> For the complete documentation index, see [llms.txt](https://docs.layerlens.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.layerlens.ai/1.-introduction/the-stratix-workflow.md).

# The Stratix Workflow — the six intents

The Stratix Workflow — six stages from picking a model to governing it in production.

Six stages from "I need to pick a model" to "this AI is governed in production." Every concept, how-to, tutorial, and recipe in these docs maps to one of them.

<table data-view="cards"><thead><tr><th></th><th></th><th></th></tr></thead><tbody><tr><td><strong>1. Select</strong></td><td>Review leaderboards and benchmarks; optionally compare candidates side-by-side.</td><td><a href="/5.-select-pick-the-model/workflow.md">Read</a></td></tr><tr><td><strong>2. Instrument</strong></td><td>Wire your code to emit traces.</td><td><a href="/6.-build-wire-your-code/workflow.md">Read</a></td></tr><tr><td><strong>3. Observe</strong></td><td>See real production behavior.</td><td><a href="/7.-observe-see-whats-happening/workflow.md">Read</a></td></tr><tr><td><strong>4. Evaluate</strong></td><td>Score with scorers, judges, and code graders.</td><td><a href="/8.-evaluate-score-the-outputs/workflow.md">Read</a></td></tr><tr><td><strong>5. Improve</strong></td><td>Tune prompts, judges, models. Re-run.</td><td><a href="/9.-improve-tune-the-system/workflow.md">Read</a></td></tr><tr><td><strong>6. Govern</strong></td><td>Enforce gates in CI/CD and across the org.</td><td><a href="/11.-admin/11-admin.md">Read</a></td></tr></tbody></table>

## Why a workflow spine

Without a spine, evaluation is a grab-bag of features. With a spine:

* Each stage has a clear question it answers
* The path from "picking a model" to "shipping confidently" is named
* Documentation links naturally between stages

## How the stages relate

The stages aren't strictly sequential; they're a cycle. Your AI is always at some stage, and the cycle goes around as it matures:

```
Select → Build → Observe → Evaluate → Improve → Govern
 ↑
 └─ back to Observe
```

The exception: **Select** can also reappear mid-cycle when a new model generation drops or your evaluation surfaces a model that's outgrown its envelope. Returning to Select means re-running the side-by-side and confirming your incumbent is still the right choice.

## Pick a starting stage

| If you're...             | Start at                                                                       |
| ------------------------ | ------------------------------------------------------------------------------ |
| Thinking about adding AI | [Select](/9.-improve-tune-the-system/workflow.md) — pick a model               |
| Already shipping         | [Observe](/9.-improve-tune-the-system/workflow.md) — what's it actually doing? |
| Mid-build                | [Evaluate](/9.-improve-tune-the-system/workflow.md) — score it                 |
| In production            | [Govern](/9.-improve-tune-the-system/workflow.md) — gate it                    |

## Where to next

* [Select](/9.-improve-tune-the-system/workflow.md)
* [Concepts](/13.3-concepts-library-+-architecture/concepts-library.md)
* [Tutorials](/2.-get-started/all-tutorials.md)