# Documentation

## Docs

- [LayerLens Stratix Documentation](https://docs.layerlens.ai/readme.md): Welcome to LayerLens Stratix documentation. Three customer-facing experiences, one platform — pick a path and ship faster.
- [Quickstart](https://docs.layerlens.ai/quickstart.md): 5-minute quickstart — pick a path and ship.
- [Glossary](https://docs.layerlens.ai/glossary.md): Definitions for every Stratix term — models, evaluations, judges, scorers, traces, and more.
- [Search & Persona Index](https://docs.layerlens.ai/search-index.md): Persona and goal index — find the right page in seconds.
- [What is LayerLens Stratix?](https://docs.layerlens.ai/1.-introduction/what-is-layerlens-stratix.md): LayerLens Stratix is the AI evaluation platform — public catalog, private workspace, and SDK.
- [Overview](https://docs.layerlens.ai/1.-introduction/01-introduction.md): Overview of LayerLens Stratix — three experiences, the workflow spine, what's in the platform.
- [Why evaluate?](https://docs.layerlens.ai/1.-introduction/why-evaluate.md): Why AI teams need evaluation discipline — the cost of shipping unmeasured AI.
- [Personas and paths](https://docs.layerlens.ai/1.-introduction/personas-paths.md): Five personas, five paths — Builder, Operator, Researcher, Admin, Buyer.
- [Three experiences (Public · Premium · SDK)](https://docs.layerlens.ai/1.-introduction/three-experiences.md): Stratix Public, Stratix Premium, and the Python SDK — what each one is for and how they work together.
- [Public vs Premium — by user intent](https://docs.layerlens.ai/1.-introduction/public-vs-premium-by-intent.md): Public vs Premium organized by user intent — Select, Build / Instrument, Observe, Evaluate, Improve, Govern.
- [The Stratix Workflow — the six intents](https://docs.layerlens.ai/1.-introduction/the-stratix-workflow.md): The Stratix Workflow — six stages from picking a model to governing it in production.
- [How Stratix compares](https://docs.layerlens.ai/1.-introduction/how-stratix-compares.md): Stratix vs Braintrust, LangSmith, Galileo, Promptfoo, Arize — the short version.
- [Deep comparison](https://docs.layerlens.ai/1.-introduction/how-stratix-compares-deep.md): Stratix vs Braintrust, LangSmith, Galileo, Promptfoo, Arize — feature-by-feature comparison.
- [Brand assets](https://docs.layerlens.ai/more-in-this-section/brand-assets.md): Brand assets, product names, voice, and boilerplate for partners and press covering LayerLens Stratix.
- [Schedule a demo](https://docs.layerlens.ai/more-in-this-section/schedule-a-demo.md): Book a 30-minute LayerLens Stratix walk-through, or start in the product today — for free.
- [Trust and security](https://docs.layerlens.ai/more-in-this-section/trust.md): Trust, security, and compliance posture for LayerLens Stratix — encryption, tenancy, audit, and how buyers run a security review.
- [Getting started](https://docs.layerlens.ai/2.-get-started/02-get-started.md): Getting started with LayerLens Stratix — go from zero to your first evaluation, or pick the entry point that fits your role.
- [Choose your path](https://docs.layerlens.ai/2.-get-started/choose-your-path.md): Pick the Stratix entry point that fits what you're trying to do.
- [First-day errors](https://docs.layerlens.ai/2.-get-started/first-day-errors.md): First-day errors — the auth, install, and network problems most people hit on day 1, with fixes.
- [Stratix Public — anonymous browsing](https://docs.layerlens.ai/2.-get-started/public.md): Stratix Public quickstart — browse, compare, test your AI without signup.
- [Browse models](https://docs.layerlens.ai/2.-get-started/browse-models.md): Browse the public Stratix catalog of 175+ models, filter by provider, capability, and licensing.
- [Compare two models](https://docs.layerlens.ai/2.-get-started/compare-two-models.md): Compare any two models head-to-head across a shared benchmark — no signup needed.
- [Browse benchmarks](https://docs.layerlens.ai/2.-get-started/browse-benchmarks.md): Browse 52+ public benchmarks with descriptions, methodology, and per-model scores.
- [Test your AI](https://docs.layerlens.ai/2.-get-started/test-your-ai.md): Test a model on a prompt anonymously — no signup required.
- [Stratix Premium — logged-in workspace](https://docs.layerlens.ai/2.-get-started/premium.md): Stratix Premium quickstart — sign up, run your first evaluation, build your first judge.
- [Sign up](https://docs.layerlens.ai/2.-get-started/sign-up.md): Create a Stratix Premium account with GitHub, Google, or email — no card required for Free.
- [Personalized onboarding](https://docs.layerlens.ai/2.-get-started/personalized-onboarding.md): Use the Stratix Premium onboarding wizard to tailor your workspace to your role and goals.
- [Your first evaluation](https://docs.layerlens.ai/2.-get-started/first-evaluation.md): Run your first private evaluation in Stratix Premium — pick a model, pick a dataset, see scores in minutes.
- [Your first trace](https://docs.layerlens.ai/2.-get-started/first-trace.md): Upload a trace to Stratix Premium and inspect it — see every span, every cost, every error.
- [Your first judge](https://docs.layerlens.ai/2.-get-started/first-judge.md): Build your first LLM judge in Stratix Premium — define a rubric, test it, optionally GEPA-optimize.
- [SDK](https://docs.layerlens.ai/2.-get-started/sdk.md): Stratix Python SDK quickstart — install, authenticate, run an evaluation in code.
- [Install](https://docs.layerlens.ai/2.-get-started/install.md): Install the Stratix Python SDK from the LayerLens package registry.
- [First evaluation via SDK](https://docs.layerlens.ai/2.-get-started/first-eval-via-sdk.md): Run your first benchmark evaluation programmatically via the Stratix Python SDK.
- [All tutorials](https://docs.layerlens.ai/2.-get-started/all-tutorials.md): Every Stratix tutorial — guided, end-to-end walkthroughs organized by workflow stage.
- [All cookbook recipes](https://docs.layerlens.ai/2.-get-started/all-cookbook-recipes.md): Every Stratix cookbook recipe — runnable snippets organized by the workflow stage they belong to.
- [All guides](https://docs.layerlens.ai/2.-get-started/all-guides.md): Every Stratix guide — task-oriented walkthroughs across the platform, organized by workflow stage and operational concern.
- [Samples (70+ runnable)](https://docs.layerlens.ai/2.-get-started/samples-overview.md): Stratix Python SDK samples — categorized index of the runnable samples that ship with the SDK.
- [Run your first evaluation in 5 minutes](https://docs.layerlens.ai/more-in-this-section-1/first-eval-5-minutes.md): Run your first Stratix evaluation end-to-end in five minutes. One Python file, copy-paste-runnable.
- [Top 5 starter recipes](https://docs.layerlens.ai/more-in-this-section-1/top-5-starter-recipes.md): Five starter cookbook recipes hand-picked for new Stratix users. Cover the full Build → Observe → Evaluate → Improve arc in your first week.
- [Pricing — overview](https://docs.layerlens.ai/3.-pricing/03-pricing.md): Pricing for LayerLens Stratix — Free, Premium PAYG, Enterprise.
- [Free tier details](https://docs.layerlens.ai/3.-pricing/free-tier-details.md): What's in the Stratix Free tier — Stratix Public, a Premium account, and starter ECU credits.
- [Premium tier details](https://docs.layerlens.ai/3.-pricing/premium-tier-details.md): What's in Stratix Premium PAYG — multi-org, BYOK, agentic evals, GEPA, traces, priority support.
- [Enterprise tier details](https://docs.layerlens.ai/3.-pricing/enterprise-tier-details.md): What's in the Stratix Enterprise tier — SSO, data residency,, dedicated CSM.
- [Pricing tiers — quick overview](https://docs.layerlens.ai/3.-pricing/pricing-tiers-overview.md): Free, Premium, Enterprise — the short version of what each tier includes.
- [Use cases](https://docs.layerlens.ai/4.1-general-use-cases/general.md): Concrete ways teams use Stratix — model evaluation, agentic eval, RAG, CI/CD gates, continuous eval.
- [Model evaluation](https://docs.layerlens.ai/4.1-general-use-cases/model-evaluation.md): Pick the right model for a task by running it against the right benchmark.
- [Benchmark-driven development](https://docs.layerlens.ai/4.1-general-use-cases/benchmark-driven-development.md): Make benchmarks a first-class signal in your dev loop — every change runs against a benchmark, every result is on the dashboard.
- [Agentic evaluation](https://docs.layerlens.ai/4.1-general-use-cases/agentic-evaluation.md): Pre- and post-deployment quality gates for multi-step agents — combine assertions, deterministic rules, and LLM judges.
- [Agentic evaluations — overview](https://docs.layerlens.ai/4.1-general-use-cases/agentic-evals-overview.md): Pre- and post-deployment quality gates for multi-step AI agents — assertions, deterministic rules, and LLM judges.
- [Continuous evaluation](https://docs.layerlens.ai/4.1-general-use-cases/continuous-evaluation.md): Score live production traces on a recurring schedule — surface drift before customers do.
- [RAG evaluation](https://docs.layerlens.ai/4.1-general-use-cases/rag-evaluation.md): Evaluate RAG pipelines end-to-end — retrieval quality, faithfulness, and answer quality.
- [AI quality gates in CI/CD](https://docs.layerlens.ai/4.1-general-use-cases/ai-quality-gates-cicd.md): Block prompt and model regressions in your merge pipeline — turn evaluations into a hard gate.
- [Industry solutions](https://docs.layerlens.ai/4.2-industry-use-cases/industry.md): Stratix industry solutions — 13 verticals with scenarios, eval patterns, compliance, and runnable samples.
- [By AI workflow shape](https://docs.layerlens.ai/4.2-industry-use-cases/by-workflow-shape.md): Industry patterns indexed by AI workflow shape — RAG, agent, classification, generation, multimodal.
- [Healthcare](https://docs.layerlens.ai/4.2-industry-use-cases/healthcare.md): Healthcare AI evaluation on Stratix — clinical Q\&A, triage, medical document analysis.
