# Rubric

## Docs

- [API Keys](https://api.therubric.ai/api-reference/authentication/api-keys.md): Create and manage API keys for authentication.
- [OAuth 2.0 / SSO](https://api.therubric.ai/api-reference/authentication/oauth.md): Enterprise single sign-on integration via OAuth 2.0.
- [Authentication Overview](https://api.therubric.ai/api-reference/authentication/overview.md): Secure your API requests with authentication.
- [Scopes & Permissions](https://api.therubric.ai/api-reference/authentication/scopes.md): Control API access with granular scopes.
- [Create Dataset](https://api.therubric.ai/api-reference/datasets/create.md): Create a new dataset for evaluation.
- [Delete Dataset](https://api.therubric.ai/api-reference/datasets/delete.md): Delete a dataset and all its samples.
- [Get Dataset](https://api.therubric.ai/api-reference/datasets/get.md): Retrieve a dataset by ID.
- [List Datasets](https://api.therubric.ai/api-reference/datasets/list.md): List all datasets in a project.
- [Datasets Overview](https://api.therubric.ai/api-reference/datasets/overview.md): Manage collections of samples for evaluation.
- [Update Dataset](https://api.therubric.ai/api-reference/datasets/update.md): Update dataset metadata.
- [Error Code Reference](https://api.therubric.ai/api-reference/errors/codes.md): Complete list of API error codes.
- [Error Format](https://api.therubric.ai/api-reference/errors/overview.md): Understanding API error responses.
- [Retry & Backoff Strategy](https://api.therubric.ai/api-reference/errors/retry.md): How to handle transient failures.
- [Cancel Evaluation](https://api.therubric.ai/api-reference/evaluations/cancel.md): Cancel a running evaluation.
- [Compare Evaluations](https://api.therubric.ai/api-reference/evaluations/compare.md): Compare results across multiple evaluations.
- [Create Evaluation](https://api.therubric.ai/api-reference/evaluations/create.md): Create a new evaluation to assess a dataset using one or more evaluators.
- [Get Evaluation](https://api.therubric.ai/api-reference/evaluations/get.md): Get evaluation details and results.
- [List Evaluations](https://api.therubric.ai/api-reference/evaluations/list.md): List all evaluations.
- [Evaluations Overview](https://api.therubric.ai/api-reference/evaluations/overview.md): Run and manage clinical AI evaluations.
- [Get Evaluation Status](https://api.therubric.ai/api-reference/evaluations/status.md): Check evaluation progress.
- [API Reference](https://api.therubric.ai/api-reference/introduction.md): The Rubric API is organized around REST. Our API accepts JSON-encoded request bodies, returns JSON-encoded responses, and uses standard HTTP response codes.
- [Get Model](https://api.therubric.ai/api-reference/models/get.md): Get model details.
- [List Models](https://api.therubric.ai/api-reference/models/list.md): List all registered models.
- [Models Overview](https://api.therubric.ai/api-reference/models/overview.md): Register and track AI model versions.
- [Register Model](https://api.therubric.ai/api-reference/models/register.md): Register a new model.
- [Model Versions](https://api.therubric.ai/api-reference/models/versions.md): List all versions of a model.
- [Pagination & Filtering](https://api.therubric.ai/api-reference/overview/pagination.md): Navigate large result sets with cursor-based pagination.
- [Request Format](https://api.therubric.ai/api-reference/overview/request-format.md): How to format API requests to the Rubric API.
- [Versioning & Stability](https://api.therubric.ai/api-reference/overview/versioning.md): API versioning policy and stability guarantees.
- [Headers & Monitoring](https://api.therubric.ai/api-reference/rate-limits/headers.md): Monitor your rate limit usage via response headers.
- [Rate Limits](https://api.therubric.ai/api-reference/rate-limits/overview.md): API rate limiting policies.
- [Reviewers Overview](https://api.therubric.ai/api-reference/reviewers/overview.md): Manage clinician reviewers.
