davidrichards
Show HN: Zrevick – AI-native business OS for technical founders
I gave up on AI images and moved to having my agent generate html, rendering it, and then taking a snapshot in the needed size.
We tag each endpoint by category in the OpenAPI spec and require the MCP to request actions by tag and optional query term. At most we return 10 endpoints at a time and the LLM can request more using pagination.
These tags also create your categories in API doc websites like swagger/mintlify so its a win win.
OpenAPI spec is the single source of truth.
Are others doing this?
It seemed obvious to me, but I don't hear others saying it.
I came to the realization that I needed a identity graph last week and started testing it one in Parallel AI.
We have 5 tools where customer touchpoints happen and we had to manually stitch them together for the full view.
Congratulations on the launch, ill check it out today.
White-Label AI Platform for SMB
Show HN: I built a model agnostic AI RAG app with enterprise level tools
Thank you for checking out the product! This product is great for individual makers, teams, and enterprises to create content, code, images, and more as an alternative to ChatGPT. We offer access to the latest and greatest AI models, complete data privacy ensured, and support a huge (32k, 128k, 200k) context window for all of our plans.Compared to ChatGPT, who only offers 32k context window...