- [Pattern: clinical decision support](https://docs.layerlens.ai/4.2-industry-use-cases/pattern.md): Healthcare — clinical decision support pattern. Faithfulness, drug-interaction safety, reasoning soundness, audit-ready evidence.
- [Financial services](https://docs.layerlens.ai/4.2-industry-use-cases/financial-services.md): Financial services AI evaluation — fraud detection, advisor chatbots, KYC.
- [Pattern: fair-lending platform](https://docs.layerlens.ai/4.2-industry-use-cases/pattern-1.md): Financial services — fair-lending platform pattern. Bias scorer shared across product teams, variant comparison, continuous monitoring.
- [Pattern: AI research citation verification](https://docs.layerlens.ai/4.2-industry-use-cases/pattern-2.md): Legal — AI research citation verification pattern. Citation-existence scorer, holding-accuracy judge, per-session block on unverified output.
- [Insurance](https://docs.layerlens.ai/4.2-industry-use-cases/insurance.md): Insurance AI evaluation — claims triage, policy Q\&A, underwriting assistance.
- [Pattern: claims-triage agent](https://docs.layerlens.ai/4.2-industry-use-cases/pattern-3.md): Insurance — claims-triage agent pattern. Span-level escalation rule, assertions, GEPA-tuned tone judge, in one agentic evaluation.
- [Government and public sector](https://docs.layerlens.ai/4.2-industry-use-cases/government-public-sector.md): Government and public sector AI evaluation — citizen services, document processing, eligibility.
- [Pattern: citizen-services chatbot](https://docs.layerlens.ai/4.2-industry-use-cases/pattern-4.md): Government / public sector — citizen-services chatbot pattern. Policy accuracy against versioned source-of-truth, plain-language reading-level, multilingual parity.
- [Retail and e-commerce](https://docs.layerlens.ai/4.2-industry-use-cases/retail-ecommerce.md): Retail and e-commerce AI evaluation — product Q\&A, customer support, recommendations.
- [Pattern: product description generation](https://docs.layerlens.ai/4.2-industry-use-cases/pattern-5.md): Retail / e-commerce — product-description generation pattern. Specification accuracy, brand voice, return-rate impact.
- [Media and entertainment](https://docs.layerlens.ai/4.2-industry-use-cases/media-entertainment.md): Media and entertainment AI evaluation — moderation, summarization, search.
- [Pattern: content moderation](https://docs.layerlens.ai/4.2-industry-use-cases/pattern-6.md): Media / entertainment — content moderation pattern. Per-category recall, cross-language parity, EU DSA exposure management.
- [Manufacturing](https://docs.layerlens.ai/4.2-industry-use-cases/manufacturing.md): Manufacturing AI evaluation — diagnostics assistance, manuals Q\&A, quality.
- [Pattern: visual quality inspection](https://docs.layerlens.ai/4.2-industry-use-cases/pattern-7.md): Manufacturing / industrial — visual quality-inspection pattern. Per-defect-class accuracy, lighting-robustness, latency under SLO.
- [Education](https://docs.layerlens.ai/4.2-industry-use-cases/education.md): Education AI evaluation — tutoring, content generation, assessment.
- [Pattern: AI tutor](https://docs.layerlens.ai/4.2-industry-use-cases/pattern-8.md): Education / EdTech — AI tutor pattern. Pedagogical-quality (Socratic vs. answer-giving), age-appropriateness, learning-outcome correlation.
- [Real estate](https://docs.layerlens.ai/4.2-industry-use-cases/real-estate.md): Real estate AI evaluation — listing Q\&A, valuation assist, document search.
- [Pattern: automated property valuation](https://docs.layerlens.ai/4.2-industry-use-cases/pattern-9.md): Real estate / proptech — automated valuation pattern. Per-segment accuracy, fair-housing parity, image-condition assessment.
- [Telecommunications](https://docs.layerlens.ai/4.2-industry-use-cases/telecommunications.md): Telecommunications AI evaluation — customer service, troubleshooting, plan Q\&A.
- [Pattern: customer-service pricing accuracy](https://docs.layerlens.ai/4.2-industry-use-cases/pattern-10.md): Telecom — customer-service AI pricing-accuracy pattern. JSON-schema scorer, numeric exact-match, per-PR CI gating, continuous sampled trace eval.
- [Energy and utilities](https://docs.layerlens.ai/4.2-industry-use-cases/energy-utilities.md): Energy and utilities AI evaluation — field service, ops assistance, customer support.
- [Pattern: vegetation-management imagery](https://docs.layerlens.ai/4.2-industry-use-cases/pattern-11.md): Energy / utilities — vegetation-management imagery pattern. Stratified accuracy by season, variant comparison, daily continuous evaluation in fire season.
- [Travel and hospitality](https://docs.layerlens.ai/4.2-industry-use-cases/travel-hospitality.md): Travel and hospitality AI evaluation — booking assist, itinerary, customer service.
- [Pattern: multilingual booking assistant](https://docs.layerlens.ai/4.2-industry-use-cases/pattern-12.md): Travel / hospitality — multilingual booking-assistant pattern. Per-language booking-detail accuracy, cultural appropriateness, locale-aware date handling.
- [Industry](https://docs.layerlens.ai/more-in-this-section-2/industry.md)
- [Education and EdTech compliance](https://docs.layerlens.ai/more-in-this-section-2/compliance.md): Education compliance — FERPA, COPPA, IDEA, Section 504, ADA, Title VI/IX, state student-data laws, ED guidance, accessibility.
- [Education cookbook and samples](https://docs.layerlens.ai/more-in-this-section-2/cookbook-and-samples.md): Education starter samples.
- [Recipe: education tutor pedagogical-quality](https://docs.layerlens.ai/more-in-this-section-2/industry-education-tutor.md): Recipe — education AI tutor pedagogical-quality judge.
- [Education and EdTech evaluation patterns](https://docs.layerlens.ai/more-in-this-section-2/eval-patterns.md): Education evaluation patterns — primitive ratio, span rules, GEPA labeling, cadence.
- [Education and EdTech scenarios](https://docs.layerlens.ai/more-in-this-section-2/scenarios.md): Education and EdTech scenarios — tutoring, grading, content generation, integrity, accessibility. Industry patterns, not customer case studies.
- [Energy and utilities compliance](https://docs.layerlens.ai/more-in-this-section-2/compliance-1.md): Energy and utilities compliance — NERC CIP/OPS, FERC, state PUC/CPUC, PHMSA, OSHA, EPA, ISO/RTO market rules.
- [Energy and utilities cookbook and samples](https://docs.layerlens.ai/more-in-this-section-2/cookbook-and-samples-1.md): Energy starter samples.
- [Energy and utilities evaluation patterns](https://docs.layerlens.ai/more-in-this-section-2/eval-patterns-1.md): Energy and utilities evaluation patterns — primitive ratio, span rules, GEPA labeling, cadence.
- [Energy and utilities scenarios](https://docs.layerlens.ai/more-in-this-section-2/scenarios-1.md): Energy and utilities scenarios — grid operations, predictive maintenance, customer service, demand response, safety. Industry patterns, not customer case studies.
- [Financial-services compliance](https://docs.layerlens.ai/more-in-this-section-2/compliance-2.md): Financial-services compliance — multi-regulator frame (SEC, FINRA, FinCEN, OCC, CFPB, SOX, GLBA), evidence shape per regime.
- [Financial services cookbook and samples](https://docs.layerlens.ai/more-in-this-section-2/cookbook-and-samples-2.md): Financial services starter samples.
- [Recipe: financial-services advisor & trading](https://docs.layerlens.ai/more-in-this-section-2/industry-finserv-advisor.md): Recipe — financial-services advisor / trading. Pointer to the SDK industry samples.
- [Financial-services evaluation patterns](https://docs.layerlens.ai/more-in-this-section-2/eval-patterns-2.md): Financial-services evaluation patterns — primitive ratios, dimensions, fair-lending considerations, GEPA labeling, continuous cadence.
- [Financial services scenarios](https://docs.layerlens.ai/more-in-this-section-2/scenarios-2.md): Financial services AI evaluation scenarios — fraud detection, advisor chatbots, KYC, document processing, trading compliance.
- [Government and public sector compliance](https://docs.layerlens.ai/more-in-this-section-2/compliance-3.md): Government compliance — FedRAMP, FISMA, NIST AI RMF, OMB M-24-10, Section 508, Privacy Act, FOIA, EO 14110.
- [Government cookbook and samples](https://docs.layerlens.ai/more-in-this-section-2/cookbook-and-samples-3.md): Government starter samples.
- [Government and public sector evaluation patterns](https://docs.layerlens.ai/more-in-this-section-2/eval-patterns-3.md): Government evaluation patterns — primitive ratio, span rules, GEPA labeling, cadence aligned to NIST AI RMF and OMB M-24-10.
- [Government and public sector scenarios](https://docs.layerlens.ai/more-in-this-section-2/scenarios-3.md): Government and public sector scenarios — citizen services, benefits, FOIA, procurement, public-safety analytics. Industry patterns, not customer case studies.
- [Healthcare compliance](https://docs.layerlens.ai/more-in-this-section-2/compliance-4.md): Healthcare compliance — HIPAA, BAA, audit retention, PHI handling, FDA SaMD considerations.
- [Healthcare cookbook and samples](https://docs.layerlens.ai/more-in-this-section-2/cookbook-and-samples-4.md): Healthcare cookbook starter samples.
- [Recipe: healthcare clinical Q\&A safety](https://docs.layerlens.ai/more-in-this-section-2/industry-healthcare-clinical-qa.md): Recipe — healthcare clinical Q\&A. Pointer to the SDK industry sample.
- [Healthcare evaluation patterns](https://docs.layerlens.ai/more-in-this-section-2/eval-patterns-4.md): Healthcare evaluation patterns — common scorer, rule, and judge combinations.
- [Healthcare scenarios](https://docs.layerlens.ai/more-in-this-section-2/scenarios-4.md): Healthcare evaluation scenarios — clinical Q\&A, triage, summarization, medication safety, prior-authorization, and more.
- [Insurance compliance](https://docs.layerlens.ai/more-in-this-section-2/compliance-5.md): Insurance compliance — state DOI rate filings, NAIC AI bulletin, GLBA, ECOA/Fair Housing, HIPAA (health lines), audit retention.
