# EvalGate

## Docs

- [accept](https://evalgate.com/docs/api-reference/accept.md)
- [alerts](https://evalgate.com/docs/api-reference/alerts.md)
- [analyze](https://evalgate.com/docs/api-reference/analyze.md)
- [analyze](https://evalgate.com/docs/api-reference/analyze-1.md)
- [annotations](https://evalgate.com/docs/api-reference/annotations.md)
- [api-keys](https://evalgate.com/docs/api-reference/api-keys.md)
- [arena-matches](https://evalgate.com/docs/api-reference/arena-matches.md)
- [artifacts](https://evalgate.com/docs/api-reference/artifacts.md)
- [audit-logs](https://evalgate.com/docs/api-reference/audit-logs.md)
- [auto-plan](https://evalgate.com/docs/api-reference/auto-plan.md)
- [auto-sessions](https://evalgate.com/docs/api-reference/auto-sessions.md)
- [benchmarks](https://evalgate.com/docs/api-reference/benchmarks.md)
- [bulk-retry](https://evalgate.com/docs/api-reference/bulk-retry.md)
- [by id](https://evalgate.com/docs/api-reference/by-id.md)
- [by id](https://evalgate.com/docs/api-reference/by-id-1.md)
- [by id](https://evalgate.com/docs/api-reference/by-id-10.md)
- [by id](https://evalgate.com/docs/api-reference/by-id-11.md)
- [by id](https://evalgate.com/docs/api-reference/by-id-12.md)
- [by id](https://evalgate.com/docs/api-reference/by-id-13.md)
- [by id](https://evalgate.com/docs/api-reference/by-id-14.md)
- [by id](https://evalgate.com/docs/api-reference/by-id-15.md)
- [by id](https://evalgate.com/docs/api-reference/by-id-16.md)
- [by id](https://evalgate.com/docs/api-reference/by-id-2.md)
- [by id](https://evalgate.com/docs/api-reference/by-id-3.md)
- [by id](https://evalgate.com/docs/api-reference/by-id-4.md)
- [by id](https://evalgate.com/docs/api-reference/by-id-5.md)
- [by id](https://evalgate.com/docs/api-reference/by-id-6.md)
- [by id](https://evalgate.com/docs/api-reference/by-id-7.md)
- [by id](https://evalgate.com/docs/api-reference/by-id-8.md)
- [by id](https://evalgate.com/docs/api-reference/by-id-9.md)
- [candidates](https://evalgate.com/docs/api-reference/candidates.md)
- [cluster](https://evalgate.com/docs/api-reference/cluster.md)
- [collector](https://evalgate.com/docs/api-reference/collector.md)
- [Batch Trace Ingestion](https://evalgate.com/docs/api-reference/collector/batch-trace-ingestion.md): Ingest up to 100 execution traces in a single request
- [Ingest Trace](https://evalgate.com/docs/api-reference/collector/ingest-trace.md): Ingest a single execution trace from the SDK or any HTTP client
- [compare](https://evalgate.com/docs/api-reference/compare.md)
- [configs](https://evalgate.com/docs/api-reference/configs.md)
- [costs](https://evalgate.com/docs/api-reference/costs.md)
- [Create signed report](https://evalgate.com/docs/api-reference/create-signed-report.md)
- [current](https://evalgate.com/docs/api-reference/current.md)
- [dataset](https://evalgate.com/docs/api-reference/dataset.md)
- [dead](https://evalgate.com/docs/api-reference/dead.md)
- [decisions](https://evalgate.com/docs/api-reference/decisions.md)
- [deliveries](https://evalgate.com/docs/api-reference/deliveries.md)
- [discover-diversity](https://evalgate.com/docs/api-reference/discover-diversity.md)
- [evaluate](https://evalgate.com/docs/api-reference/evaluate.md)
- [evaluation-templates](https://evalgate.com/docs/api-reference/evaluation-templates.md)
- [evaluations](https://evalgate.com/docs/api-reference/evaluations.md)
- [Create Evaluation Schedule](https://evalgate.com/docs/api-reference/evaluations/create-evaluation-schedule.md): Schedule recurring evaluation runs using a cron expression
