Update README.md

README.md

@@ -132,13 +132,13 @@ Install our [python library](https://github.com/root-signals/rs-python-sdk):
 pip install root-signals
 ```
 
-Import our library:
+Import:
 ```python
 from root import RootSignals
 client = RootSignals()
 ```
 
-Create your custom judge with custom instructions and run evaluation:
+Create a custom evaluator powered by **Root Judge**:
 ```python
 my_custom_judge = client.evaluators.create(
     name="Political Text Evaluator",
@@ -146,7 +146,10 @@ my_custom_judge = client.evaluators.create(
     predicate="Assess if a text containts political jargon or talks about politics: {{response}}",
     model="RootJudge",
 )
+```
 
+Execute:
+```python
 result = my_custom_judge.run(
     response="A defence spending target of 3% of GDP is more likely than the 5% aim pushed by US President Donald Trump, say members of the parliamentary Defence Committee."
 )
@@ -156,8 +159,7 @@ print(result.justification)  # detailed reasoning for the score
 
 ## 3.2 Locally
 
-We recommend using [SGLang](https://github.com/sgl-project/sglang) for production use together with *xml tags* for important sections in your prompt. At least 96GB of VRAM is recommended. 
-While the model runs on 80GB VRAM the effective context size (around 7k total tokens) will be too low for evaluating most RAG inputs.
+We recommend using [SGLang](https://github.com/sgl-project/sglang) for production use-cases together with *xml tags* for important sections in your prompt. While the model can run on 80GB VRAM, we recommend at least 96GB for evaluating long-context RAG inputs.
 
 SGlang example for a single Nvidia H100 (80GB):
 ```bash