- [Insurance cookbook and samples](https://docs.layerlens.ai/more-in-this-section-2/cookbook-and-samples-5.md): Insurance starter samples.
- [Recipe: insurance claims & underwriting](https://docs.layerlens.ai/more-in-this-section-2/industry-insurance-claims.md): Recipe — insurance claims and underwriting. Pointer to the SDK industry samples.
- [Insurance evaluation patterns](https://docs.layerlens.ai/more-in-this-section-2/eval-patterns-5.md): Insurance evaluation patterns — primitive ratio, span rules, GEPA labeling, cadence.
- [Insurance scenarios](https://docs.layerlens.ai/more-in-this-section-2/scenarios-5.md): Insurance industry scenarios — claims triage, underwriting, policy Q\&A, fraud detection, subrogation. Industry patterns, not customer case studies.
- [Legal](https://docs.layerlens.ai/more-in-this-section-2/legal.md): Legal AI evaluation — contract review, legal research, document analysis.
- [Legal compliance](https://docs.layerlens.ai/more-in-this-section-2/compliance-6.md): Legal compliance — privilege, work product, court rules, bar discipline, malpractice exposure, retention.
- [Legal cookbook and samples](https://docs.layerlens.ai/more-in-this-section-2/cookbook-and-samples-6.md): Legal starter samples.
- [Recipe: legal contract review & research](https://docs.layerlens.ai/more-in-this-section-2/industry-legal-contract.md): Recipe — legal contract review and research. Pointer to the SDK industry samples.
- [Legal evaluation patterns](https://docs.layerlens.ai/more-in-this-section-2/eval-patterns-6.md): Legal evaluation patterns — primitive ratios, dimensions, citation verification depth, GEPA labeling.
- [Legal scenarios](https://docs.layerlens.ai/more-in-this-section-2/scenarios-6.md): Legal AI evaluation scenarios — contract review, legal research, document discovery, document automation.
- [Manufacturing and industrial compliance](https://docs.layerlens.ai/more-in-this-section-2/compliance-7.md): Manufacturing compliance — ISO 9001, IATF 16949, AS9100, ISO 13485, OSHA PSM, EPA RMP, ITAR/EAR/OFAC, RoHS/REACH/Conflict Minerals.
- [Manufacturing cookbook and samples](https://docs.layerlens.ai/more-in-this-section-2/cookbook-and-samples-7.md): Manufacturing starter samples.
- [Manufacturing and industrial evaluation patterns](https://docs.layerlens.ai/more-in-this-section-2/eval-patterns-7.md): Manufacturing evaluation patterns — primitive ratio, span rules, GEPA labeling, cadence.
- [Manufacturing and industrial scenarios](https://docs.layerlens.ai/more-in-this-section-2/scenarios-7.md): Manufacturing and industrial scenarios — predictive maintenance, quality, supply chain, technical Q\&A, safety. Industry patterns, not customer case studies.
- [Media and entertainment compliance](https://docs.layerlens.ai/more-in-this-section-2/compliance-8.md): Media and entertainment compliance — DSA, OSA, COPPA, ratings systems, DMCA, defamation, broadcast/state laws.
- [Media cookbook and samples](https://docs.layerlens.ai/more-in-this-section-2/cookbook-and-samples-8.md): Media starter samples.
- [Media and entertainment evaluation patterns](https://docs.layerlens.ai/more-in-this-section-2/eval-patterns-8.md): Media and entertainment evaluation patterns — primitive ratio, span rules, GEPA labeling, cadence.
- [Media and entertainment scenarios](https://docs.layerlens.ai/more-in-this-section-2/scenarios-8.md): Media and entertainment scenarios — content recommendation, moderation, ad relevance, news summarization, IP/rights. Industry patterns, not customer case studies.
- [Real estate and PropTech compliance](https://docs.layerlens.ai/more-in-this-section-2/compliance-9.md): Real estate compliance — Fair Housing Act, ECOA, FCRA, RESPA, TILA, HMDA, state broker rules, AVM rules, state landlord-tenant law.
- [Real estate cookbook and samples](https://docs.layerlens.ai/more-in-this-section-2/cookbook-and-samples-9.md): Real estate starter samples.
- [Real estate and PropTech evaluation patterns](https://docs.layerlens.ai/more-in-this-section-2/eval-patterns-9.md): Real estate evaluation patterns — primitive ratio, span rules, GEPA labeling, cadence.
- [Real estate and PropTech scenarios](https://docs.layerlens.ai/more-in-this-section-2/scenarios-9.md): Real estate and PropTech scenarios — listing assistance, valuation, tenant screening, transaction support, property management. Industry patterns, not customer case studies.
- [Retail and e-commerce compliance](https://docs.layerlens.ai/more-in-this-section-2/compliance-10.md): Retail and e-commerce compliance — FTC Act, state UDAP, PCI DSS, COPPA, ADA, CCPA/GDPR, age-restricted goods.
- [Retail cookbook and samples](https://docs.layerlens.ai/more-in-this-section-2/cookbook-and-samples-10.md): Retail starter samples.
- [Recipe: retail product Q\&A & support](https://docs.layerlens.ai/more-in-this-section-2/industry-retail-product-qa.md): Recipe — retail product Q\&A and support. Pointer to the SDK industry samples.
- [Retail and e-commerce evaluation patterns](https://docs.layerlens.ai/more-in-this-section-2/eval-patterns-10.md): Retail evaluation patterns — primitive ratio, span rules, GEPA labeling, cadence.
- [Retail and e-commerce scenarios](https://docs.layerlens.ai/more-in-this-section-2/scenarios-10.md): Retail and e-commerce scenarios — product Q\&A, recommendations, pricing, customer service, returns/fraud. Industry patterns, not customer case studies.
- [Telecommunications compliance](https://docs.layerlens.ai/more-in-this-section-2/compliance-11.md): Telecom compliance — FCC rules, CPNI, TCPA, CALEA, ECPA, STIR/SHAKEN, NORS, state PUC, privacy laws.
- [Telecom cookbook and samples](https://docs.layerlens.ai/more-in-this-section-2/cookbook-and-samples-11.md): Telecom starter samples.
- [Telecommunications evaluation patterns](https://docs.layerlens.ai/more-in-this-section-2/eval-patterns-11.md): Telecommunications evaluation patterns — primitive ratio, span rules, GEPA labeling, cadence.
- [Telecommunications scenarios](https://docs.layerlens.ai/more-in-this-section-2/scenarios-11.md): Telecommunications scenarios — customer service, network ops, plan recommendations, fraud prevention, lawful intercept. Industry patterns, not customer case studies.
- [Travel and hospitality compliance](https://docs.layerlens.ai/more-in-this-section-2/compliance-12.md): Travel and hospitality compliance — DOT, EU 261, ACAA, ADA, FTC junk-fees, GDPR/CCPA, PCI DSS, state emergency-pricing laws.
- [Travel cookbook and samples](https://docs.layerlens.ai/more-in-this-section-2/cookbook-and-samples-12.md): Travel starter samples.
- [Travel and hospitality evaluation patterns](https://docs.layerlens.ai/more-in-this-section-2/eval-patterns-12.md): Travel and hospitality evaluation patterns — primitive ratio, span rules, GEPA labeling, cadence.
- [Travel and hospitality scenarios](https://docs.layerlens.ai/more-in-this-section-2/scenarios-12.md): Travel and hospitality scenarios — booking, customer service, loyalty, dynamic pricing, accessibility. Industry patterns, not customer case studies.
- [Select (workflow)](https://docs.layerlens.ai/5.-select-pick-the-model/workflow.md): Stage 1 — Select. Review leaderboards and benchmarks, optionally benchmark candidates side-by-side, pick the model to build with.
- [Catalog (Public + Premium)](https://docs.layerlens.ai/5.-select-pick-the-model/catalog-public-+-premium.md)
- [Browse the leaderboard](https://docs.layerlens.ai/5.-select-pick-the-model/leaderboard.md): Browse the Stratix leaderboard — top models per capability and per benchmark.
- [Models catalog](https://docs.layerlens.ai/5.-select-pick-the-model/models-catalog.md): Stratix Public Models catalog — 175+ models with metadata, capability tags, and per-benchmark scores.
- [Benchmarks catalog](https://docs.layerlens.ai/5.-select-pick-the-model/benchmarks-catalog.md): Stratix Public Benchmarks catalog — 52+ benchmarks with methodology and per-model scores.
- [Compare models](https://docs.layerlens.ai/5.-select-pick-the-model/compare-models.md): Compare any two models head-to-head across any shared benchmark — Stratix Public's flagship feature.
- [Public evaluations](https://docs.layerlens.ai/5.-select-pick-the-model/public-evaluations.md): 2,000+ public evaluations browsable on Stratix Public — full results, sample inputs, methodology.
- [Public evaluation spaces](https://docs.layerlens.ai/5.-select-pick-the-model/public-evaluation-spaces.md): Public evaluation spaces — curated bundles of model + dataset + scoring config, browsable without signup.
- [Test your AI (anonymous)](https://docs.layerlens.ai/5.-select-pick-the-model/test-your-ai-anonymous.md): Anonymous prompt-against-model sandbox on Stratix Public — no signup, rate-limited.
- [Search](https://docs.layerlens.ai/5.-select-pick-the-model/search.md): Search the Stratix Public catalog — models, benchmarks, evaluations, spaces in one place.
- [Sharing public results](https://docs.layerlens.ai/5.-select-pick-the-model/sharing-results.md): How to share Stratix Public results — citing evaluation IDs, embedding scores, contributing public evaluations.
- [Public catalog data freshness](https://docs.layerlens.ai/5.-select-pick-the-model/data-freshness.md): How fresh is the public catalog data — refresh cadence, "last updated" timestamps, methodology versioning.
- [Public vs Premium — feature matrix](https://docs.layerlens.ai/5.-select-pick-the-model/public-vs-premium.md): Feature matrix — what's available on Stratix Public vs Stratix Premium.
- [Models (Premium custom)](https://docs.layerlens.ai/5.-select-pick-the-model/models.md): The Stratix Premium Models surface — public catalog plus your BYOK custom models.
- [Benchmarks (Premium custom)](https://docs.layerlens.ai/5.-select-pick-the-model/benchmarks.md): The Stratix Premium Benchmarks surface — public benchmarks plus your private datasets.
