> ## Documentation Index
> Fetch the complete documentation index at: https://docs.slng.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Where it sits

Two boundaries define it.

**Above it:** your orchestrator. It owns the conversation, turn-taking, and session state, and it doesn't call providers directly. It calls the Execution Layer.

**Below it:** the models, both the ones SLNG runs in-region and the ones proxied to external providers.

<img src="https://mintcdn.com/slng-new-docs/fgzHSTXC7k7AhIuF/images/graph-1.png?fit=max&auto=format&n=fgzHSTXC7k7AhIuF&q=85&s=ab0a54c3e73867e58e64ffd9ebdeb1b6" alt="Graph 1" title="Graph 1" className="mx-auto" style={{ width:"49%" }} width="1248" height="544" data-path="images/graph-1.png" />

The layer occupies the space in between, and improves the 3 model steps. Your orchestrator asks for a transcript, asks for a response, asks for audio. What runs between the asking and the answering is the Execution Layer, and it can change entirely without your orchestrator noticing.

It runs in-region across [SLNG regions](/guides/regions/regions-map), next to the models it's routing to. That's not incidental. It is done so that there's no hop, which means no data residency