- [Delete Evaluation Schedule](https://evalgate.com/docs/api-reference/evaluations/delete-evaluation-schedule.md): Remove a scheduled evaluation
- [Get Evaluation Schedule](https://evalgate.com/docs/api-reference/evaluations/get-evaluation-schedule.md): Retrieve the current schedule configuration for an evaluation
- [Update Evaluation Schedule](https://evalgate.com/docs/api-reference/evaluations/update-evaluation-schedule.md): Update schedule configuration
- [Execute MCP tool](https://evalgate.com/docs/api-reference/execute-mcp-tool.md)
- [export](https://evalgate.com/docs/api-reference/export.md)
- [Export evaluation run](https://evalgate.com/docs/api-reference/export-evaluation-run.md)
- [feedback](https://evalgate.com/docs/api-reference/feedback.md)
- [Get LLM judge alignment for an evaluation run](https://evalgate.com/docs/api-reference/get-llm-judge-alignment-for-an-evaluation-run.md)
- [Get quality score](https://evalgate.com/docs/api-reference/get-quality-score.md)
- [handoffs](https://evalgate.com/docs/api-reference/handoffs.md)
- [import](https://evalgate.com/docs/api-reference/import.md)
- [items](https://evalgate.com/docs/api-reference/items.md)
- [Check Output Grounding](https://evalgate.com/docs/api-reference/knowledge/check-output-grounding.md): Verify that an AI output is grounded in documents from the knowledge base
- [Delete Knowledge Document](https://evalgate.com/docs/api-reference/knowledge/delete-knowledge-document.md): Remove a document and its chunks from the knowledge base
- [List Knowledge Documents](https://evalgate.com/docs/api-reference/knowledge/list-knowledge-documents.md): Retrieve all documents in the organization knowledge base
- [Upload Knowledge Document](https://evalgate.com/docs/api-reference/knowledge/upload-knowledge-document.md): Upload a document to the knowledge base for grounding checks
- [leaderboard](https://evalgate.com/docs/api-reference/leaderboard.md)
- [leaderboard](https://evalgate.com/docs/api-reference/leaderboard-1.md)
- [leaderboard](https://evalgate.com/docs/api-reference/leaderboard-2.md)
- [organizations](https://evalgate.com/docs/api-reference/organizations.md)
- [progress](https://evalgate.com/docs/api-reference/progress.md)
- [promote](https://evalgate.com/docs/api-reference/promote.md)
- [publish](https://evalgate.com/docs/api-reference/publish.md)
- [publish-run](https://evalgate.com/docs/api-reference/publish-run.md)
- [Recompute quality score](https://evalgate.com/docs/api-reference/recompute-quality-score.md)
- [regression](https://evalgate.com/docs/api-reference/regression.md)
- [report](https://evalgate.com/docs/api-reference/report.md)
- [report-cards](https://evalgate.com/docs/api-reference/report-cards.md)
- [results](https://evalgate.com/docs/api-reference/results.md)
- [results](https://evalgate.com/docs/api-reference/results-1.md)
- [retry](https://evalgate.com/docs/api-reference/retry.md)
- [run](https://evalgate.com/docs/api-reference/run.md)
- [run](https://evalgate.com/docs/api-reference/run-1.md)
- [runs](https://evalgate.com/docs/api-reference/runs.md)
- [runs](https://evalgate.com/docs/api-reference/runs-1.md)
- [Get Scoring Configuration](https://evalgate.com/docs/api-reference/settings/get-scoring-configuration.md): Retrieve the current scoring weights and thresholds for quality gates
- [Update Scoring Weights](https://evalgate.com/docs/api-reference/settings/update-scoring-weights.md): Update scoring weights and pass threshold for quality gates
- [shadow-evals](https://evalgate.com/docs/api-reference/shadow-evals.md)
- [slo](https://evalgate.com/docs/api-reference/slo.md)
- [spans](https://evalgate.com/docs/api-reference/spans.md)
