# All guides Guides sit between recipes and tutorials in shape. Use a guide when you have a clear goal that's larger than a copy-paste recipe but doesn't need a full guided learning sequence. Organized below by [workflow stage](/1.-introduction/the-stratix-workflow.md) — **Select**, **Build**, **Observe**, **Evaluate**, **Improve** — plus operational concerns (admin, migration) at the bottom. ## Select Pick and prepare what you'll evaluate against. ### BYOK models * [Register a BYOK custom model](https://github.com/LayerLens/gitbook-full/blob/main/05-select/guides/register-byok-model.md) * [Test a BYOK endpoint](https://github.com/LayerLens/gitbook-full/blob/main/05-select/guides/test-byok-endpoint.md) * [Rotate a BYOK API key](https://github.com/LayerLens/gitbook-full/blob/main/05-select/guides/rotate-byok-key.md) ### Benchmarks and datasets * [Upload a private benchmark](https://github.com/LayerLens/gitbook-full/blob/main/05-select/guides/upload-benchmark.md) * [Refresh a benchmark with new data](https://github.com/LayerLens/gitbook-full/blob/main/05-select/guides/refresh-benchmark.md) ## Build Wire Stratix into your code and CI. ### Trace ingestion * [Set up trace ingestion](https://github.com/LayerLens/gitbook-full/blob/main/06-build/guides/setup-trace-ingestion.md) ### Calling Stratix from your stack * [Calling Stratix from a backend](https://github.com/LayerLens/gitbook-full/blob/main/06-build/guides/calling-stratix-from-a-backend.md) * [Pattern: calling Stratix from Next.js](https://github.com/LayerLens/gitbook-full/blob/main/06-build/guides/pattern-from-nextjs.md) ### CI / quality gates * [Wire CI/CD evaluation gates](https://github.com/LayerLens/gitbook-full/blob/main/06-build/guides/wire-cicd-gates.md) * [Set per-feature quality tolerances](https://github.com/LayerLens/gitbook-full/blob/main/06-build/guides/per-feature-tolerances.md) * [Investigate a regression in CI](https://github.com/LayerLens/gitbook-full/blob/main/06-build/guides/investigate-ci-regression.md) ## Observe Run continuous evaluation over what's already happening. * [Build a trace set for agentic evals](https://github.com/LayerLens/gitbook-full/blob/main/07-observe/guides/build-trace-set.md) * [Schedule continuous trace evaluation](https://github.com/LayerLens/gitbook-full/blob/main/07-observe/guides/schedule-continuous.md) * [Investigate a failing trace](https://github.com/LayerLens/gitbook-full/blob/main/07-observe/guides/investigate-failing-trace.md) ## Evaluate Build, standardize, and harden your scoring library. * [Bootstrap judges from real traces](https://github.com/LayerLens/gitbook-full/blob/main/08-evaluate/guides/bootstrap-judges.md) * [Build your judge library](https://github.com/LayerLens/gitbook-full/blob/main/08-evaluate/guides/build-judge-library.md) * [Standardize judges across teams](https://github.com/LayerLens/gitbook-full/blob/main/08-evaluate/guides/standardize-judges.md) * [Author a custom code grader](https://github.com/LayerLens/gitbook-full/blob/main/08-evaluate/guides/custom-code-scorer.md) * [Detect and remove flaky scorers](https://github.com/LayerLens/gitbook-full/blob/main/08-evaluate/guides/remove-flaky-scorers.md) ## Improve Optimize judges, cut cost, keep regressions out. * [Optimize a judge with GEPA](https://github.com/LayerLens/gitbook-full/blob/main/09-improve/guides/optimize-judge-gepa.md) * [Curate a regression test set](https://github.com/LayerLens/gitbook-full/blob/main/09-improve/guides/curate-regression-set.md) * [Reduce eval cost without losing signal](https://github.com/LayerLens/gitbook-full/blob/main/09-improve/guides/reduce-eval-cost.md) * [Cost-control levers](https://github.com/LayerLens/gitbook-full/blob/main/09-improve/guides/cost-control-levers.md) ## Admin and operations Day-two work — orgs, teams, billing, security, notifications. ### Setup and onboarding * [Set up your first organization](/11.-admin/setup-first-org.md) * [Invite your team](/11.-admin/invite-team.md) * [Set up SSO](/11.-admin/setup-sso.md) * [Manage seats and roles](/11.-admin/manage-seats-roles.md) ### Billing * [Buy and manage ECU](/11.-admin/manage-ecu.md) ### Keys * [Rotate an API key](/11.-admin/rotate-api-key.md) ### Notifications and audit * [Set up notifications and alerting](/11.-admin/setup-notifications.md) * [Set up Slack integration](/11.-admin/setup-slack.md) * [Audit-friendly release evidence](/11.-admin/audit-friendly-evidence.md) ## Migration Coming from another evaluation platform. * [Plan a migration to Stratix](https://github.com/LayerLens/gitbook-full/blob/main/06-build/migration/guides/plan-migration.md) * [Run Stratix and another tool side-by-side during migration](https://github.com/LayerLens/gitbook-full/blob/main/06-build/migration/guides/dual-run-migration.md) ## Where to next * [All tutorials](/2.-get-started/all-tutorials.md) — guided, end-to-end learning paths * [All cookbook recipes](/2.-get-started/all-cookbook-recipes.md) — copy-paste snippets by problem * [Top 5 starter recipes](https://github.com/LayerLens/gitbook-full/blob/main/02-get-started/top-5-starter-recipes.md) — the curated week-one subset * [Common first-day errors](/2.-get-started/first-day-errors.md) — when something doesn't work --- # 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/all-guides.md?ask= ``` 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.