more tasks, they become more capable\. And as the famous quote goes: "With great power comes great responsibility\." Assuming that humans in the loop can mitigate t\.\.\.

## Sources

- [Story source](<https://www.intigriti.com/researchers/blog/hacking-tools/hacking-ai-customer-service-agents>)
- [Discussion](<https://news.ycombinator.com/item?id=49699526>)