# Get Started This guide takes you from a fresh Intel® edge system to a running QSR Store Agent. ## Prerequisites - A Linux system with an Intel® GPU that meets the [System Requirements](./get-started/system-requirements.md). - Docker Engine with the Compose plugin, Git, `make`, and Python 3. - Network access to GitHub, Docker Hub, and Hugging Face. If you are behind a proxy, see [Configuration](./get-started/configuration.md#proxy). ## Step 1: Get the Code ```bash git clone https://github.com/intel-retail/qsr-agent.git cd qsr-agent ``` ## Step 2: Download the Model ```bash make download-models ``` This downloads the model set by `MODEL_ID` in `.env.example` (default `OpenVINO/Qwen3-30B-A3B-Instruct-2507-int4-ov`, about 16 GB) into `./models`. The download is skipped if the model is already present. ## Step 3: Connect Store Services Store data comes from the store services, which run on their own hosts. Set their MCP URLs in `.env.example` before you start the agent, for example: ```bash QSR_KIOSK_MCP_URL=http://:/mcp QSR_EXTRA_NO_PROXY= ``` See [Connect Store Services](get-started/configuration.md#connect-store-services). Without service URLs the agent runs with weather only. To change the URLs later, edit `.env.example` and run `make up` again. ## Step 4: Start the Agent ```bash make up ``` `make up` checks Docker, the Intel GPU device, and the model. It then pulls the agent image and starts three containers (to run the code you cloned instead of the published image, use `make up REGISTRY=false`; see [Build from Source](./get-started/build-from-source.md)): | Container | Role | | --- | --- | | `ovms` | OpenVINO™ Model Server running the language model on the Intel® GPU | | `qsr-agent` | Operator UI and agent runtime | | `weather` | Weather service (simulated by default) | The first start loads the model onto the GPU and warms it up. This can take a few minutes. Check progress with: ```bash make status ``` The agent is ready when `qsr-agent` reports `healthy`. ## Step 5: Open the Operator UI Open `http://:8600` in a browser, or `http://localhost:8600` on the same machine. Try a few questions in **Operator Chat**: - *What is the current queue count?* - *What is the current order accuracy rate?* - *What's the weather at the store right now?* ## Step 6: Trigger an Event Change the simulated weather. This also sends a weather event to the agent: ```bash make weather CONDITION=rain TEMP=12 ``` The event appears in the **Autonomy Decisions** panel, and the agent evaluates it. If the agent proposes a change, such as taking cold drinks off the menu, select **Approve** or **Reject**. See the [Operator Guide](./operator-guide.md#review-event-decisions) for more. ## Stop the Agent ```bash make down ``` Settings, decisions, and learned behaviour are kept in Docker volumes and are restored on the next `make up`. ## Next Steps - Connect your store services: [Configuration](./get-started/configuration.md#connect-store-services). - Understand the system: [How It Works](./how-it-works.md). - Familiarise yourself with the [Operator Guide](./operator-guide.md). :::{toctree} :hidden: ./get-started/system-requirements.md ./get-started/configuration.md ./get-started/build-from-source.md :::