- [BYOK custom models](https://docs.layerlens.ai/5.-select-pick-the-model/byok-custom-models.md): Register an OpenAI-compatible endpoint as a first-class custom model in Stratix Premium.
- [Research — quarterly reports](https://docs.layerlens.ai/5.-select-pick-the-model/quarterly-reports.md): Q1-Q4 research reports — model performance, benchmark winners, AI evaluation trends.
- [Concepts](https://docs.layerlens.ai/5.-select-pick-the-model/concepts.md)
- [Models and benchmarks](https://docs.layerlens.ai/5.-select-pick-the-model/models-and-benchmarks.md): Models and benchmarks — the building blocks of the Stratix catalog.
- [BYOK models](https://docs.layerlens.ai/5.-select-pick-the-model/byok-models.md): Bring-your-own-key (BYOK) models in Stratix — register OpenAI-compatible endpoints as first-class models.
- [Public vs Premium](https://docs.layerlens.ai/5.-select-pick-the-model/public-vs-premium-1.md): How Stratix Public and Stratix Premium relate — same catalog, different surfaces.
- [Catalog](https://docs.layerlens.ai/more-in-this-section-3/catalog.md)
- [Stratix Public](https://docs.layerlens.ai/more-in-this-section-3/catalog-1.md): Stratix Public — anonymous browsing of 175+ models, 52+ benchmarks, 2,000+ public evaluations.
- [Stratix Premium](https://docs.layerlens.ai/more-in-this-section-3/premium-workspace-overview.md): Stratix Premium — the logged-in workspace at stratix.layerlens.ai. Private evaluations, judges, traces, agentic evals.
- [Cookbook](https://docs.layerlens.ai/more-in-this-section-3/cookbook.md)
- [Recipe: compare prompts on a small test set](https://docs.layerlens.ai/more-in-this-section-3/compare-prompts.md): Recipe — A/B compare prompt variants. Pointer to the canonical SDK sample.
- [Recipe: pick a model for a task](https://docs.layerlens.ai/more-in-this-section-3/pick-a-model.md): Recipe — pick the right model for a task. Pointer to the canonical SDK quickstart + filtering sample.
- [Guides](https://docs.layerlens.ai/more-in-this-section-3/guides.md)
- [Refresh a benchmark with new data](https://docs.layerlens.ai/more-in-this-section-3/refresh-benchmark.md): Guide — refresh a private benchmark with new data.
- [Register a BYOK custom model](https://docs.layerlens.ai/more-in-this-section-3/register-byok-model.md): Guide — register a BYOK custom model.
- [Rotate a BYOK API key](https://docs.layerlens.ai/more-in-this-section-3/rotate-byok-key.md): Guide — rotate a BYOK API key without downtime.
- [Test a BYOK endpoint](https://docs.layerlens.ai/more-in-this-section-3/test-byok-endpoint.md): Guide — test a BYOK custom-model endpoint.
- [Upload a private benchmark](https://docs.layerlens.ai/more-in-this-section-3/upload-benchmark.md): Guide — upload a private benchmark dataset.
- [Build (workflow)](https://docs.layerlens.ai/6.-build-wire-your-code/workflow.md): Stage 2 — Build. Wire your code or agent to emit traces Stratix can ingest, and develop with evaluation-driven feedback from the start.
- [SDK](https://docs.layerlens.ai/6.-build-wire-your-code/sdk.md)
- [Python SDK — quickstart](https://docs.layerlens.ai/6.-build-wire-your-code/quickstart.md): SDK quickstart — install, authenticate, run an eval.
- [Python SDK — install](https://docs.layerlens.ai/6.-build-wire-your-code/installation.md): Stratix Python SDK installation.
- [Python SDK — auto-instrumentation](https://docs.layerlens.ai/6.-build-wire-your-code/sdk-python.md): Stratix Python SDK reference — Stratix, AsyncStratix, complete resource surface, errors.
- [Concepts](https://docs.layerlens.ai/6.-build-wire-your-code/concepts.md)
- [Traces and spans](https://docs.layerlens.ai/6.-build-wire-your-code/traces-and-spans.md): Traces and spans in Stratix — the unit of "what did my AI actually do."
- [Async vs sync workflow](https://docs.layerlens.ai/6.-build-wire-your-code/async-vs-sync-workflow.md): Async vs sync workflow in Stratix — when work is queued, when it's immediate, what to expect.
- [Streaming](https://docs.layerlens.ai/6.-build-wire-your-code/streaming.md): Streaming evaluation results and trace progress — SSE and WebSocket patterns.
- [Cookbook](https://docs.layerlens.ai/6.-build-wire-your-code/cookbook.md)
- [Instrument LangChain](https://docs.layerlens.ai/6.-build-wire-your-code/instrument-langchain.md): Recipe — instrument LangChain. Pointer to the SDK langchain\_instrumented sample.
- [Instrument LlamaIndex](https://docs.layerlens.ai/6.-build-wire-your-code/instrument-llamaindex.md): Recipe — instrument a LlamaIndex pipeline. SDK adapter + manual trace upload patterns.
- [Instrument Haystack](https://docs.layerlens.ai/6.-build-wire-your-code/instrument-haystack.md): Recipe — instrument a Haystack pipeline using manual trace upload.
- [Instrument OpenAI Assistants](https://docs.layerlens.ai/6.-build-wire-your-code/instrument-openai-assistants.md): Recipe — instrument OpenAI / Assistants. Pointer to the SDK samples.
- [Instrument Anthropic SDK](https://docs.layerlens.ai/6.-build-wire-your-code/instrument-anthropic-sdk.md): Recipe — instrument the Anthropic SDK. Pointer to the canonical SDK samples.
- [Instrument Vercel AI SDK](https://docs.layerlens.ai/6.-build-wire-your-code/instrument-vercel-ai-sdk.md): Recipe — instrument a Vercel AI SDK call to emit traces (via REST).
- [Instrument custom Python](https://docs.layerlens.ai/6.-build-wire-your-code/instrument-custom-python.md): Recipe — instrument a custom Python pipeline using @trace and span().
- [OpenTelemetry trace ingestion](https://docs.layerlens.ai/6.-build-wire-your-code/otel-trace-ingestion.md): Recipe — OpenTelemetry trace ingestion. Pointer to the canonical SDK adapter doc.
- [Containerized CI](https://docs.layerlens.ai/6.-build-wire-your-code/containerized-ci.md): Recipe — containerized CI evaluation with a minimal Dockerfile.
- [Pre-release readiness](https://docs.layerlens.ai/6.-build-wire-your-code/prerelease-readiness.md): Recipe — pre-release readiness evaluation gate.
- [Slack notifications](https://docs.layerlens.ai/6.-build-wire-your-code/integration-slack.md): Recipe — route Stratix evaluation results into a Slack channel by polling and forwarding.
- [PagerDuty escalation](https://docs.layerlens.ai/6.-build-wire-your-code/integration-pagerduty.md): Recipe — escalate critical evaluation regressions to PagerDuty by polling and forwarding.
- [GitHub Actions](https://docs.layerlens.ai/6.-build-wire-your-code/integration-github-actions.md): Recipe — GitHub Actions evaluation gate. Pointer to the SDK's drop-in workflow file.
- [GitLab CI](https://docs.layerlens.ai/6.-build-wire-your-code/integration-gitlab-ci.md): Recipe — GitLab CI evaluation gate.
- [Buildkite](https://docs.layerlens.ai/6.-build-wire-your-code/integration-buildkite.md): Recipe — Buildkite evaluation gate.
- [Jenkins](https://docs.layerlens.ai/6.-build-wire-your-code/integration-jenkins.md): Recipe — Jenkins evaluation gate.
- [CI/CD tutorial](https://docs.layerlens.ai/6.-build-wire-your-code/ci-cd-tutorial.md)
- [Tutorial 3: Wire CI/CD quality gates](https://docs.layerlens.ai/6.-build-wire-your-code/03-cicd-gates.md): Tutorial 3 — Wire Stratix evaluations into GitHub Actions to gate AI changes.
- [CI/CD integrations](https://docs.layerlens.ai/6.-build-wire-your-code/ci-cd-integrations.md)
- [GitHub Actions integration](https://docs.layerlens.ai/6.-build-wire-your-code/cicd-github-actions.md): GitHub Actions CI gate.
- [GitLab CI integration](https://docs.layerlens.ai/6.-build-wire-your-code/cicd-gitlab.md): GitLab CI gate.
- [Buildkite integration](https://docs.layerlens.ai/6.-build-wire-your-code/cicd-buildkite.md): Buildkite CI gate.
- [Surfaces](https://docs.layerlens.ai/6.-build-wire-your-code/surfaces.md)
- [VS Code extension](https://docs.layerlens.ai/6.-build-wire-your-code/vscode-extension.md): The Stratix VS Code extension — run evaluations and inspect results from your editor.
- [Slack app](https://docs.layerlens.ai/6.-build-wire-your-code/slack.md): The Stratix Slack app — notifications and quick actions in your workspace.
- [Migration from another tool](https://docs.layerlens.ai/6.-build-wire-your-code/migration-from-another-tool.md)
- [Migration overview](https://docs.layerlens.ai/6.-build-wire-your-code/migration.md): Migrate to Stratix from another evaluation tool.
- [From LangSmith](https://docs.layerlens.ai/6.-build-wire-your-code/from-langsmith.md): Migrate from LangSmith to Stratix — concept mapping, what to port, what to re-author, and a phased cutover plan.
- [From Braintrust](https://docs.layerlens.ai/6.-build-wire-your-code/from-braintrust.md): Migrate from Braintrust to Stratix.
- [From Galileo](https://docs.layerlens.ai/6.-build-wire-your-code/from-galileo.md): Migrate from Galileo to Stratix.
- [From Promptfoo](https://docs.layerlens.ai/6.-build-wire-your-code/from-promptfoo.md): Migrate from Promptfoo to Stratix.
- [From MLflow](https://docs.layerlens.ai/6.-build-wire-your-code/from-mlflow.md): Migrate from MLflow to Stratix.
- [From Arize](https://docs.layerlens.ai/6.-build-wire-your-code/from-arize.md): Migrate from Arize AI to Stratix — concept mapping, what to port, what to re-author, and a phased cutover plan.
