---
title: "Comment by Evelyn Wyatt on \"Common ServiceNow AI Agent Mistakes (and How to Avoid Them)\" | Hashnode"
description: "One thing worth emphasizing with ServiceNow AI agents is that a successful response doesn't always mean the workflow completed correctly. At IT Path Solutions,"
url: "https://hashnode.com/posts/servicenow-ai-agent-mistakes/6ad09136b2ae051939d9ed94/comment/6ad0bd1f53e1c1382bb5f461"
---

[Discussion](https://hashnode.com/posts/servicenow-ai-agent-mistakes/6ad09136b2ae051939d9ed94)

Comment [Common ServiceNow AI Agent Mistakes (and How to Avoid Them)](https://hashnode.com/posts/servicenow-ai-agent-mistakes/6ad09136b2ae051939d9ed94)

[Evelyn Wyatt](https://hashnode.com/@Evelynwyatt)

[Oct 15](https://hashnode.com/posts/servicenow-ai-agent-mistakes/6ad09136b2ae051939d9ed94/comment/6ad0bd1f53e1c1382bb5f461)

One thing worth emphasizing with ServiceNow AI agents is that a successful response doesn't always mean the workflow completed correctly. At IT Path Solutions, we see the importance of verifying the actual record changes, approval states, and downstream actions rather than relying only on the agent's final message. A useful safeguard is to define the expected postconditions for each action and check them before reporting success. This makes failures easier to detect and prevents an agent from presenting an incomplete workflow as a completed task.

[Pratham Agrawal](https://hashnode.com/@agrawalpratham)

[Oct 15](https://hashnode.com/posts/servicenow-ai-agent-mistakes/6ad09136b2ae051939d9ed94/comment/6ad0bd1f53e1c1382bb5f461#reply-6ad0cb2550d1070eb760be5c)

Thanks, this is an important point. An agent saying “Done” isn’t proof that anything happened.

I agree that defining postconditions per action is the right safeguard. A few ways I’d connect it to the platform:

In the instructions: make the completion condition explicit, and tell the agent to re-read the record after a write (state, assignment, approval) before it confirms success to the user. In testing: agentic evaluations score task completeness and tool calling, not just the final message. That helps catch runs that “sound” complete but aren’t. After go-live: check the execution plan and its tasks (sn\_aia\_execution\_plan / sn\_aia\_execution\_task) against the actual record changes. Any gap between what the agent reported and what the records show is your failure signal.

Supervised mode on write actions adds another check, because a human sees the proposed change before it runs. I may cover postcondition checks as their own post. Appreciate you adding this!