# 5-minute demo

The fastest way to see Edge is the hosted demo.

→ [**demo.edge.nyami.fr**](https://demo.edge.nyami.fr)

## What you'll see

1. **Landing UI** — visual flow builder with 12 node types.
2. **Pre-seeded dataset** — a frozen golden set built from a regulatory PDF.
3. **One-click eval** — runs `answer_relevancy + faithfulness + hallucination` against a stub LLM, < 30 s.
4. **Result report** — per-item breakdown, score chart, exportable.

```mermaid
sequenceDiagram
    participant You as You (browser)
    participant UI as Edge UI
    participant API as Edge backend
    participant LLM as Stub LLM

    You->>UI: Open demo.edge.nyami.fr
    UI->>API: Load "Vacation Directive" dataset
    You->>UI: Click "Run evaluation"
    UI->>API: POST /flows/execute
    API->>LLM: 6 chat completions
    LLM-->>API: 6 responses
    API->>API: DeepEval scores (3 metrics)
    API-->>UI: Result events stream
    UI-->>You: Score chart + per-item drilldown
```

## Local quickstart instead

If you'd rather run it on your laptop:

```bash
git clone https://github.com/NKAP360-dev/edge-app.git
cd edge-app
cp .env.example .env  # set POCKETBASE_ADMIN_* at minimum
./start.sh
open http://localhost:3000
```

See [Deployment / Quickstart](/deployment/quickstart.md) for full prerequisites.

## What's faked in the public demo

The demo's LLM is a stub that returns canned answers — your real deployment routes to your own LLM gateway. The dataset is real and frozen. The metrics are real and computed locally.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.edge.nyami.fr/getting-started/demo.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.