microsoft / microsoft/semantic-kernel
.Net: Missing guidance on GenAIOps (LLMOps) with Semantic Kernel / especially in the area of .NET + experimentation and evaluation
Nobody has claimed this yet.
- Dominant language
- C#
- Stars
- 28.6k
- Forks
- 4.8k
- Avg merge
- 14h 13m
- Merged PRs (30d)
- 18
Description
Discussed in https://github.com/microsoft/semantic-kernel/discussions/10022
Originally posted by RicardoNiepel December 20, 2024
This discussion adds to #10007 with additional dimensions.
Looking into Microsoft's current strategy for GenAIOps (LLMOps) Prompt Flow as part of AI Studio and Azure Machine Learning is always used as a solution (1 & 2)
But concrete guidance is missing:
- How to do GenAIOps with Semantic Kernel Agent Framework
- especially how to do prompt experimentation and evaluation when using Agent Collaboration with AgentChat is not available
- How to do GenAIOps when using DotNet with Semantic Kernel, as Promptflow lags .NET support #1317
Any PG insights, community input or references are welcome.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with discussion #10022 and the related issue #10007, then review the linked Azure Machine Learning Prompt Flow guidance and templates. Document concrete GenAIOps guidance for Semantic Kernel Agent Framework and .NET, including prompt experimentation and evaluation when AgentChat is unavailable; account for the referenced Prompt Flow .NET support limitation in issue #1317.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- azure, csharp
- Domain
- ai, documentation, machine-learning
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100