Updates per DSB team to replace metaprompt

[aprilgittens]

The DSB team provided proposed edits to align with terminology Microsoft uses for system messaging for the Building Trustworthy AI Agents lesson. The proposed edits remove any mentions of meta prompting and replaces that with “system messaging” as the preferred terminology we use externally.

There is a separate request for an update to the image provided in the Building Trustworthy AI Agents lesson. I'll follow up with Korey/Lee separately on Teams for that request as I do not have access to the original image file.

[github-actions[bot]]

👋 Thanks for contributing @aprilspeight! We will review the pull request and get back to you soon.

[koreyspace]

Hi @aprilspeight thanks for the review. I think there is some contextual things to consider here when talking about Agents. The "metaprompt" described here is not exactly direct replacement to "system messaging". In this context, this is to design a system to scale writing prompts for multiple agents and using the LLM to reflect and improve your intial prompts to be agent focused.

System messaging "is a feature-specific set of instructions or contextual frameworks given to a generative AI model (for example, GPT4-o, GPT3.5 Turbo, etc.) to direct and improve the quality and safety of a model’s output." This would be focused on designing guardrails for an LLM (or one agent)

I believe replacing these terms will confuse learners as they are not the same thing.

https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/system-message?tabs=top-techniques https://blog.langchain.dev/exploring-prompt-optimization/

[aprilgittens]

@koreyspace I’ll pass this feedback to the DSB team.