- [Guides](https://docs.layerlens.ai/more-in-this-section-4/guides.md)
- [Calling Stratix from a backend](https://docs.layerlens.ai/more-in-this-section-4/calling-stratix-from-a-backend.md): Calling Stratix from a backend — TS, Go, Python patterns. Keep keys server-side; never in browsers.
- [Investigate a CI regression](https://docs.layerlens.ai/more-in-this-section-4/investigate-ci-regression.md): Guide — investigate a regression flagged by CI.
- [Run an industry pattern from a Next.js app](https://docs.layerlens.ai/more-in-this-section-4/pattern-from-nextjs.md): Guide — implement an industry pattern end-to-end from a Next.js app, fusing pattern config + backend-call + browser UI.
- [Per-feature quality tolerances](https://docs.layerlens.ai/more-in-this-section-4/per-feature-tolerances.md): Guide — set per-feature quality tolerances.
- [Set up trace ingestion](https://docs.layerlens.ai/more-in-this-section-4/setup-trace-ingestion.md): Guide — wire your application to ingest traces into Stratix.
- [Wire CI/CD evaluation gates](https://docs.layerlens.ai/more-in-this-section-4/wire-cicd-gates.md): Guide — wire Stratix evaluation gates into CI/CD.
- [Integrations](https://docs.layerlens.ai/more-in-this-section-4/integrations.md)
- [CI/CD integrations](https://docs.layerlens.ai/more-in-this-section-4/cicd.md): CI/CD integrations overview.
- [Migration](https://docs.layerlens.ai/more-in-this-section-4/migration.md)
- [Dual-run migration](https://docs.layerlens.ai/more-in-this-section-4/dual-run-migration.md): Guide — run Stratix and another tool side-by-side during migration.
- [Plan a migration to Stratix](https://docs.layerlens.ai/more-in-this-section-4/plan-migration.md): Guide — plan a migration to Stratix.
- [Recipe: Port a Braintrust eval](https://docs.layerlens.ai/more-in-this-section-4/migration-braintrust.md): Recipe — port a Braintrust eval into Stratix.
- [Recipe: Port a LangSmith eval](https://docs.layerlens.ai/more-in-this-section-4/migration-langsmith.md): Recipe — port a LangSmith eval dataset and judge into Stratix.
- [Recipe: Port an MLflow run](https://docs.layerlens.ai/more-in-this-section-4/migration-mlflow.md): Recipe — port an MLflow run into Stratix.
- [Recipe: Port a Promptfoo config](https://docs.layerlens.ai/more-in-this-section-4/migration-promptfoo.md): Recipe — port a Promptfoo config into Stratix.
- [Observe (workflow)](https://docs.layerlens.ai/7.-observe-see-whats-happening/workflow.md): Stage 2 — Observe. See real production behavior across surfaces.
- [Premium surfaces](https://docs.layerlens.ai/7.-observe-see-whats-happening/premium-surfaces.md)
- [Home dashboard](https://docs.layerlens.ai/7.-observe-see-whats-happening/home-dashboard.md): The Stratix Premium home dashboard — at-a-glance view of your team's evaluations, traces, and ECU.
- [Traces](https://docs.layerlens.ai/7.-observe-see-whats-happening/traces.md): Upload, browse, and inspect agent traces in Stratix Premium.
- [Datasets](https://docs.layerlens.ai/7.-observe-see-whats-happening/datasets.md): Create, version, and evaluate datasets — collections of traces grouped for streamlined analysis — in Stratix Premium.
- [Synthetic data](https://docs.layerlens.ai/7.-observe-see-whats-happening/synthetic-data.md): Generate realistic, multi-agent synthetic trace datasets — from your own data, a built-in industry scenario, or a saved definition — in Stratix Premium.
- [Agent Evaluation](https://docs.layerlens.ai/7.-observe-see-whats-happening/agent-evaluation.md): The Stratix Premium Agent Evaluation surface — Traces, Judges, and Trace Evaluations.
- [Concepts](https://docs.layerlens.ai/7.-observe-see-whats-happening/concepts.md)
- [Continuous evaluation](https://docs.layerlens.ai/7.-observe-see-whats-happening/continuous-evaluation.md): Continuous evaluation — score live production traces on a recurring schedule.
- [Multi-tenancy](https://docs.layerlens.ai/7.-observe-see-whats-happening/multi-tenancy.md): Multi-tenancy in Stratix — orgs, isolation, multi-org membership.
- [Cookbook](https://docs.layerlens.ai/7.-observe-see-whats-happening/cookbook.md)
- [Backfill traces from logs](https://docs.layerlens.ai/7.-observe-see-whats-happening/backfill-from-logs.md): Recipe — backfill traces from existing application logs.
- [Post-release continuous evaluation](https://docs.layerlens.ai/7.-observe-see-whats-happening/postrelease-continuous.md): Recipe — post-release continuous evaluation on production traces.
- [Guides](https://docs.layerlens.ai/more-in-this-section-5/guides.md)
- [Build a trace set for agentic evals](https://docs.layerlens.ai/more-in-this-section-5/build-trace-set.md): Guide — build a trace set for agentic evaluation.
- [Investigate a failing trace](https://docs.layerlens.ai/more-in-this-section-5/investigate-failing-trace.md): Guide — investigate a failing trace.
- [Schedule continuous trace evaluation](https://docs.layerlens.ai/more-in-this-section-5/schedule-continuous.md): Guide — schedule continuous trace evaluation.
- [Evaluate (workflow)](https://docs.layerlens.ai/8.-evaluate-score-the-outputs/workflow.md): Stage 4 — Evaluate. Score outputs and traces with scorers and judges.
- [Premium surfaces](https://docs.layerlens.ai/8.-evaluate-score-the-outputs/premium-surfaces.md)
- [Evaluations](https://docs.layerlens.ai/8.-evaluate-score-the-outputs/evaluations.md): The Stratix Premium Evaluations surface — create, run, browse, and compare private evaluations.
- [Judges](https://docs.layerlens.ai/8.-evaluate-score-the-outputs/judges.md): Build, test, and manage LLM-as-a-judge graders in Stratix Premium.
- [System judges](https://docs.layerlens.ai/8.-evaluate-score-the-outputs/system-judges.md): System judges shipped with Stratix Premium — names, evaluation goals, default models, and how to use them.
- [Scorers](https://docs.layerlens.ai/8.-evaluate-score-the-outputs/scorers.md): The Stratix Premium Scorers surface — manage LLM-backed scorers org-scoped.
- [Trace evaluations](https://docs.layerlens.ai/8.-evaluate-score-the-outputs/trace-evaluations.md): Score uploaded traces with scorers and judges — recurring, on-demand, agentic.
- [Spaces](https://docs.layerlens.ai/8.-evaluate-score-the-outputs/spaces.md): The Stratix Premium Spaces surface — save and re-run evaluation configurations as conditions change.
- [Concepts](https://docs.layerlens.ai/8.-evaluate-score-the-outputs/concepts.md)
- [Mental model](https://docs.layerlens.ai/8.-evaluate-score-the-outputs/mental-model.md): The Stratix mental model — catalog, engine, judges, traces, and how data moves through the platform.
- [Evaluations](https://docs.layerlens.ai/8.-evaluate-score-the-outputs/evaluations-1.md): An evaluation in Stratix — what it actually is, what it produces, how it's stored.
- [Evaluation anatomy](https://docs.layerlens.ai/8.-evaluate-score-the-outputs/evaluation-anatomy.md): The anatomy of a Stratix evaluation — every field, every state, every artifact.
- [Judges](https://docs.layerlens.ai/8.-evaluate-score-the-outputs/judges-1.md): LLM-as-a-judge in Stratix — building, running, and optimizing judges with GEPA.
- [Scorers](https://docs.layerlens.ai/8.-evaluate-score-the-outputs/scorers-1.md): LLM-backed scorers in Stratix — model + prompt, when to use them, when to use a judge instead.
- [Evaluation spaces](https://docs.layerlens.ai/8.-evaluate-score-the-outputs/evaluation-spaces.md): Evaluation spaces — saved configurations you re-run as conditions change.
- [Agentic evaluation](https://docs.layerlens.ai/8.-evaluate-score-the-outputs/agentic-evaluation.md): Agentic evaluation — pre- and post-deployment quality gates for multi-step AI agents.
- [Tutorials](https://docs.layerlens.ai/8.-evaluate-score-the-outputs/tutorials.md)
- [Tutorial 1: First evaluation in 10 minutes](https://docs.layerlens.ai/8.-evaluate-score-the-outputs/01-first-evaluation.md): Tutorial 1 — Run your first end-to-end Stratix evaluation in 10 minutes.
- [Tutorial 2: Build your first judge](https://docs.layerlens.ai/8.-evaluate-score-the-outputs/02-first-judge.md): Tutorial 2 — Build, test, and apply your first LLM judge.
- [Tutorial 4: Score live traces](https://docs.layerlens.ai/8.-evaluate-score-the-outputs/04-score-traces.md): Tutorial 4 — Score production traces continuously with Stratix trace evaluations.
- [Cookbook](https://docs.layerlens.ai/more-in-this-section-6/cookbook.md)
- [Recipe: detect tool-call regressions in agents](https://docs.layerlens.ai/more-in-this-section-6/agent-tool-regressions.md): Recipe — detect tool-call regressions. Pointer to the SDK code-review cowork sample.
- [Recipe: catch hallucinations](https://docs.layerlens.ai/more-in-this-section-6/catch-hallucinations.md): Recipe — catch hallucinations with a faithfulness judge whose rubric handles refusals.
- [Recipe: Confidence-weighted aggregation](https://docs.layerlens.ai/more-in-this-section-6/confidence-weighted-aggregation.md): Recipe — confidence-weighted aggregation for noisy judges.
- [Recipe: Cost-aware evaluation](https://docs.layerlens.ai/more-in-this-section-6/cost-aware-evaluation.md): Recipe — score cost alongside quality so you can pick smaller-and-cheaper when it's good enough.
- [Recipe: create a custom scorer](https://docs.layerlens.ai/more-in-this-section-6/custom-code-scorer.md): Recipe — create a custom scorer (LLM-backed). Pointer to the SDK scorer + judge-creation samples.
