# Observability for Discourse AI

**URL:** <https://meta.discourse.org/t/observability-for-discourse-ai/316107>\
**Category:** Feature\
**Tags:** ai, ai-bot\
**Created:** [July 12, 2024, 4:00pm UTC](https://meta.discourse.org/t/observability-for-discourse-ai/316107 "2024-07-12T16:00:12Z")\
**Posts on this page:** 1\
**Showing post:** 1

<div class="post-metadata">

**Author:** ![aas](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/aas/32/289331_2.png) [@aas](https://meta.discourse.org/u/aas)\
**Post date:** [July 12, 2024, 4:00pm UTC](https://meta.discourse.org/t/observability-for-discourse-ai/316107/1 "2024-07-12T16:00:12Z")

</div>

Monitoring and evaluating LLMs is critical:

> I started working with language models five years ago when I led the team that created CodeSearchNet, a precursor to GitHub CoPilot. Since then, I’ve seen many successful and unsuccessful approaches to building LLM products. I’ve found that unsuccessful products almost always share a common root cause: a failure to create robust evaluation systems.

> **[Your AI Product Needs Evals –](https://hamel.dev/blog/posts/evals/)**
>
> How to construct domain-specific LLM evaluation systems.

If Discourse AI is to power business-critical LLM tasks, I think supporting monitoring tools like [LangSmith](https://docs.smith.langchain.com/) should be prioritized.

Using LangSmith is as simple as running `yarn add langchain langsmith` and adding a few environment variables.

Has team Discourse thought about how we can configure LLM tracing? Also, any thoughts on how we can implement this prior to discourse-ai official supporting it?

---

_[View the full topic](https://meta.discourse.org/t/observability-for-discourse-ai/316107)._