Update organization card: inference provider description

README.md

@@ -7,4 +7,31 @@ sdk: static
 pinned: false
 ---
 
-Edit this `README.md` markdown file to author your organization card.
+# IntelCS-AI
+
+We run an **inference provider** on the Hugging Face Inference Providers
+platform: open-weight models served on rented GPU capacity, sold at
+marketplace prices.
+
+## What we offer
+
+- **OpenAI-compatible endpoints** (`/v1/chat/completions`, `/v1/models`)
+  behind the HF Inference Providers API.
+- **Tool calling** (function calling) and **structured output**
+  (`response_format: json_schema`) support.
+- **Low-latency serving**: time-to-first-token well under the 5 s budget
+  (measured ~0.9 s non-streaming).
+- **Autoscaling fleet**: capacity scales out automatically with demand;
+  routing, metering, and billing run on edge infrastructure.
+
+## Currently serving
+
+| Model | Notes |
+|---|---|
+| `google/gemma-3-4b-it` | 131K context, tool calling, JSON schema output |
+
+Model lineup rotates as we add capacity — watch this space.
+
+## Links
+
+- Website: [intelcs.ai](https://intelcs.ai)