- [Reviews Overview](https://api.therubric.ai/api-reference/reviews/overview.md): Human review submissions and management.
- [Rubrics Overview](https://api.therubric.ai/api-reference/rubrics/overview.md): Define grading criteria for human review.
- [Batch Upload](https://api.therubric.ai/api-reference/samples/batch.md): Upload multiple samples at once.
- [Create Sample](https://api.therubric.ai/api-reference/samples/create.md): Add a sample to a dataset.
- [Get Sample](https://api.therubric.ai/api-reference/samples/get.md): Retrieve a sample by ID.
- [List Samples](https://api.therubric.ai/api-reference/samples/list.md): List samples in a dataset.
- [Samples Overview](https://api.therubric.ai/api-reference/samples/overview.md): Individual data points within datasets.
- [Schemas by Modality](https://api.therubric.ai/api-reference/samples/schemas.md): Sample schemas for different data types.
- [Scores Overview](https://api.therubric.ai/api-reference/scores/overview.md): Retrieve and analyze evaluation scores.
- [SDKs Overview](https://api.therubric.ai/api-reference/sdks/overview.md): Official client libraries for the Rubric API.
- [Python SDK](https://api.therubric.ai/api-reference/sdks/python.md): Complete reference for the Rubric Python SDK.
- [Tasks Overview](https://api.therubric.ai/api-reference/tasks/overview.md): Background tasks and job management.
- [Webhooks Overview](https://api.therubric.ai/api-reference/webhooks/overview.md): Receive real-time notifications for events.
- [Rubric vs. Alternatives](https://api.therubric.ai/docs/comparison.md): How Rubric compares to general-purpose LLM evaluation tools and why healthcare AI needs specialized evaluation.
- [Clinical Evaluations](https://api.therubric.ai/docs/core-concepts/clinical-evaluations.md): Understanding when clinical expertise is required for AI evaluation, credential requirements, and regulatory considerations.
- [Evaluation Lifecycle](https://api.therubric.ai/docs/core-concepts/evaluation-lifecycle.md): Understanding evaluation states, triggers, progress monitoring, and error handling.
- [Human vs Automated Evaluation](https://api.therubric.ai/docs/core-concepts/human-vs-automated.md): Understanding when to use automated evaluators versus human review, and how to combine them effectively.
- [Core Objects](https://api.therubric.ai/docs/core-concepts/objects.md): Understanding Rubric's fundamental data model: Datasets, Tasks, Models, Evaluations, Reviewers, and Scores.
- [Human Expert Network](https://api.therubric.ai/docs/evaluation-framework/human-expert-network.md): Rubric's network of credentialed healthcare professionals provides expert review for AI outputs that require clinical judgment.
- [Human Review Design](https://api.therubric.ai/docs/evaluation-framework/human-review-design.md): Best practices for designing effective clinician review workflows that capture expert judgment while maintaining efficiency and consistency.
- [Metrics Reference](https://api.therubric.ai/docs/evaluation-framework/metrics.md): Quantitative measures for healthcare AI evaluation. Each metric is designed for clinical interpretability and regulatory documentation.
- [Evaluation Framework](https://api.therubric.ai/docs/evaluation-framework/overview.md): A comprehensive framework for evaluating healthcare AI systems across clinical accuracy, patient safety, and regulatory compliance dimensions.
- [Evaluation Types](https://api.therubric.ai/docs/evaluation-framework/types.md): Rubric provides specialized evaluators designed for healthcare AI assessment. Each evaluator targets a specific dimension of clinical AI performance.
- [Evaluation Versioning](https://api.therubric.ai/docs/evaluation-framework/versioning.md): Track evaluation configurations over time, compare model versions, and ensure reproducible results for regulatory compliance and scientific rigor.
- [Create Your First Evaluation](https://api.therubric.ai/docs/getting-started/first-evaluation.md): Step-by-step guide to creating a dataset, adding samples, selecting evaluators, and viewing results.
