# Getting started

Welcome. This section gets you from "I just heard of LayerLens Stratix" to "I have a real evaluation running against my data" — fast. The page you're on is a launchpad; the links below are the actual ride.

{% hint style="warning" %}
**Hit an error already?** Skip ahead to [Common first-day errors](/2.-get-started/first-day-errors.md) — install, auth, env-var, and network problems most people see in their first hour, with fixes.
{% endhint %}

## Fastest path: 5 minutes to a real score

If you have a Python environment and 5 minutes, do this first. One file, copy-paste-runnable, ends with a real accuracy number and a UI link.

<table data-view="cards"><thead><tr><th></th><th></th><th></th></tr></thead><tbody><tr><td><strong>Run your first evaluation in 5 minutes</strong></td><td>One Python script. Install, auth, fetch a model, fetch a benchmark, run, inspect results.</td><td><a href="https://github.com/LayerLens/gitbook-full/blob/main/02-get-started/first-eval-5-minutes.md">Start</a></td></tr></tbody></table>

Did the 5-minute run. Now what?

<table data-view="cards"><thead><tr><th></th><th></th><th></th></tr></thead><tbody><tr><td><strong>Top 5 starter recipes</strong></td><td>The five highest-ROI cookbook recipes for week one — one per workflow stage.</td><td><a href="https://github.com/LayerLens/gitbook-full/blob/main/02-get-started/top-5-starter-recipes.md">Open</a></td></tr><tr><td><strong>Choose your path</strong></td><td>Match your role and goal to the right entry point: Public, Premium, or SDK.</td><td><a href="/pages/iioJDEvwiFw4zdsLvNpX">Open</a></td></tr></tbody></table>

## Prefer to start in the UI?

Not everyone wants to start in Python. Three browser-first entry points — pick whichever matches what you're trying to learn.

<table data-view="cards"><thead><tr><th></th><th></th><th></th></tr></thead><tbody><tr><td><strong>Stratix Public</strong></td><td>Browse models, compare them, read benchmark scores. No account needed.</td><td><a href="/pages/6PYqmCXsHcpi0rsPNBXj">Browse</a></td></tr><tr><td><strong>Stratix Premium</strong></td><td>Sign up, run your first private evaluation, build a judge in the UI.</td><td><a href="/pages/zoPqH5589MtPxr7v3BOC">Sign up</a></td></tr><tr><td><strong>Python SDK</strong></td><td><code>pip install layerlens --extra-index-url https://sdk.layerlens.ai/package</code> and run an eval from code.</td><td><a href="/pages/Hu2wOkBH4mpbbzD4ANEG">Install</a></td></tr></tbody></table>

Most teams use all three together. A typical first day: **Public** to shortlist candidate models, **Premium** to run a private eval on your data, **SDK** to wire the winner into CI.

## Browse by depth

Once you've run your first eval, dig into whichever shape of content matches how you learn.

| Format        | When to use it                                                             | Index                                                           |
| ------------- | -------------------------------------------------------------------------- | --------------------------------------------------------------- |
| **Tutorials** | Guided, end-to-end, sequenced. Take an evening, finish a working pipeline. | [All tutorials](/2.-get-started/all-tutorials.md)               |
| **Cookbook**  | Problem-shaped recipes. "I have task X, give me code."                     | [All cookbook recipes](/2.-get-started/all-cookbook-recipes.md) |
| **Guides**    | Task-oriented walkthroughs. Bigger than a recipe, smaller than a tutorial. | [All guides](/2.-get-started/all-guides.md)                     |

## The workflow under the hood

Everything in Stratix maps to five stages. Knowing the stage helps you find the right doc fast.

| Stage        | What you're doing                                     | Where it lives                                            |
| ------------ | ----------------------------------------------------- | --------------------------------------------------------- |
| **Select**   | Pick models, benchmarks, datasets to evaluate against | [§5 Select](/5.-select-pick-the-model/workflow.md)        |
| **Build**    | Instrument your code so Stratix can see what it does  | [§6 Build](/6.-build-wire-your-code/workflow.md)          |
| **Observe**  | Capture traces, route them to where they're scored    | [§7 Observe](/7.-observe-see-whats-happening/workflow.md) |
| **Evaluate** | Score runs with judges and code graders               | [§8 Evaluate](/8.-evaluate-score-the-outputs/workflow.md) |
| **Improve**  | Optimize judges, cut cost, regression-protect         | [§9 Improve](/9.-improve-tune-the-system/workflow.md)     |

See [The Stratix workflow](/1.-introduction/the-stratix-workflow.md) for the full picture.

## When something breaks

* [Common first-day errors](/2.-get-started/first-day-errors.md) — auth, install, network, env-var problems.
* [SDK troubleshooting](https://github.com/LayerLens/gitbook-full/blob/main/13-reference/sdk-python/troubleshooting.md) — deeper SDK-specific issues.
* [Support](/12.-support/contact.md) — how to reach a human.
* [Status page](https://status.layerlens.ai) — is it us or you?

## Where to next

The honest answer depends on what you're trying to do. If you're not sure:

1. Run [Your first evaluation in 5 minutes](https://github.com/LayerLens/gitbook-full/blob/main/02-get-started/first-eval-5-minutes.md).
2. Pick one of the [Top 5 starter recipes](https://github.com/LayerLens/gitbook-full/blob/main/02-get-started/top-5-starter-recipes.md) that matches a real problem you have.
3. When you hit something specific you need to learn, return to [All tutorials](/2.-get-started/all-tutorials.md) / [All cookbook recipes](/2.-get-started/all-cookbook-recipes.md) / [All guides](/2.-get-started/all-guides.md).


---

# 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.layerlens.ai/2.-get-started/02-get-started.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.