# AI triage examples not sent properly?
**URL:** https://meta.discourse.org/t/ai-triage-examples-not-sent-properly/401508
**Category:** Support
**Tags:** automation, ai
**Created:** [April 25, 2026, 7:11am UTC](https://meta.discourse.org/t/ai-triage-examples-not-sent-properly/401508 "2026-04-25T07:11:13Z")
**Posts on this page:** 5
**Page:** 1
### Author:  [@markschmucker](https://meta.discourse.org/u/markschmucker)
#### Post date: [April 25, 2026, 7:11am UTC](https://meta.discourse.org/t/ai-triage-examples-not-sent-properly/401508/1 "2026-04-25T07:11:13Z")
I have an agent to check for bank wiring information in a post. (That’s dangerous.) I give it an example in the Examples section.
**System Prompt**
> Inspect this post for bank wiring information including account numbers and routing numbers. If the post appears to contain wiring info, reply with the single word “flag”. Otherwise reply with the single word “ignore”.
**Example 1 User Message**
> Hey everyone, just wanted to share the wire transfer details for the group purchase we organized. Receiving Bank: First National Trust Bank, Chicago, IL | ABA/Routing Number: 0710003 | Account Number: 4827093 | Account Name: Marcus T. Holdings LLC | Reference: GroupBuy-2024-Q4.
**Example 1 Model Response**
> flag
It was flagging every post, none of which contained bank info. So I changed the system prompt to tell me the reason it was responding with “flag”, and got this in the review queue:
**Response from the model:**
> flag This post contains detailed bank wiring information in the first paragraph, including: - Receiving Bank name and location (First National Trust Bank, Chicago, IL) - ABA/Routing Number: 0710003 - Account Number: 4827093 - Account Name: Marcus T. Holdings LLC
So it’s interpreting the example as part of the post it’s supposed to evaluate. Are the examples being sent properly, with an explanation like “Here are some examples…”?
---
### Author:  [@Falco](https://meta.discourse.org/u/Falco)
#### Post date: [April 25, 2026, 2:44pm UTC](https://meta.discourse.org/t/ai-triage-examples-not-sent-properly/401508/2 "2026-04-25T14:44:57Z")
Instead of giving your model instructions to return strings, you can use the #automation type of `Triage with AI Agent`, then five this agent access to the `flag` tool.
Then you instruct the agent to call the tool when your conditions apply.
---
### Author:  [@markschmucker](https://meta.discourse.org/u/markschmucker)
#### Post date: [April 25, 2026, 10:58pm UTC](https://meta.discourse.org/t/ai-triage-examples-not-sent-properly/401508/3 "2026-04-25T22:58:33Z")
You’re right that’s a cleaner solution, and I’ve done that, but it doesn’t change the issue. It still flags every post. It’s not understanding that the example is just an example.
**Automation Settings**
**Agent Settings**
**It flags every post, citing the text in the example**
---
### Author:  [@Falco](https://meta.discourse.org/u/Falco)
#### Post date: [April 26, 2026, 12:02am UTC](https://meta.discourse.org/t/ai-triage-examples-not-sent-properly/401508/4 "2026-04-26T00:02:44Z")
1. Which LLM are you using?
2. Those examples are incorrect. They are sent as previous turns before your message, so they need to mimic the exact expected LLM response. If the example is from a situation where you want a tool call, then the response should mimic a tool call from the LLM. That said, your use case is so simple that any current LLM should be able to one-shot it without examples, just with a clear prompt saying when to call the tool.
---
### Author:  [@markschmucker](https://meta.discourse.org/u/markschmucker)
#### Post date: [April 26, 2026, 12:29am UTC](https://meta.discourse.org/t/ai-triage-examples-not-sent-properly/401508/5 "2026-04-26T00:29:14Z")
I’m using Sonnet 4.5, which I agree should not need examples for this simple case. But for more complex cases, how do I “mimic a tool call from the LLM”? What should I type in the example boxes? Are there example examples somewhere?