- [spec](https://evalgate.com/docs/api-reference/spec.md)
- [stats](https://evalgate.com/docs/api-reference/stats.md)
- [stats](https://evalgate.com/docs/api-reference/stats-1.md)
- [status](https://evalgate.com/docs/api-reference/status.md)
- [stop](https://evalgate.com/docs/api-reference/stop.md)
- [stream](https://evalgate.com/docs/api-reference/stream.md)
- [summary](https://evalgate.com/docs/api-reference/summary.md)
- [synthesize](https://evalgate.com/docs/api-reference/synthesize.md)
- [tasks](https://evalgate.com/docs/api-reference/tasks.md)
- [test-cases](https://evalgate.com/docs/api-reference/test-cases.md)
- [tools](https://evalgate.com/docs/api-reference/tools.md)
- [traces](https://evalgate.com/docs/api-reference/traces.md)
- [trends](https://evalgate.com/docs/api-reference/trends.md)
- [usage](https://evalgate.com/docs/api-reference/usage.md)
- [usage](https://evalgate.com/docs/api-reference/usage-1.md)
- [versions](https://evalgate.com/docs/api-reference/versions.md)
- [webhooks](https://evalgate.com/docs/api-reference/webhooks.md)
- [workflows](https://evalgate.com/docs/api-reference/workflows.md)
- [API authentication](https://evalgate.com/docs/api/authentication.md): Authenticate EvalGate API requests with Bearer tokens and organization-scoped SDK configuration.
- [Errors](https://evalgate.com/docs/api/errors.md)
- [Overview](https://evalgate.com/docs/api/overview.md)
- [Authentication](https://evalgate.com/docs/authentication.md): Create an API key, set environment variables, and initialize the EvalGate SDK.
- [Evaluations](https://evalgate.com/docs/concepts/evaluations.md)
- [Llm judge](https://evalgate.com/docs/concepts/llm-judge.md)
- [Regression data](https://evalgate.com/docs/concepts/regression-data.md): What EvalGate records when it detects regressions locally, in CI, and from production traces.
- [Trace to eval to gate](https://evalgate.com/docs/concepts/trace-eval-gate.md): How EvalGate turns real AI behavior into reviewed eval coverage and CI release gates.
- [Traces](https://evalgate.com/docs/concepts/traces.md)
- [Chatbot evaluation](https://evalgate.com/docs/guides/chatbot-evaluation.md)
- [CI/CD regression gates](https://evalgate.com/docs/guides/cicd-integration.md): Run EvalGate in GitHub Actions or GitLab CI with local gates, eval artifacts, and platform quality checks.
- [Langchain integration](https://evalgate.com/docs/guides/langchain-integration.md)
- [Openai integration](https://evalgate.com/docs/guides/openai-integration.md)
- [Rag evaluation](https://evalgate.com/docs/guides/rag-evaluation.md)
- [Tracing setup](https://evalgate.com/docs/guides/tracing-setup.md)
- [EvalGate](https://evalgate.com/docs/index.md): CI for AI behavior: capture real AI failures, turn them into eval coverage, and block regressions before release.
- [Agent governance](https://evalgate.com/docs/platform/agent-governance.md)
- [Exporting sharing](https://evalgate.com/docs/platform/exporting-sharing.md)
- [Mcp integration](https://evalgate.com/docs/platform/mcp-integration.md)
- [Rate limits](https://evalgate.com/docs/platform/rate-limits.md)
- [Quick start](https://evalgate.com/docs/quickstart.md): Start with a local EvalGate regression gate, then add platform traces and eval history when you need them.
- [Assertions](https://evalgate.com/docs/sdk/assertions.md)
- [Cli](https://evalgate.com/docs/sdk/cli.md)
- [Python](https://evalgate.com/docs/sdk/python.md)
- [Typescript](https://evalgate.com/docs/sdk/typescript.md)

## OpenAPI Specs

- [openapi](https://evalgate.com/docs/api-reference/openapi.json)