- [Quickstart](https://api.therubric.ai/docs/getting-started/quickstart.md): Get started with Rubric in 5 minutes. Install the SDK, log your first call, and see evaluation results.
- [Sandbox Environment](https://api.therubric.ai/docs/getting-started/sandbox.md): Explore Rubric with pre-loaded healthcare data. No setup required — start evaluating immediately.
- [Account Setup](https://api.therubric.ai/docs/getting-started/setup.md): Complete guide to setting up your Rubric account, workspace, team, and security settings.
- [AI / ML Metrics Definitions](https://api.therubric.ai/docs/glossary-appendix/ai-ml-metrics.md): Definitions of machine learning metrics, evaluation measures, and performance indicators used in healthcare AI assessment
- [Healthcare & Clinical Terms](https://api.therubric.ai/docs/glossary-appendix/healthcare-terms.md): Glossary of medical terminology, clinical concepts, and healthcare standards used throughout Rubric
- [Regulatory References](https://api.therubric.ai/docs/glossary-appendix/regulatory-references.md): Reference guide for healthcare regulations, compliance frameworks, and legal requirements relevant to healthcare AI evaluation
- [Evaluation Rubrics Library](https://api.therubric.ai/docs/glossary-appendix/rubrics-library.md): Pre-built evaluation rubrics for healthcare AI assessment across triage, clinical documentation, imaging, and safety domains
- [DICOM & Medical Imaging](https://api.therubric.ai/docs/images/dicom.md): Evaluate radiology AI for detection accuracy, localization, and report quality.
- [Pathology (WSI)](https://api.therubric.ai/docs/images/pathology.md): Evaluate whole-slide imaging AI for digital pathology applications.
- [Custom Pipelines](https://api.therubric.ai/docs/integrations/custom-pipelines.md): Build custom data flows and evaluation pipelines using Rubric's SDK and REST APIs. Integrate with your existing ML infrastructure, CI/CD systems, and orchestration tools.
- [Data Warehouses](https://api.therubric.ai/docs/integrations/data-warehouses.md): Export evaluation data to Snowflake, BigQuery, Redshift, and Databricks for analytics and reporting.
- [EHR Integration](https://api.therubric.ai/docs/integrations/ehr.md): Connect Rubric to Epic, Cerner, and other Electronic Health Record systems for clinical AI evaluation.
- [FHIR Integration](https://api.therubric.ai/docs/integrations/fhir.md): Standards-based healthcare data exchange using FHIR R4 for interoperable AI evaluation.
- [LLM Providers](https://api.therubric.ai/docs/integrations/llm-providers.md): Connect Rubric to OpenAI, Anthropic, Azure OpenAI, Google Vertex AI, and custom model endpoints for comprehensive AI evaluation.
- [Integrations Overview](https://api.therubric.ai/docs/integrations/overview.md): Connect Rubric to your existing infrastructure, data sources, and healthcare systems.
- [Webhooks & Events](https://api.therubric.ai/docs/integrations/webhooks.md): Receive real-time notifications for evaluation events via webhooks and event streams.
- [Introduction to Rubric](https://api.therubric.ai/docs/introduction.md): The evaluation platform for healthcare voice AI. Ensure your patient-facing AI agents triage correctly, follow clinical guidelines, and never miss critical symptoms.
- [Clinical Documentation](https://api.therubric.ai/docs/notes/clinical.md): Detailed guide to evaluating AI-generated clinical documentation.
- [Clinical Notes Overview](https://api.therubric.ai/docs/notes/overview.md): Evaluate AI-generated clinical documentation for accuracy, completeness, and compliance.
- [Evaluating Clinical NLP Models](https://api.therubric.ai/docs/onboarding/clinical-nlp.md): Guide for teams with custom NER, classification, or extraction models for clinical text processing — ICD coding, entity recognition, note classification, and more.