- [Recipe: validate JSON output against a schema](https://docs.layerlens.ai/more-in-this-section-6/json-schema-validate.md): Recipe — validate JSON outputs against a strict schema using a custom judge or pre-evaluation validation.
- [Recipe: Run a judge in CI without auto-merging on pass](https://docs.layerlens.ai/more-in-this-section-6/judge-ci-no-merge.md): Recipe — gate CI on a judge verdict without auto-merging on pass.
- [Recipe: multi-judge consensus](https://docs.layerlens.ai/more-in-this-section-6/multi-judge-consensus.md): Recipe — run multiple judges against the same trace and aggregate via consensus.
- [Recipe: Score multilingual outputs](https://docs.layerlens.ai/more-in-this-section-6/multilingual.md): Recipe — score outputs in multiple languages with an LLM judge.
- [Recipe: build a faithfulness judge for RAG](https://docs.layerlens.ai/more-in-this-section-6/rag-faithfulness-judge.md): Recipe — RAG faithfulness judge. Pointer to the SDK rag\_assessment sample.
- [Recipe: score a free-form chat output](https://docs.layerlens.ai/more-in-this-section-6/score-chat.md): Recipe — score chat output. Pointer to the canonical SDK text-evaluation sample.
- [Recipe: evaluate code-generation models](https://docs.layerlens.ai/more-in-this-section-6/score-code.md): Recipe — evaluate code-generation models. Use a code benchmark from the public catalog.
- [Recipe: Score reasoning chains](https://docs.layerlens.ai/more-in-this-section-6/score-reasoning.md): Recipe — score reasoning chains with chain-of-thought aware judges.
- [Recipe: score retrieval quality](https://docs.layerlens.ai/more-in-this-section-6/score-retrieval.md): Recipe — score retrieval quality. Pointer to the SDK rag\_assessment sample.
- [Recipe: score a structured-output prompt](https://docs.layerlens.ai/more-in-this-section-6/score-structured-output.md): Recipe — score structured outputs. Pointer to the SDK document-evaluation sample.
- [Recipe: span-level scoring](https://docs.layerlens.ai/more-in-this-section-6/span-level-scoring.md): Recipe — span-level scoring. Pointer to the cowork code-review pattern.
- [Guides](https://docs.layerlens.ai/more-in-this-section-6/guides.md)
- [Bootstrap a judge before GEPA](https://docs.layerlens.ai/more-in-this-section-6/bootstrap-judges.md): Bootstrap a judge before GEPA — what to ship in week one when you don't yet have labeled data.
- [Build your judge library](https://docs.layerlens.ai/more-in-this-section-6/build-judge-library.md): Guide — build a shared judge library across your org.
- [Author a custom code grader](https://docs.layerlens.ai/more-in-this-section-6/custom-code-scorer-1.md): Guide — author a custom code grader.
- [Detect and remove flaky scorers](https://docs.layerlens.ai/more-in-this-section-6/remove-flaky-scorers.md): Guide — detect and remove flaky scorers.
- [Standardize judges across teams](https://docs.layerlens.ai/more-in-this-section-6/standardize-judges.md): Guide — standardize judges across teams.
- [Improve (workflow)](https://docs.layerlens.ai/9.-improve-tune-the-system/workflow.md): Stage 5 — Improve. Tune prompts, judges, and configurations. Re-run.
- [Premium surfaces](https://docs.layerlens.ai/9.-improve-tune-the-system/premium-surfaces.md)
- [Judge Optimization (GEPA)](https://docs.layerlens.ai/9.-improve-tune-the-system/judge-optimization.md): GEPA judge optimization — automatically tune your judge rubric to match labeled ground truth.
- [Tutorials](https://docs.layerlens.ai/9.-improve-tune-the-system/tutorials.md)
- [Tutorial 5: Optimize a judge with GEPA](https://docs.layerlens.ai/9.-improve-tune-the-system/05-gepa-optimize.md): Tutorial 5 — Optimize a judge with GEPA so its verdicts match your team's labels.
- [Cookbook](https://docs.layerlens.ai/9.-improve-tune-the-system/cookbook.md)
- [GEPA basics](https://docs.layerlens.ai/9.-improve-tune-the-system/gepa-basics.md): Recipe — judge optimization basics. Pointer to the SDK judge\_optimization sample.
- [GEPA holdout](https://docs.layerlens.ai/9.-improve-tune-the-system/gepa-holdout.md): Recipe — held-out validation when running judge optimization, to detect over-fit.
- [GEPA iterative labeling](https://docs.layerlens.ai/9.-improve-tune-the-system/gepa-iterative-labeling.md): Recipe — iteratively label examples and re-optimize judges as your bar evolves.
- [Daily smoke eval](https://docs.layerlens.ai/9.-improve-tune-the-system/daily-smoke-eval.md): Recipe — daily smoke evaluation against a representative trace set, scheduled by your own cron.
- [Quarterly rebench](https://docs.layerlens.ai/9.-improve-tune-the-system/quarterly-rebench.md): Recipe — quarterly model re-evaluation as the frontier moves.
- [Guides](https://docs.layerlens.ai/more-in-this-section-7/guides.md)
- [Cost-control levers](https://docs.layerlens.ai/more-in-this-section-7/cost-control-levers.md): Cost-control levers in Stratix — prompt caching pass-through, batch judges, sampling, BYOK.
- [Curate a regression test set](https://docs.layerlens.ai/more-in-this-section-7/curate-regression-set.md): Guide — curate a regression test set from production traces.
- [Optimize a judge with GEPA](https://docs.layerlens.ai/more-in-this-section-7/optimize-judge-gepa.md): Guide — optimize a judge with GEPA.
- [Reduce evaluation cost](https://docs.layerlens.ai/more-in-this-section-7/reduce-eval-cost.md): Guide — reduce evaluation cost without losing signal.
- [Integrations landing](https://docs.layerlens.ai/10.-integrate-connect-your-stack/10-integrate.md): Stratix integrations — platform integrations (Stratix Premium), SDK auto-instrumentation (stratix-python), CI/CD, BYOK.
- [Frameworks](https://docs.layerlens.ai/10.-integrate-connect-your-stack/frameworks.md)
- [LangChain](https://docs.layerlens.ai/10.-integrate-connect-your-stack/framework-langchain.md): LangChain integration — emit Stratix traces from LangChain chains.
- [LlamaIndex](https://docs.layerlens.ai/10.-integrate-connect-your-stack/framework-llamaindex.md): LlamaIndex integration — RAG pipeline traces in Stratix.
- [Haystack](https://docs.layerlens.ai/10.-integrate-connect-your-stack/framework-haystack.md): Haystack integration — emit traces from Haystack pipelines.
- [DSPy](https://docs.layerlens.ai/10.-integrate-connect-your-stack/framework-dspy.md): DSPy integration — emit traces from DSPy programs.
- [OpenAI Assistants](https://docs.layerlens.ai/10.-integrate-connect-your-stack/framework-openai-assistants.md): OpenAI Assistants integration — capture run traces.
- [Vercel AI SDK](https://docs.layerlens.ai/10.-integrate-connect-your-stack/framework-vercel-ai-sdk.md): Vercel AI SDK integration — emit traces from Next.js applications.
- [Anthropic SDK](https://docs.layerlens.ai/10.-integrate-connect-your-stack/framework-anthropic-sdk.md): Anthropic SDK integration — capture Messages API calls.
- [Custom Python](https://docs.layerlens.ai/10.-integrate-connect-your-stack/framework-custom-python.md): Custom Python integration — wrap your own agent.
- [LLM providers](https://docs.layerlens.ai/10.-integrate-connect-your-stack/llm-providers.md)
- [OpenAI](https://docs.layerlens.ai/10.-integrate-connect-your-stack/provider-openai.md): OpenAI integration — models, BYOK, instrumentation.
- [Anthropic](https://docs.layerlens.ai/10.-integrate-connect-your-stack/provider-anthropic.md): Anthropic integration — Claude models, BYOK, instrumentation.
- [Google](https://docs.layerlens.ai/10.-integrate-connect-your-stack/provider-google.md): Google integration — Gemini models.
- [Mistral](https://docs.layerlens.ai/10.-integrate-connect-your-stack/provider-mistral.md): Mistral integration — Mistral models.
- [Meta](https://docs.layerlens.ai/10.-integrate-connect-your-stack/provider-meta.md): Meta integration — Llama models.
- [Observability](https://docs.layerlens.ai/10.-integrate-connect-your-stack/observability.md)
- [OpenTelemetry](https://docs.layerlens.ai/10.-integrate-connect-your-stack/opentelemetry.md): OpenTelemetry — convert OTel spans to Stratix traces.
- [Partner clouds (BYOK / OpenAI-compatible)](https://docs.layerlens.ai/10.-integrate-connect-your-stack/partner-clouds.md): Partner-cloud integrations — Fireworks, Nebius, SambaNova, MLflow.
- [Cookbook](https://docs.layerlens.ai/10.-integrate-connect-your-stack/cookbook.md)
- [Send results to S3](https://docs.layerlens.ai/10.-integrate-connect-your-stack/integration-s3-export.md): Recipe — export evaluation results to S3.
- [Send results to BigQuery](https://docs.layerlens.ai/10.-integrate-connect-your-stack/integration-bigquery-export.md): Recipe — stream evaluation results into BigQuery.
- [Send results to Snowflake](https://docs.layerlens.ai/10.-integrate-connect-your-stack/integration-snowflake-export.md): Recipe — load Stratix results into Snowflake.
- [VS Code](https://docs.layerlens.ai/more-in-this-section-8/ide-vscode.md): VS Code extension.
- [Fireworks AI](https://docs.layerlens.ai/more-in-this-section-8/partner-fireworks.md): Fireworks AI integration.
- [MLflow gateway](https://docs.layerlens.ai/more-in-this-section-8/partner-mlflow.md): MLflow gateway integration.
- [Nebius](https://docs.layerlens.ai/more-in-this-section-8/partner-nebius.md): Nebius integration.
- [SambaNova Cloud](https://docs.layerlens.ai/more-in-this-section-8/partner-sambanova.md): SambaNova Cloud integration.
- [Admin](https://docs.layerlens.ai/11.-admin/11-admin.md): Admin — workspace administration for org admins, security leads, and IT.
- [Notifications](https://docs.layerlens.ai/11.-admin/notifications.md): In-app and email notifications in Stratix Premium — evaluations, traces, threshold crossings.
