.Net Better repeatability for Agent KernelExample #72 (Example72_AgentCollaboration) - #4314

…tCollaboration) (microsoft#4314)

### Motivation and Context

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->

`Example72_AgentCollaboration.RunAsPluginsAsync()` prefered to execute
as a non-terminating loop since the instruction to the art-director
emphasized finding a critique as the overall goal (as opposed to
approving copy).

### Description

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

- Tuned prompt for art-director agent and verified with multiple runs.
- Added comment to that either example has an off-chance to not reach
agreement
- Tracking further improvements:
microsoft#4313

> Note: `Example72_AgentCollaboration.RunAsPluginsAsync()` tends to be
more iterative than
`Example72_AgentCollaboration.RunCollaborationAsync()`

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [x] The code builds clean without any errors or warnings
- [x] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [x] All unit tests pass, and I have added new tests where possible
- [x] I didn't break anyone 😄

---------

Co-authored-by: Gil LaHaye <[email protected]>