For the complete documentation index, see llms.txt. This page is also available as Markdown.

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.

1. Select

Review leaderboards and benchmarks; optionally compare candidates side-by-side.

Read

2. Instrument

Wire your code to emit traces.

Read

3. Observe

See real production behavior.

Read

4. Evaluate

Score with scorers, judges, and code graders.

Read

5. Improve

Tune prompts, judges, models. Re-run.

Read

6. Govern

Enforce gates in CI/CD and across the org.

Read

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 — pick a model

Already shipping

Observe — what's it actually doing?

Mid-build

Evaluate — score it

In production

Govern — gate it

Where to next

Last updated

Was this helpful?