- [Settings](https://docs.layerlens.ai/11.-admin/settings.md): The Stratix Premium Settings surface — account, organizations, billing, integrations, API keys.
- [Organizations and multi-org](https://docs.layerlens.ai/11.-admin/organizations.md): Multi-org membership and switching in Stratix Premium.
- [Team management](https://docs.layerlens.ai/11.-admin/team-management.md): Invite teammates, manage roles, and watch seat utilization in Stratix Premium.
- [ECU credits and billing](https://docs.layerlens.ai/11.-admin/ecu-credits-billing.md): ECU credits, consumption, and billing in Stratix Premium.
- [ECU credits — concept](https://docs.layerlens.ai/11.-admin/concepts-ecu-credits.md): ECU credits — how compute consumption is metered and billed in Stratix Premium.
- [Onboarding wizard](https://docs.layerlens.ai/11.-admin/onboarding-wizard.md): The Stratix Premium onboarding wizard — tailored first-time setup based on your role and goals.
- [In-app Assistant](https://docs.layerlens.ai/11.-admin/in-app-assistant.md): The in-app Assistant in Stratix Premium — context-aware help inline.
- [Show tutorial](https://docs.layerlens.ai/11.-admin/show-tutorial.md): Re-run the Stratix Premium onboarding wizard at any time via Show tutorial.
- [Switch toggle (Public/Premium)](https://docs.layerlens.ai/11.-admin/switch-toggle.md): The Switch toggle in Stratix Premium — flip between Public-only and Premium-augmented catalog views.
- [Search (Premium)](https://docs.layerlens.ai/11.-admin/search-premium.md): The Stratix Premium global search — across catalog plus your org's private items.
- [Guides](https://docs.layerlens.ai/11.-admin/guides.md)
- [Invite team](https://docs.layerlens.ai/11.-admin/invite-team.md): Guide — invite teammates to your Stratix org.
- [Manage seats and roles](https://docs.layerlens.ai/11.-admin/manage-seats-roles.md): Guide — manage seats and roles in your org.
- [Manage ECU](https://docs.layerlens.ai/11.-admin/manage-ecu.md): Guide — buy and manage ECU credits.
- [Rotate API key](https://docs.layerlens.ai/11.-admin/rotate-api-key.md): Guide — rotate a Stratix API key without downtime.
- [Set up first org](https://docs.layerlens.ai/11.-admin/setup-first-org.md): Guide — set up your first Stratix organization.
- [Set up notifications](https://docs.layerlens.ai/11.-admin/setup-notifications.md): Guide — set up notifications and alerting.
- [Set up Slack](https://docs.layerlens.ai/11.-admin/setup-slack.md): Guide — set up Slack integration.
- [Set up SSO](https://docs.layerlens.ai/11.-admin/setup-sso.md): Guide — set up SSO (SAML/OIDC) for your enterprise.
- [Audit-friendly evidence](https://docs.layerlens.ai/11.-admin/audit-friendly-evidence.md): Guide — produce audit-friendly evaluation evidence per release.
- [Support](https://docs.layerlens.ai/12.-support/12-support.md): Stratix support — channels, FAQ, troubleshooting, contact.
- [Best practices](https://docs.layerlens.ai/12.-support/best-practices.md): Stratix best practices — quick reference for new users.
- [Community](https://docs.layerlens.ai/12.-support/community.md): Community channels — forums, Slack, docs feedback.
- [Contact](https://docs.layerlens.ai/12.-support/contact.md): How to reach Stratix support.
- [API troubleshooting](https://docs.layerlens.ai/12.-support/api-troubleshooting.md): API-specific troubleshooting.
- [SDK troubleshooting](https://docs.layerlens.ai/12.-support/sdk-troubleshooting.md): SDK-specific troubleshooting.
- [General troubleshooting](https://docs.layerlens.ai/12.-support/troubleshooting.md): Common Stratix issues and fixes.
- [FAQ](https://docs.layerlens.ai/12.-support/faq.md): Frequently-asked questions about Stratix.
- [Billing FAQ](https://docs.layerlens.ai/12.-support/billing-faq.md): Billing FAQ — ECU, invoices, plans, upgrades.
- [Overview FAQ](https://docs.layerlens.ai/12.-support/faq-overview.md): Quick FAQ for first-time visitors — what Stratix is, what it isn't, who it's for.
- [Glossary pointer](https://docs.layerlens.ai/12.-support/glossary-pointer.md): Pointer to the definitive Glossary.
- [Type stubs and IDE support](https://docs.layerlens.ai/13.1-sdk-and-apis/type-stubs.md): Type stubs and IDE autocomplete for the Stratix Python SDK.
- [Migrating SDK versions](https://docs.layerlens.ai/13.1-sdk-and-apis/migrating-sdk-versions.md): Migrate between Stratix SDK versions — breaking changes and replacement paths.
- [API reference (REST)](https://docs.layerlens.ai/13.1-sdk-and-apis/api.md): REST API reference — same surface the dashboard and SDK use.
- [Trace JSON Schema](https://docs.layerlens.ai/13.1-sdk-and-apis/trace-schema.md): Stratix Trace JSON Schema — formal specification of the trace payload.
- [CLI reference](https://docs.layerlens.ai/13.1-sdk-and-apis/cli.md): layerlens CLI reference — commands, arguments, examples.
- [Surfaces — where Stratix runs](https://docs.layerlens.ai/13.2-surfaces/surfaces.md): Stratix surfaces — every place you can interact with the platform.
- [Web (browser)](https://docs.layerlens.ai/13.2-surfaces/web.md): The Stratix web surface — anonymous Public catalog and signed-in Premium workspace at the same hostname.
- [Python SDK](https://docs.layerlens.ai/13.2-surfaces/python-sdk.md): The Stratix Python SDK — pip install layerlens --extra-index-url https://sdk.layerlens.ai/package, sync + async, 11 resources, 138 samples.
- [CLI](https://docs.layerlens.ai/13.2-surfaces/cli.md): The Stratix CLI — terminal access to evaluations, traces, and reports.
- [REST API](https://docs.layerlens.ai/13.2-surfaces/rest-api.md): The Stratix REST API — same surface the dashboard and SDK use.
- [Concepts library](https://docs.layerlens.ai/13.3-concepts-library-+-architecture/concepts-library.md): Stratix concepts — the mental model behind models, evaluations, judges, scorers, traces, and ECU.
- [Architecture deep dive](https://docs.layerlens.ai/13.3-concepts-library-+-architecture/architecture.md): How Stratix is built — catalog, evaluation engine, judge engine, trace pipeline, and the customer-facing experiences.
- [In-product Learning Portal](https://docs.layerlens.ai/13.4-learning-portal/learning-portal.md): Bridge from this documentation to the Stratix Premium Learning Portal.
- [Library overview](https://docs.layerlens.ai/13.4-learning-portal/library-overview.md): Stratix Learning Library overview — what's in it and how to find content.
- [Paths overview](https://docs.layerlens.ai/13.4-learning-portal/paths-overview.md): Stratix Learning Paths overview — structured curricula by role.
- [Premium Learning](https://docs.layerlens.ai/13.4-learning-portal/learning.md): The Stratix Premium Learning surface — Library and Paths.
- [Premium Learning Library](https://docs.layerlens.ai/13.4-learning-portal/learning-library.md): The Stratix Premium Learning Library — curated articles, recipes, and walkthroughs.
- [Premium Learning Paths](https://docs.layerlens.ai/13.4-learning-portal/learning-paths.md): The Stratix Premium Learning Paths — structured curricula for builders, operators, and admins.
- [Release notes](https://docs.layerlens.ai/13.5-operational/release-notes.md): Stratix release notes — platform, SDK, dashboard, and samples.
- [Latest releases](https://docs.layerlens.ai/13.5-operational/latest.md): Latest Stratix platform releases.
- [Release archive](https://docs.layerlens.ai/13.5-operational/archive.md): Historical release notes.
- [Status and reliability](https://docs.layerlens.ai/13.5-operational/status.md): Stratix status, reliability, health endpoints, and incident communication.
- [System judge implementation reference](https://docs.layerlens.ai/13.6-system-judges-implementation/system.md): Implementation reference for Stratix system judges — record shape, scoring contracts, and how they run.
- [Faithfulness implementation](https://docs.layerlens.ai/13.6-system-judges-implementation/faithfulness-implementation.md): The full Faithfulness system-judge rubric — scoring bands, inputs, output contract, and tuning.
- [Api](https://docs.layerlens.ai/more-in-this-section-9/api.md)
- [API keys](https://docs.layerlens.ai/more-in-this-section-9/api-keys.md): REST — API keys endpoints.
- [Authentication](https://docs.layerlens.ai/more-in-this-section-9/auth.md): API authentication — API keys, scopes, headers.
- [Benchmarks](https://docs.layerlens.ai/more-in-this-section-9/benchmarks.md): REST — Benchmarks endpoints.
- [BYOK custom models](https://docs.layerlens.ai/more-in-this-section-9/byok-models.md): REST — BYOK custom-model endpoints.
- [Errors](https://docs.layerlens.ai/more-in-this-section-9/errors.md): REST — error codes, response shape.
- [Evaluations](https://docs.layerlens.ai/more-in-this-section-9/evaluations.md): REST — Evaluations endpoints.
- [Judge optimizations (GEPA)](https://docs.layerlens.ai/more-in-this-section-9/judge-optimizations.md): REST — Judge optimization (GEPA) endpoints.
- [Judges](https://docs.layerlens.ai/more-in-this-section-9/judges.md): REST — Judges endpoints.
- [Models](https://docs.layerlens.ai/more-in-this-section-9/models.md): REST — Models endpoints.
- [Notifications](https://docs.layerlens.ai/more-in-this-section-9/notifications.md): REST — Notifications endpoints.
- [Organizations](https://docs.layerlens.ai/more-in-this-section-9/organizations.md): REST — Organizations endpoints.
- [Rate limits](https://docs.layerlens.ai/more-in-this-section-9/rate-limits.md): REST — rate limits and headers.
- [Scorers](https://docs.layerlens.ai/more-in-this-section-9/scorers.md): REST — Scorers endpoints.
