> ## 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.

# Optimize

> Evaluate changes against cost, quality, and successful task completion.

A cheaper model is useful only if it still completes the task. Evaluate changes to models, skills, and harnesses against successful outcomes, then compare the cost of doing the work.

**IRL Gym** gives you repeatable flight scenarios for evaluating agent behavior. A harness runs the agent, skills provide instructions, and the scenario defines its starting conditions and goal. Evaluation provides evidence for optimization; it does not guarantee lower costs.

## Run your first evaluation

You need a GitHub account. The hosted service runs the simulator and agent; you do not need to install X-Plane, start an MCP server, or supply model API keys in the flight form.

1. Open [New flight](https://irl.narev.ai/dashboard/flights/new/) and select **Continue with GitHub**.
2. Keep **Sydney to Canberra**, **Codex**, and **Default for this harness**. The form supplies the pilot skills.
3. Select **Submit flight** and follow the request in [Flights](https://irl.narev.ai/dashboard/flights/).
4. Once it finishes, review the recording and score. Treat this run as your baseline, then change a skill, model, or harness and compare results.

A completed run does not guarantee a successful landing. Inspect failures as well as scores, and use relevant spending measurements before claiming savings.

## Learn more

[Explore IRL Gym](https://www.narev.ai/docs/irl-gym/index.md) for scenarios and setup. Follow the [practical FinOps framework](https://www.narev.ai/docs/guides/finops-for-ai/index.md) to evaluate cost, quality, and latency together.


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