- [Evaluating LLM Applications](https://api.therubric.ai/docs/onboarding/evaluating-llm.md): Guide for teams building LLM-powered healthcare features — chatbots, Q&A systems, summarization, and more.
- [Evaluating Voice & Multimodal AI](https://api.therubric.ai/docs/onboarding/voice-multimodal.md): Guide for teams building voice-based patient triage, clinical call centers, or multimodal systems combining audio, transcripts, and clinical reasoning.
- [Platform Capabilities](https://api.therubric.ai/docs/platform-capabilities.md): Everything Rubric offers for evaluating healthcare AI — from data ingestion to clinician review workflows.
- [Access Logging](https://api.therubric.ai/docs/security-compliance/access-logging.md): Comprehensive audit trails capturing all access to PHI and system operations. Immutable logs with 7-year retention for HIPAA compliance and forensic analysis.
- [Data Retention & Deletion](https://api.therubric.ai/docs/security-compliance/data-retention.md): Configurable retention policies with cryptographic deletion guarantees. Meet regulatory requirements while maintaining operational efficiency and supporting patient rights to data deletion.
- [Encryption](https://api.therubric.ai/docs/security-compliance/encryption.md): Comprehensive encryption controls protecting PHI at rest and in transit. All data is encrypted using industry-standard algorithms with customer-managed key options for enterprise deployments.
- [Security & Compliance](https://api.therubric.ai/docs/security-compliance/overview.md): Rubric is built from the ground up for healthcare. We maintain rigorous security controls and compliance certifications to protect patient data throughout the evaluation lifecycle.
- [PHI Handling](https://api.therubric.ai/docs/security-compliance/phi-handling.md): Rubric implements comprehensive controls for Protected Health Information (PHI) throughout the evaluation lifecycle, ensuring HIPAA compliance at every step.
- [Deploy Evaluations in CI/CD](https://api.therubric.ai/docs/tutorials/ci-cd.md): Integrate Rubric evaluations into your continuous integration pipeline to catch regressions before they reach production.
- [Evaluate a Clinical NLP Model](https://api.therubric.ai/docs/tutorials/clinical-nlp.md): Step-by-step guide to evaluating a clinical note summarization model for accuracy, completeness, and safety.
- [Export Results for Regulators](https://api.therubric.ai/docs/tutorials/export.md): Generate comprehensive evaluation reports, audit trails, and compliance documentation for FDA submissions, SOC 2 audits, and regulatory inspections.
- [Continuous Monitoring in Production](https://api.therubric.ai/docs/tutorials/monitoring.md): Set up real-time monitoring for your healthcare AI to detect performance degradation and safety issues before they impact patients.
- [Evaluate RAG for Clinical Summaries](https://api.therubric.ai/docs/tutorials/rag-evaluation.md): Evaluate Retrieval-Augmented Generation systems that synthesize clinical information from patient records, medical literature, and clinical guidelines.
- [Safety Gating Before Production](https://api.therubric.ai/docs/tutorials/safety-gating.md): Implement automated safety gates that block deployment of clinical AI models that don't meet safety thresholds. Never ship a model that misses red flags.
- [Evaluate a Medical Voice Agent](https://api.therubric.ai/docs/tutorials/voice-agent.md): Complete guide to evaluating patient-facing voice triage AI for clinical accuracy, safety, and conversation quality.
- [Voice AI Overview](https://api.therubric.ai/docs/voice/overview.md): Evaluate patient-facing voice agents for triage accuracy, safety, and clinical compliance.
- [Transcripts & Audio](https://api.therubric.ai/docs/voice/transcripts.md): Audio processing, transcript formats, and speaker diarization for voice AI evaluation.
- [Patient Triage](https://api.therubric.ai/docs/voice/triage.md): Evaluate AI triage decisions for accuracy, safety, and appropriate escalation.
- [Clinician Review](https://api.therubric.ai/docs/workflows/clinician-review.md): Route flagged AI outputs to physicians and nurses for expert human review.