# trusys Documentation - [Security Evaluation](https://docs.trusys.ai/intro/truscout.md) - [Functional Evaluation](https://docs.trusys.ai/intro/trueval.md) - [Production Monitoring](https://docs.trusys.ai/intro/trupulse.md) - [AI Guardrails](https://docs.trusys.ai/intro/truguard.md) - [Argus](https://docs.trusys.ai/intro/argus.md) - [Application](https://docs.trusys.ai/product/applications.md) - [Command-Line Usage](https://docs.trusys.ai/product/command-line-usage.md) - [Using CI/CD](https://docs.trusys.ai/product/cicd-usage.md) - [Security Evaluation](https://docs.trusys.ai/product/tru-scout.md) - [Security Configs](https://docs.trusys.ai/product/security-config.md) - [Functional Evaluation](https://docs.trusys.ai/product/tru-eval.md) - [Prompt Library](https://docs.trusys.ai/product/prompt-library.md) - [Datasets](https://docs.trusys.ai/product/dataset.md) - [Monitor Settings](https://docs.trusys.ai/product/monitor-settings.md) - [Track (Dashboard)](https://docs.trusys.ai/product/tru-pulse.md) - [Logs](https://docs.trusys.ai/product/traces.md) - [Analytics & Exception](https://docs.trusys.ai/product/validation-exeptions.md) - [Notifications](https://docs.trusys.ai/tools/alerts.md) - [Boards](https://docs.trusys.ai/tools/boards.md) - [Scheduled Jobs](https://docs.trusys.ai/tools/scheduled-jobs.md) - [Optimization Playground](https://docs.trusys.ai/tools/optimisation.md) - [RAG Poisioning](https://docs.trusys.ai/tools/rag-poisoning.md) - [Text to Speech](https://docs.trusys.ai/tools/text-to-speech.md) - [Workspace](https://docs.trusys.ai/workspace/workspace.md) - [Account](https://docs.trusys.ai/workspace/account.md) - [Projects](https://docs.trusys.ai/workspace/projects.md): How to structure and manage AI assurance activities within Projects in a Trusys workspace. - [API Keys](https://docs.trusys.ai/workspace/api-keys.md): Manage API keys for secure access to Trusys APIs per project. - [User Management](https://docs.trusys.ai/workspace/user-management.md) - [Prompt](https://docs.trusys.ai/concepts/prompts.md) - [Metric](https://docs.trusys.ai/concepts/metrics.md) - [Test Case](https://docs.trusys.ai/concepts/test-case.md) - [Probe](https://docs.trusys.ai/concepts/probe.md) - [Vulnerable Categories](https://docs.trusys.ai/concepts/v-categories.md) - [Attack Startegies](https://docs.trusys.ai/concepts/attack-strategies.md) - [Traces & Sessions](https://docs.trusys.ai/concepts/traces.md) - [Validators](https://docs.trusys.ai/concepts/validators.md) - [🩺 For Healthcare](https://docs.trusys.ai/use-case/for-healthcare.md) - [🛩 For Government & Defence](https://docs.trusys.ai/use-case/for-government-defence.md) - [💵 For Financial Services](https://docs.trusys.ai/use-case/for-financial-services.md) - [Trusys MCP](https://docs.trusys.ai/mcp/mcp.md) - [Claude](https://docs.trusys.ai/mcp/claude.md) - [Cursor](https://docs.trusys.ai/mcp/cursor.md) - [Anti-Gravity](https://docs.trusys.ai/mcp/anti-gravity.md) - [List applications](https://docs.trusys.ai/api-reference/applications/list-applications.md): Returns a paginated list of applications. - [Create an application](https://docs.trusys.ai/api-reference/applications/create-an-application.md): Registers a new AI application in your Trusys workspace. - [Get application details](https://docs.trusys.ai/api-reference/applications/get-application-details.md): Returns application metadata: name, description, and timestamps. - [Update an application](https://docs.trusys.ai/api-reference/applications/update-an-application.md): Updates the display name and/or description of an existing application. - [List quality evaluation metrics](https://docs.trusys.ai/api-reference/metrics/list-quality-evaluation-metrics.md): Returns the catalog of quality evaluation metrics available for monitoring — for example answer relevance, faithfulness, and custom criteria. - [List security evaluation plugins](https://docs.trusys.ai/api-reference/metrics/list-security-evaluation-plugins.md): Returns security testing plugins grouped by risk category (for example `harmful`, `bias`, `pii`). Each entry includes `type` and `description` for discovery. Use plugin IDs in monitoring `plugins`. - [Get monitoring configuration](https://docs.trusys.ai/api-reference/monitoring/get-monitoring-configuration.md): Returns the eval metrics, security plugins, and application security context configured for monitoring. - [Configure monitoring](https://docs.trusys.ai/api-reference/monitoring/configure-monitoring.md): Creates or updates monitoring for an application. - [List trace evaluation results](https://docs.trusys.ai/api-reference/evaluations/list-trace-evaluation-results.md): Returns paginated evaluation results recorded against production traces — i.e. results from `POST /applications/{applicationId}/evaluations` and automatic monitoring/security scoring on live traffic. - [Submit traces for evaluation](https://docs.trusys.ai/api-reference/evaluations/submit-traces-for-evaluation.md): Scores one or more prompt/response traces against the monitoring configuration on the application. - [List traces with optional evaluation summary](https://docs.trusys.ai/api-reference/traces/list-traces-with-optional-evaluation-summary.md): Returns a paginated list of traces for an application in the requested time range. Includes traces with or without evaluation results. - [Get trace with spans and full evaluation results](https://docs.trusys.ai/api-reference/traces/get-trace-with-spans-and-full-evaluation-results.md): Returns one trace by ID, including all spans (attributes and events) and full evaluation results when evaluations exist for that trace. - [List widget types for widget-data](https://docs.trusys.ai/api-reference/widgets/list-widget-types-for-widget-data.md): First step before calling `POST /applications/{applicationId}/widget-data`. - [Get widget chart data](https://docs.trusys.ai/api-reference/widgets/get-widget-chart-data.md): Returns chart data for one or more widget types in the requested time range. - [Get guardrails configuration](https://docs.trusys.ai/api-reference/guardrails/get-guardrails-configuration.md): Returns the guardrails enabled for an application. - [Configure guardrails](https://docs.trusys.ai/api-reference/guardrails/configure-guardrails.md): Enables or disables guardrails and sets input/output validators for an application. - [List guardrail validators and actions](https://docs.trusys.ai/api-reference/guardrails/list-guardrail-validators-and-actions.md): Returns the static catalog of guardrail validator types and enforcement actions. - [List guardrail evaluation history](https://docs.trusys.ai/api-reference/guardrails/list-guardrail-evaluation-history.md): Returns paginated guardrail validation records for an application within a time range. - [Get guardrail evaluation by ID](https://docs.trusys.ai/api-reference/guardrails/get-guardrail-evaluation-by-id.md): Returns one guardrail validation record by ID, including full validator component results. - [Trust Bank Bot](https://docs.trusys.ai/sample-apps/trust-bank-bot.md) ## OpenAPI Specs - [openapi](/openapi.json) ## Optional - [Book a Demo](https://www.trusys.ai/demo) This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.