Where should the AI CoE bot jump in?

Morning! Are we still moving to the OpenAI Enterprise edition now that the dust has settled with Sam Altman? Asking because we are using the API's and see some some charges, wondering if the API calls are more cost effective on Enterprise.

We don't know how sub-agents work in the case of Claude code (whether we can override their system prompts).

I have to jump in an IM meeting, but I would love to hear thoughts about running loops in Agentic AI. I've been struggling to make it work in Cu Chulainn (it always drifts, and the Andon Corder finds a reason to shut it down after a few iterations.)

Hi Team, do we have some sort of documentation / guiding principles how to evaluate RAGs? like which where to get certain LLM keys / where to run the evaluation in infra level and how to minimize cost in the context of XO

for the LLM Keys, I'll reword that as API keys, for example we have a RAG pipeline and at the moment we're using open AI, ideally we would want to compare it with let's say using claude, grok etc

It's annoying that I can't do it all in one session, however the output is what we're looking for So... I wonder if we can have a GPT action that calls Claude to do the work Or maybe do it with Zapier

Does anyone know if Claude has GPT creation capabilities similar to OpenAI?

Does anyone have Claude API access? I requested but looks like there's a waiting list

Sounds really great for large complex tasks. Being able to develop code and only having to intervene every 30m rather than 5m would be a game changer. I'd love a followup showing how to integrate this technique with a developer workflow. e.g. can we trigger it from Windsurf or Aider or similar? Can we intercept and upgrade LLM calls using LiteLLM?

self hosting fur lanfuse deployment look cumbersome to me

@Jamie Sidey is there a way to auto-label beyond based on sender? Sometimes I want to match subject or body phrases instead.

I've been working with the STL dEP application suite. I loaded the collateral we have from a marketing perspective but need to add some additional detail and add competitor information. Also need to refine the prompts.

Which GPT is best for OCR?

@Stanislav Huseletov I need a little with MCP for a potential deal.

Cursor be heavy on my M4 Pro

Hello Team, Any recommendation for prompt. tracing tool for agents built using Langgraph ? My best find is : Self hosted LangFuse.

When I finished conversational prompting GPT lied to me and said it could not generate images 😱

Just off the back of 2 RFP completions with a couple of thousand questions, an Enterprise Custom GPT RFP Responder trained on our product docs and existing responses will be an epic timesaver.

Pls send me the collateral and prior high quality submissions and I’ll spin it up.

It would go through gpt4 enterprise that has data privacy protections. But take a look and let me know if any concerns. .

To the BU product folks here -- Can this accelerate our implementation of AI co-pilots into our roadmaps? https://github.com/openchatai/OpenCopilot [Edit] Also... just seeing this one from Jamie too: https://www.commandbar.com/

Yeah... been trying to figure out how to have GPT do multiple analysis passes on the content it creates, and I think this is how to do it... Otherwise it gets lost when you ask it to refer to work earlier in the conversation It's fascinating digging into this stuff... 🙂

I sent Dragos a note and looped you in. I think the new stuff not live yet are the ones I tried yesterday. Was still async, but using AI to grade the written responses.

-- Ugh OpenAI having lots of issues right now anyway. Will try again tomorrow.