Samples (70+ runnable)

Stratix Python SDK samples — categorized index of the runnable samples that ship with the SDK.

The LayerLens Python SDK ships with 70+ runnable samples covering every public resource — from a single trace evaluation to multi-agent evaluation patterns and CI/CD quality gates. All samples live in stratix-python/samples/ and run directly after installing the SDK.

Quick start

pip install layerlens --extra-index-url https://sdk.layerlens.ai/package
export LAYERLENS_STRATIX_API_KEY=your-api-key
python samples/core/quickstart.py

quickstart.py walks through the complete workflow end-to-end: upload a trace, create a judge, run an evaluation, and retrieve results.

Samples by category

Each category groups samples around a specific Stratix capability or integration surface. Pick the category closest to what you're building.

Category	What's in it	Count
Core SDK operations	Every public resource — traces, judges, evaluations, results, models, benchmarks — used individually and together, including async patterns and pagination	18
Industry solutions	Domain-specific evaluation scenarios with judges tuned for regulated and high-stakes verticals (healthcare, financial services, legal, government, insurance, retail)	10
Multi-agent evaluation	Patterns for evaluating multi-agent collaboration where each agent's output needs independent quality assessment	5
Content-type evaluations	Specialized judges applied to different content types — text responses, brand assets, structured documents	3
CI/CD integration	Quality gates that embed evaluation into build and deployment pipelines so regressions never reach production	2 + workflow
LLM provider integrations	Trace and evaluate outputs from OpenAI and Anthropic — both manual trace upload and auto-instrumentation paths	4
OpenClaw agent evaluation	Trace, evaluate, and monitor OpenClaw autonomous AI agents — cage-match tournaments, code gating, drift detection, content auditing	10 + skill
MCP server	Expose Stratix capabilities as tools for Claude, Cursor, and any MCP-compatible AI assistant	1
CopilotKit integration	Full-stack pattern with LangGraph CoAgents + generative-UI cards for human-in-the-loop evaluation workflows	2 agents + UI
Claude Code skills	Slash commands that bring Stratix workflows into the Claude Code CLI	6
Sample data	Pre-built trace files and 16 industry-specific evaluation datasets so every sample runs without sourcing your own data	n/a

---

Core SDK operations

Located in samples/core/. Start here to learn how every public Stratix resource works, individually and combined.

Key samples:

• quickstart.py — first evaluation in under 30 lines
• trace_evaluation.py — full trace-evaluation lifecycle
• judge_optimization.py — optimize a judge via automated prompt evolution (GEPA)
• evaluation_pipeline.py — chain judges, traces, and results into an automated pipeline
• async_workflow.py — concurrent operations with AsyncStratix

See the Core SDK README. Maps to gitbook: Tutorials · Concept: Evaluations.

Industry solutions

Located in samples/industry/. Domain-specific scenarios with judges and scoring configurations tuned for regulated and high-stakes verticals.

Key samples:

• healthcare_clinical.py — clinical decision support evaluation
• financial_trading.py — SOX-aligned trading compliance
• legal_contracts.py — contract review quality assessment

See the Industry Solutions README. Maps to gitbook: Industry patterns.

Multi-agent evaluation

Located in samples/cowork/. Patterns for evaluating multi-agent collaboration — applicable to any framework where multiple agents produce intermediate outputs that need independent quality assessment.

Key samples:

• multi_agent_eval.py — Generator-Evaluator pattern
• code_review.py — Instrumentor-Reviewer pattern
• rag_assessment.py — RAG-quality evaluation

See the Multi-Agent README. Maps to gitbook: Concept: Agentic evaluation.

Content-type evaluations

Located in samples/modalities/. Specialized judges applied to different content types.

• text_evaluation.py — score text across safety, relevance, and compliance
• brand_evaluation.py — enforce brand-voice consistency
• document_evaluation.py — validate document-extraction accuracy

CI/CD integration

Located in samples/cicd/. Embed evaluation quality gates into build and deployment pipelines.

• quality_gate.py — gate deployments on evaluation pass rates
• pre_commit_hook.py — catch regressions at commit time
• github_actions_gate.yml — drop-in GitHub Actions workflow

See the CI/CD README. Maps to gitbook: Tutorial 3: CI/CD gates · Cookbook: containerized CI.

LLM provider integrations

Located in samples/integrations/. Two paths: manual trace upload for full control, and auto-instrumentation via layerlens.instrument for zero-code observability.

• openai_traced.py — manual trace upload around an OpenAI completion
• anthropic_traced.py — capture multi-turn Claude conversations (manual trace upload)
• openai_instrumented.py — auto-instrument OpenAI with instrument_openai(), @trace, span()
• langchain_instrumented.py — auto-capture LangChain chain execution with LangChainCallbackHandler

Maps to gitbook: Integrations.

OpenClaw agent evaluation

Located in samples/openclaw/. Trace, evaluate, and monitor OpenClaw autonomous AI agents — including cage-match model tournaments, code gating, drift detection, content auditing, honeypot-skill auditing, and adversarial red-teaming.

See the OpenClaw README for the full list and advanced evaluation patterns.

MCP server

Located in samples/mcp/. Expose Stratix capabilities as tools for Claude, Cursor, and any MCP-compatible AI assistant.

• layerlens_server.py — MCP server exposing trace management, judge creation, and evaluation execution

See the MCP README for setup.

CopilotKit integration

Located in samples/copilotkit/. Full-stack pattern combining LangGraph CoAgents (Python) with generative-UI card components (React) for human-in-the-loop evaluation workflows.

• agents/evaluator_agent.py — LangGraph CoAgent for evaluation workflows (uses interrupt() for human-in-the-loop judge confirmation)
• agents/investigator_agent.py — LangGraph CoAgent for trace investigation
• components/*.tsx — React card components for rendering results (EvaluationCard, JudgeVerdictCard, TraceCard, MetricCard, ComplianceCard)
• hooks/*.ts — CopilotKit hooks for wiring Stratix actions (useLayerLensActions, useLayerLensContext)

Checkpointer note: any LangGraph CoAgent that calls interrupt() (such as evaluator_agent.py) must be compiled with a checkpointer. Without one, the AG-UI stream ends without emitting RUN_FINISHED and CopilotKit blocks all subsequent messages. The sample ships with InMemorySaver for a zero-setup local run; the README documents Postgres / SQLite / Redis / LangGraph Platform alternatives for production.

See the CopilotKit README for setup, full file list, and the human-in-the-loop walkthrough.

Claude Code skills

Located in samples/claude-code/. Slash commands that bring Stratix workflows directly into the Claude Code CLI — manage traces, judges, evaluations, optimizations, benchmarks, and investigations without leaving your terminal.

/trace, /judge, /evaluate, /optimize, /benchmark, /investigate. See the Claude Code Skills README.

Sample data

Located in samples/data/. Pre-built trace files, test datasets, and 16 industry-specific evaluation datasets so every sample runs without you sourcing your own data first.

See the Sample Data README for contents.

---

Full sample reference

For the complete table of every sample with descriptions, see the samples README in the SDK repo.

Where to next

• SDK README — full resource list
• Cookbook — recipes drawn from these samples
• Integrations — full adapter list
• Tutorials — guided walkthroughs anchored to these samples