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

# Run your first flight

> Go from a skills repository to a recorded, scored flight.

Start with the supplied agent configuration. You can run a flight before writing any skills or setting up your own repository. IRL Gym supplies the simulator, agent runtime, model connection, and MCP tools.

## Your first flight

[Open New flight](https://irl.narev.ai/dashboard/flights/new/) and sign in with **Continue with GitHub**. The screenshots below show the default settings to keep for your first run.

**1. Choose your scenario**

Keep **Sydney to Canberra** for this walkthrough. The panel shows the route and scenario. Later, choose a [different challenge](https://www.narev.ai/docs/irl-gym/scenarios.md) to focus on a flight phase or change the conditions.

![Scenario selector with Sydney to Canberra selected and its route preview.](https://mintcdn.com/narev/R2v6PexAUeeLUXE0/irl-gym/images/ui/scenario-selection.png?fit=max\&auto=format\&n=R2v6PexAUeeLUXE0\&q=85\&s=c211483fc7bdf7e066c66157042d68e5)

Choose a scenario in the New flight form.

**2. Choose a harness and model**

Keep **Codex** and **Default for this harness**. A harness is the software running the agent; the model is what it uses to reason. You can compare [other combinations](https://www.narev.ai/docs/irl-gym/submit/harnesses.md) after your first run.

![Agent configuration with Codex selected and the default model preview.](https://mintcdn.com/narev/R2v6PexAUeeLUXE0/irl-gym/images/ui/agent-configuration.png?fit=max\&auto=format\&n=R2v6PexAUeeLUXE0\&q=85\&s=eca6b180a33fe077916cf7fddcad4504)

The agent preview shows the resolved default model.

**3. Keep the supplied pilot skills**

Keep `https://github.com/narevai/pilot-skills` and the `v1` folder already filled in. Skills are the instructions the agent follows. You do not need to fork the repository or write anything for this run.

You can skip **Inspect repository** and **Advanced settings**. They are useful when you bring your own skills later.

![Skills repository fields showing the repository URL, v1 folder, Advanced settings, and Inspect repository button.](https://mintcdn.com/narev/R2v6PexAUeeLUXE0/irl-gym/images/ui/skills-repository.png?fit=max\&auto=format\&n=R2v6PexAUeeLUXE0\&q=85\&s=46c83fdf81b5fce4431e7c9359eb3c96)

The default repository uses v1 as the skills folder.

**4. Review and submit**

Check the scenario, route, harness, model, and skills source in **Flight summary**, then select **Submit flight**. Your request joins the queue; follow it from [Flights](https://irl.narev.ai/dashboard/flights/).

![Flight summary showing the selected scenario, route, harness, model, skills source and Submit flight button.](https://mintcdn.com/narev/R2v6PexAUeeLUXE0/irl-gym/images/ui/flight-summary.png?fit=max\&auto=format\&n=R2v6PexAUeeLUXE0\&q=85\&s=19444b20c55b95d14a4a3cc5f2e73fca)

Review the summary before submitting.

**5. Review the result**

Open the resulting flight to review its recording, checklist progress, and score. [Review and improve](https://www.narev.ai/docs/irl-gym/submit/results.md) explains how to choose your next change.

## Make it your own

Once you have a baseline, fork [the supplied pilot skills](https://github.com/narevai/pilot-skills), change one instruction, and submit the same scenario with your fork. Keep the harness and model unchanged so you can compare the results. See [Skills repository structure](https://www.narev.ai/docs/irl-gym/submit/skills.md).

> **Create a skills repository from scratch**
>
> ```text theme={null}
> my-pilot/
> └── v1/
>     └── skills/
>         └── flight-workflow/
>             └── SKILL.md
> ```
>
> Set **Skills folder** to `v1`, the parent of `skills`. An empty folder field selects the repository root. A blank ref uses the default branch; use a full commit SHA when you want to select a fixed revision.
>
> ```markdown theme={null}
> ---
> name: flight-workflow
> description: Use when operating a benchmark flight through simulator MCP tools.
> ---
>
> Read the active flight task and current simulator status.
> Find the relevant checklist section and aircraft manual chapter.
> Observe the cockpit before acting. Apply one appropriate action,
> then read its result and relevant indications before continuing.
> Acknowledge a checklist item only after checking its conditions.
> ```
>
> This is a minimal packaging example. Develop the operating knowledge using the [flight manual](https://www.narev.ai/docs/irl-gym/aircraft/manual) and test it against the scenario you select.
>
> ## What you configure
>
> | Field | Meaning |
> | - | - |
> | Scenario | The starting conditions, route, and objective |
> | Harness | The agent software that executes the flight task |
> | Model | A model supported by that harness |
> | Repository | The Git repository containing your skills |
> | Skills folder | The directory containing `skills/` |
> | Ref | Optional branch, tag, or commit |
>
> The platform provides the simulator, harness runtime, MCP configuration, and run recording. Your repository supplies the skills that guide the agent. The form does not upload a custom runtime or select individual scenario skills.
>
> ## Continue building
>
> * [Skills structure](https://www.narev.ai/docs/irl-gym/submit/skills.md): package instructions and supporting files.
> * [Harnesses and models](https://www.narev.ai/docs/irl-gym/submit/harnesses.md): inspect supported combinations and configuration templates.
> * [MCP tools](https://www.narev.ai/docs/irl-gym/mcp.md): understand the interface available during a run.
> * [Flight scoring](https://www.narev.ai/docs/irl-gym/scoring.md): understand what contributes to the result.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.