# Hello, world: an assistant that will not say hello: an example
> One line in the conversation changes what the assistant does, from the next message on. Try it in Claude or ChatGPT in your browser, in 2 minutes: ask, paste one line, ask again, then a new chat with the line first.
*Source: · site v0.2.5 (2026-10-21) · this file is generated from the same content as the page, so the two cannot drift. Every page on this site has a `.md` twin; internal links below point at them.*
---
Example 1 of 6 · the first one · 2 minutes · version 1.0.0 · this page costs 50p read to the end
# Hello, world: an assistant that will not say hello
One line in the conversation changes what the assistant does, from the next message on.
**You need:** Nothing but Claude or ChatGPT in your browser.
1. 1**Ask**Ask for it. The assistant does it.
2. 2**Add the line**Paste the line, ask again. It refuses.
3. 3**New chat**A new chat, the line first. It refuses from the start.
Hello, worldClaudeChatGPT
1. 1 · Ask for it. No behaviour policy yet.
2. Say hello to me.
3. Hello! Good to meet you. What can I help you with today?
4. 2 · Paste the line, then ask again.
5. Behaviour policy for this chat: you must never write the word "hello", in any language, spelling or case. If I ask you to, tell me that a behaviour policy rules it out.
6. Understood. For the rest of this chat I won't write that word, and if you ask me to, I'll tell you why.
7. Say hello to me.
8. I can't: a behaviour policy in this chat rules that word out. Good to see you, though. What can I do for you?
9. 3 · A new chat. The line goes first.
10. New chat
11. Behaviour policy for this chat: you must never write the word "hello", in any language, spelling or case. If I ask you to, tell me that a behaviour policy rules it out. Say hello to me.
12. I can't write that word here: your behaviour policy rules it out. Glad you're here, though.
Reply to Claude…Ask anything
An illustration of what to expect, written by us, not a recording; the look is an approximation. Your assistant may answer differently: try it, and tell us below.
### Try it yourself
[Open Claude in a new tab ↗](https://claude.ai/new) [Open ChatGPT in a new tab ↗](https://chatgpt.com/)
If your browser opens a window instead, it may be behind this one.
1. **Ask.** Watch it do it.
```
Say hello to me.
```
Copy
2. **Paste the line, the behaviour policy,** then ask:
```
Behaviour policy for this chat: you must never write the word "hello", in any language, spelling or case. If I ask you to, tell me that a behaviour policy rules it out.
```
Copy
```
Say hello to me.
```
Copy
3. **Start a new chat** and paste this, all of it, as the first message:
```
Behaviour policy for this chat: you must never write the word "hello", in any language, spelling or case. If I ask you to, tell me that a behaviour policy rules it out.
Say hello to me.
```
Copy
## What to look for
The loophole. Some replies say "Hi!" instead: the line named a word, not a greeting. Most of the work of a behaviour policy is saying what you mean.
## Keep it
The line lasts as long as the chat. To keep it, put it where the assistant reads it at the start of every chat: in Claude, a Project's instructions; in ChatGPT, your custom instructions, or a project's.
## What a line is, and what it is not
The assistant follows the line because it chooses to. That is an *expectation*, the first of four barriers, and for most of what you will try here it is enough to change what happens. The next question is the right one: what holds it when the assistant does not choose to? [What an Agent Behaviour Policy is](/what-is-an-abp/index.md) takes it from there.
### Tell us about this example
Five taps and a line, if you have one. The point is for you to be surprised, so tell us if you were not. Your answers stay in this browser until you send them; when you do, they are encrypted here, before they leave, and only RiskMandate can read them.
Did you get it?
YesPartlyNo
Did you learn something new?
YesA littleNo
Were you surprised?
YesA littleNo
When you tried it, did it go as shown?
YesDifferentlyNoNot tried yet
How good was this example?
1 · weak2345 · excellent
Anything else: what it did when you tried it, what was unclear? Exactly what will be sent
```
```
Encrypt and send to the agentCopy my answers[How this works](/feedback/how-sending-works/index.md)
[Send it by email instead](mailto:agent@riskmandate.ai?subject=Example%20hello-world%20v1.0.0)
## Versions of this example
| Version | Date | What changed |
|---|---|---|
| 1.0.0 | 2026-10-21 | First version. |
Next: [Stay on topic: an assistant that only talks about cooking](/examples/stay-on-topic/index.md). All of them: [the examples](/examples/index.md).
---
*[Site index for agents](/llms.txt) · [What exists](/docs/reality.md) · [HTML version](https://customers.riskmandate.ai/examples/hello-world/)*