# Ab Testing Ml > A/B testing compares ML models in production. This guide covers experiment Use when this capability is needed. - Skill: `tomevault-io/ab-testing-ml` (Agent Skill, multi-file: 2 files) - Install (CLI): `npx skillmds@latest add tomevault-io/ab-testing-ml` - Raw SKILL.md: https://api.skillmd.com/api/skills/tomevault-io/ab-testing-ml/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Coding & Dev Tools - Author: tomevault-io (https://skillmd.com/u/tomevault-io) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/tomevault-io/ab-testing-ml --- # Ab Testing Ml ## Skill Profile *(Select at least one profile to enable specific modules)* - [ ] **DevOps** - [x] **Backend** - [ ] **Frontend** - [ ] **AI-RAG** - [ ] **Security Critical** ## Overview A/B testing compares ML models in production. This guide covers experiment design, statistical testing, multi-armed bandits, and monitoring for safely deploying and comparing ML models to determine which performs better on business metrics. ## Why This Matters - **Risk Mitigation**: A/B testing allows safe model deployment with gradual rollout - **Data-Driven Decisions**: Statistical testing ensures decisions are based on significant results - **Business Impact**: Multi-armed bandits optimize for business metrics during experimentation --- ## Core Concepts & Rules ### 1. Core Principles - Follow established patterns and conventions - Maintain consistency across codebase - Document decisions and trade-offs ### 2. Implementation Guidelines - Start with the simplest viable solution - Iterate based on feedback and requirements - Test thoroughly before deployment ## Inputs / Outputs / Contracts * **Inputs**: - User ID for consistent variant assignment - Features for model prediction - Actual outcomes for metric calculation * **Entry Conditions**: - Two or more models ready for production - Sufficient traffic for statistical significance - Metrics tracking infrastructure in place * **Outputs**: - Variant assignment (A/B) - Model prediction with variant info - Statistical test results (p-value, significance) - Winner recommendation * **Artifacts Required (Deliverables)**: - Experiment design configuration - Traffic splitting logic - Statistical testing implementation - Multi-armed bandit algorithms - Monitoring dashboard * **Acceptance Evidence**: - A/B test API endpoints functional - Statistical tests passing - Monitoring dashboard showing results * **Success Criteria**: - Statistical significance (p < 0.05) - Minimum sample size achieved - Business metrics improvement validated ## Skill Composition * **Depends on**: ML models, Metrics tracking, Feature flags * **Compatible with**: ML Serving, Model Experiments, Feature Engineering * **Conflicts with**: None * **Related Skills**: [ml-serving](39-data-science-ml/ml-serving/SKILL.md), [model-experiments](39-data-science-ml/model-experiments/SKILL.md), [feature-engineering](39-data-science-ml/feature-engineering/SKILL.md) --- ## Quick Start / Implementation Example 1. Review requirements and constraints 2. Set up development environment 3. Implement core functionality following patterns 4. Write tests for critical paths 5. Run tests and fix issues 6. Document any deviations or decisions ```python # Example implementation following best practices def example_function(): # Your implementation here pass ``` ## Assumptions / Constraints / Non-goals * **Assumptions**: - Development environment is properly configured - Required dependencies are available - Team has basic understanding of domain * **Constraints**: - Must follow existing codebase conventions - Time and resource limitations - Compatibility requirements * **Non-goals**: - This skill does not cover edge cases outside scope - Not a replacement for formal training ## Compatibility & Prerequisites * **Supported Versions**: - Python 3.8+ - Node.js 16+ - Modern browsers (Chrome, Firefox, Safari, Edge) * **Required AI Tools**: - Code editor (VS Code recommended) - Testing framework appropriate for language - Version control (Git) * **Dependencies**: - Language-specific package manager - Build tools - Testing libraries * **Environment Setup**: - `.env.example` keys: `API_KEY`, `DATABASE_URL` (no values) ## Test Scenario Matrix (QA Strategy) | Type | Focus Area | Required Scenarios / Mocks | | :--- | :--- | :--- | | **Unit** | Core Logic | Must cover primary logic and at least 3 edge/error cases. Target minimum 80% coverage | | **Integration** | DB / API | All external API calls or database connections must be mocked during unit tests | | **E2E** | User Journey | Critical user flows to test | | **Performance** | Latency / Load | Benchmark requirements | | **Security** | Vuln / Auth | SAST/DAST or dependency audit | | **Frontend** | UX / A11y | Accessibility checklist (WCAG), Performance Budget (Lighthouse score) | ## Technical Guardrails & Security Threat Model ### 1. Security & Privacy (Threat Model) * **Top Threats**: Injection attacks, authentication bypass, data exposure - [ ] **Data Handling**: Sanitize all user inputs to prevent Injection attacks. Never log raw PII - [ ] **Secrets Management**: No hardcoded API keys. Use Env Vars/Secrets Manager - [ ] **Authorization**: Validate user permissions before state changes ### 2. Performance & Resources - [ ] **Execution Efficiency**: Consider time complexity for algorithms - [ ] **Memory Management**: Use streams/pagination for large data - [ ] **Resource Cleanup**: Close DB connections/file handlers in finally blocks ### 3. Architecture & Scalability - [ ] **Design Pattern**: Follow SOLID principles, use Dependency Injection - [ ] **Modularity**: Decouple logic from UI/Frameworks ### 4. Observability & Reliability - [ ] **Logging Standards**: Structured JSON, include trace IDs `request_id` - [ ] **Metrics**: Track `error_rate`, `latency`, `queue_depth` - [ ] **Error Handling**: Standardized error codes, no bare except - [ ] **Observability Artifacts**: - **Log Fields**: timestamp, level, message, request_id - **Metrics**: request_count, error_count, response_time - **Dashboards/Alerts**: High Error Rate > 5% ## Agent Directives & Error Recovery *(ข้อกำหนดสำหรับ AI Agent ในการคิดและแก้ปัญหาเมื่อเกิดข้อผิดพลาด)* - **Thinking Process**: Analyze root cause before fixing. Do not brute-force. - **Fallback Strategy**: Stop after 3 failed test attempts. Output root cause and ask for human intervention/clarification. - **Self-Review**: Check against Guardrails & Anti-patterns before finalizing. - **Output Constraints**: Output ONLY the modified code block. Do not explain unless asked. ## Definition of Done (DoD) Checklist - [ ] Tests passed + coverage met - [ ] Lint/Typecheck passed - [ ] Logging/Metrics/Trace implemented - [ ] Security checks passed - [ ] Documentation/Changelog updated - [ ] Accessibility/Performance requirements met (if frontend) ## Anti-patterns # ## Reference Links & Examples * Internal documentation and examples * Official documentation and best practices * Community resources and discussions ## Versioning & Changelog * **Version**: 1.0.0 * **Changelog**: - 2026-02-22: Initial version with complete template structure --- > Converted and distributed by [TomeVault](https://tomevault.io/claim/amnadtaowsoam) — claim your Tome and manage your conversions.