- [Spaces](https://docs.layerlens.ai/more-in-this-section-9/spaces.md): REST — Spaces endpoints.
- [Trace evaluations](https://docs.layerlens.ai/more-in-this-section-9/trace-evaluations.md): REST — Trace evaluations endpoints.
- [Traces](https://docs.layerlens.ai/more-in-this-section-9/traces.md): REST — Traces endpoints.
- [Webhooks](https://docs.layerlens.ai/more-in-this-section-9/webhooks.md): REST — Webhook event payloads.
- [Cli](https://docs.layerlens.ai/more-in-this-section-9/cli.md)
- [layerlens benchmarks](https://docs.layerlens.ai/more-in-this-section-9/benchmarks-1.md): layerlens benchmarks — browse and upload.
- [layerlens config](https://docs.layerlens.ai/more-in-this-section-9/config.md): layerlens config — multi-profile, env, output format.
- [layerlens evaluate](https://docs.layerlens.ai/more-in-this-section-9/evaluate.md): layerlens evaluate — create and run an evaluation.
- [Examples](https://docs.layerlens.ai/more-in-this-section-9/examples.md): Common layerlens CLI command sequences.
- [CLI getting started](https://docs.layerlens.ai/more-in-this-section-9/getting-started.md): CLI getting started — install, login, first command.
- [layerlens judges](https://docs.layerlens.ai/more-in-this-section-9/judges-1.md): layerlens judges — create and manage LLM judges.
- [layerlens login](https://docs.layerlens.ai/more-in-this-section-9/login.md): layerlens login — interactive authentication.
- [layerlens models](https://docs.layerlens.ai/more-in-this-section-9/models-1.md): layerlens models — browse the catalog.
- [layerlens scorers](https://docs.layerlens.ai/more-in-this-section-9/scorers-1.md): layerlens scorers — manage code graders.
- [layerlens trace-evaluate](https://docs.layerlens.ai/more-in-this-section-9/trace-evaluate.md): layerlens trace-evaluate — score a trace set.
- [layerlens traces](https://docs.layerlens.ai/more-in-this-section-9/traces-1.md): layerlens traces — upload and browse traces.
- [Screenshots](https://docs.layerlens.ai/more-in-this-section-9/screenshots.md)
- [Screenshot inventory](https://docs.layerlens.ai/more-in-this-section-9/screenshots-1.md): Screenshot inventory and capture conventions.
- [Sdk Python](https://docs.layerlens.ai/more-in-this-section-9/sdk-python.md)
- [LangChain framework adapter](https://docs.layerlens.ai/more-in-this-section-9/frameworks-langchain.md): LangChain framework adapter — LayerLensCallbackHandler for chains, agents, tools, and memory.
- [Async patterns](https://docs.layerlens.ai/more-in-this-section-9/async-patterns.md): Async patterns — concurrency, gather, semaphore-bounded parallelism.
- [Authentication](https://docs.layerlens.ai/more-in-this-section-9/authentication.md): SDK authentication — API keys, env vars, key scoping.
- [CLI — Command Reference](https://docs.layerlens.ai/more-in-this-section-9/commands.md): Complete reference for every stratix CLI command — trace, judge, evaluate, scorer, space, bulk, ci.
- [CLI — Workflow Examples](https://docs.layerlens.ai/more-in-this-section-9/examples-1.md): Fifteen copy-paste CLI workflows covering traces, judges, evaluations, bulk runs, CI, and cleanup.
- [CLI — Getting Started](https://docs.layerlens.ai/more-in-this-section-9/getting-started-1.md): SDK CLI getting started — installation, configuration, output formats, shell completion.
- [Client configuration](https://docs.layerlens.ai/more-in-this-section-9/client.md): Stratix / AsyncStratix client — construction, env vars, timeout, retries, per-request overrides.
- [Errors](https://docs.layerlens.ai/more-in-this-section-9/errors-1.md): SDK exception hierarchy — StratixError → APIError → APIStatusError → HTTP-status-specific exceptions.
- [Evaluations](https://docs.layerlens.ai/more-in-this-section-9/evaluations-1.md): client.evaluations — create benchmark and dataset evaluations, wait for completion, list, retrieve results.
- [Code Examples](https://docs.layerlens.ai/more-in-this-section-9/examples-2.md): Code examples index — runnable samples for evaluations, traces, judges, public catalog.
- [Creating Evaluations](https://docs.layerlens.ai/more-in-this-section-9/creating-evaluations.md): Create evaluations — sync, async, parallel, comparison, error handling.
- [Judges and Traces](https://docs.layerlens.ai/more-in-this-section-9/judges-and-traces.md): Examples for judges and traces — create, list, update, delete; upload traces; run trace evaluations.
- [Models and Benchmarks](https://docs.layerlens.ai/more-in-this-section-9/models-and-benchmarks.md): Browse, filter, create custom/smart, and manage models and benchmarks.
- [Public API](https://docs.layerlens.ai/more-in-this-section-9/public-api.md): Public catalog examples — browse models, benchmarks, evaluations, compare results without auth scopes.
- [Retrieving Results](https://docs.layerlens.ai/more-in-this-section-9/retrieving-results.md): Retrieve evaluation results — paginated, bulk, and concurrent fetching patterns.
- [Judge optimizations](https://docs.layerlens.ai/more-in-this-section-9/judge-optimizations-1.md): client.judge\_optimizations — automated judge optimization (GEPA-style). Estimate, create, get, apply.
- [Judges](https://docs.layerlens.ai/more-in-this-section-9/judges-2.md): client.judges — CRUD for evaluation judges, with version-on-update semantics.
- [Models and benchmarks](https://docs.layerlens.ai/more-in-this-section-9/models-benchmarks.md): client.models and client.benchmarks — manage models, benchmarks, custom registrations, smart benchmarks.
- [Notifications (SDK)](https://docs.layerlens.ai/more-in-this-section-9/notifications-1.md): client.notifications — manage event subscriptions.
- [Organizations (SDK)](https://docs.layerlens.ai/more-in-this-section-9/organizations-1.md): Multi-org switching from the SDK.
- [Pagination](https://docs.layerlens.ai/more-in-this-section-9/pagination.md): Pagination over large list endpoints.
- [Public client](https://docs.layerlens.ai/more-in-this-section-9/public-client.md): PublicClient — read-only access to public catalog (models, benchmarks, evaluations, comparisons).
- [Recipe: pagination over large result sets](https://docs.layerlens.ai/more-in-this-section-9/pagination-1.md): Recipe — pagination. Pointer to the SDK paginated\_results sample.
- [Recipe: rate-limit handling](https://docs.layerlens.ai/more-in-this-section-9/rate-limit-handling.md): Recipe — rate-limit handling. Pointer to the SDK security guide.
- [Recipe: retry and backoff](https://docs.layerlens.ai/more-in-this-section-9/retry-backoff.md): Recipe — retry and backoff. Pointer to the SDK's built-in retry behaviour.
- [Recipe: sync vs async clients](https://docs.layerlens.ai/more-in-this-section-9/sync-async-clients.md): Recipe — sync vs async client. Pointer to the SDK async\_workflow sample.
- [SDK release notes](https://docs.layerlens.ai/more-in-this-section-9/release-notes-sdk.md): SDK-specific release notes.
- [Results](https://docs.layerlens.ai/more-in-this-section-9/results.md): client.results — fetch evaluation results, with auto-pagination helpers.
- [Scorers](https://docs.layerlens.ai/more-in-this-section-9/scorers-2.md): client.scorers — LLM-backed scorers (model + prompt). CRUD reference.
- [Security](https://docs.layerlens.ai/more-in-this-section-9/security.md): SDK security overview — API key management, data privacy, environment variables, rate limiting.
- [API Key Management](https://docs.layerlens.ai/more-in-this-section-9/api-key-management.md): API key management — secure storage, environment variables,.env files, rotation.
- [Data Privacy](https://docs.layerlens.ai/more-in-this-section-9/data-privacy.md): Data privacy — what the SDK transmits, how to sanitize traces, logging redaction.
- [Environment Variables](https://docs.layerlens.ai/more-in-this-section-9/environment-variables.md): Environment variables — required vars, OS-specific setup,.env file loading, verification.
- [Rate Limiting](https://docs.layerlens.ai/more-in-this-section-9/rate-limiting.md): Rate limiting — recognize 429 responses, handle RateLimitError, inspect retry headers.
- [Spaces (SDK)](https://docs.layerlens.ai/more-in-this-section-9/spaces-1.md): client.spaces — saved evaluation configurations.
- [Trace evaluations](https://docs.layerlens.ai/more-in-this-section-9/trace-evaluations-1.md): client.trace\_evaluations — run a judge against a trace, poll, retrieve results, estimate cost.
- [Traces](https://docs.layerlens.ai/more-in-this-section-9/traces-2.md): client.traces — upload trace files (JSON/JSONL, ≤50 MB), retrieve, list, delete.
- [SDK troubleshooting](https://docs.layerlens.ai/more-in-this-section-9/troubleshooting.md): SDK troubleshooting — installation, authentication, evaluation, trace upload, timeouts.
- [Troubleshooting](https://docs.layerlens.ai/more-in-this-section-9/troubleshooting-1.md): SDK troubleshooting index — authentication, common issues, error codes.
- [Authentication Problems](https://docs.layerlens.ai/more-in-this-section-9/authentication-1.md): Authentication troubleshooting — 401 errors, invalid keys, missing configuration.
- [Common Issues](https://docs.layerlens.ai/more-in-this-section-9/common-issues.md): Common SDK issues — installation, client init, evaluations, trace upload, timeouts, network.
- [Error Codes Reference](https://docs.layerlens.ai/more-in-this-section-9/error-codes.md): SDK error codes — full StratixError exception hierarchy and HTTP status mapping.
- [Type models (Pydantic)](https://docs.layerlens.ai/more-in-this-section-9/type-models.md): SDK Pydantic models — exhaustive list of types exported from the layerlens package.
- [Versioning](https://docs.layerlens.ai/more-in-this-section-9/versioning.md): SDK versioning, compatibility, deprecation policy.
- [Webhooks](https://docs.layerlens.ai/more-in-this-section-9/webhooks-1.md): Stratix webhooks — receive events at your endpoint.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on a page URL with the `ask` query parameter:
```
GET https://docs.layerlens.ai/readme.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.