# Vijil

> Harden during development, validate before deployment, defend in runtime, and continuously improve agents with reinforcement learning.

## Docs

- [Activate Policy](https://docs.vijil.ai/api-reference/agent-environment/activate-policy.md): Activate a policy (requires all rules to be approved).
- [Add Value](https://docs.vijil.ai/api-reference/agent-environment/add-value.md): Add a value to a dimension.
- [Add Value](https://docs.vijil.ai/api-reference/agent-environment/add-value-1.md): Add a value to a dimension.
- [Approve Proposal](https://docs.vijil.ai/api-reference/agent-environment/approve-proposal.md): Approve a mutation proposal.
- [Approve Rule](https://docs.vijil.ai/api-reference/agent-environment/approve-rule.md): Approve a rule.
- [Archive Agent Configuration](https://docs.vijil.ai/api-reference/agent-environment/archive-agent-configuration.md): Archive agent configuration.
- [Bulk Add Values](https://docs.vijil.ai/api-reference/agent-environment/bulk-add-values.md): Bulk add values to a dimension.
- [Bulk Add Values](https://docs.vijil.ai/api-reference/agent-environment/bulk-add-values-1.md): Bulk add values to a dimension.
- [Copy Preset](https://docs.vijil.ai/api-reference/agent-environment/copy-preset.md): Create a copy of a preset policy for the team.
- [Create Agent Configuration](https://docs.vijil.ai/api-reference/agent-environment/create-agent-configuration.md): Create a new agent configuration.
- [Create Dimension](https://docs.vijil.ai/api-reference/agent-environment/create-dimension.md): Create a new demographic dimension.
- [Create Dimension](https://docs.vijil.ai/api-reference/agent-environment/create-dimension-1.md): Create a new demographic dimension.
- [Create From Preset](https://docs.vijil.ai/api-reference/agent-environment/create-from-preset.md): Create a new persona from a system preset.
- [Create Genome](https://docs.vijil.ai/api-reference/agent-environment/create-genome.md): Create (seed) a new genome. Proxies to Darwin POST /v1/genomes.
- [Create Persona](https://docs.vijil.ai/api-reference/agent-environment/create-persona.md): Create a new persona.
- [Create Policy](https://docs.vijil.ai/api-reference/agent-environment/create-policy.md): Create a new policy.
- [Create Policy Rule](https://docs.vijil.ai/api-reference/agent-environment/create-policy-rule.md): Create a new manual rule for a policy.
- [Delete Dimension](https://docs.vijil.ai/api-reference/agent-environment/delete-dimension.md): Delete a demographic dimension and all its values.
- [Delete Dimension](https://docs.vijil.ai/api-reference/agent-environment/delete-dimension-1.md): Delete a demographic dimension and all its values.
- [Delete File](https://docs.vijil.ai/api-reference/agent-environment/delete-file.md): Delete the attached file from a policy.
- [Delete Genome](https://docs.vijil.ai/api-reference/agent-environment/delete-genome.md): Delete a genome and all its versions. Proxies to Darwin.
- [Delete Persona](https://docs.vijil.ai/api-reference/agent-environment/delete-persona.md): Delete a persona.
- [Delete Policy](https://docs.vijil.ai/api-reference/agent-environment/delete-policy.md): Delete a policy.
- [Delete Rule](https://docs.vijil.ai/api-reference/agent-environment/delete-rule.md): Delete a rule.
- [Delete Value](https://docs.vijil.ai/api-reference/agent-environment/delete-value.md): Delete a value.
- [Delete Value](https://docs.vijil.ai/api-reference/agent-environment/delete-value-1.md): Delete a value.
- [Diff Genome Versions](https://docs.vijil.ai/api-reference/agent-environment/diff-genome-versions.md): Compare two genome versions. Proxies to Darwin.
- [Download Converted File](https://docs.vijil.ai/api-reference/agent-environment/download-converted-file.md): Download the converted markdown file for a policy.
- [Download File](https://docs.vijil.ai/api-reference/agent-environment/download-file.md): Download the policy's attached file.
- [Extract Genome From Agent](https://docs.vijil.ai/api-reference/agent-environment/extract-genome-from-agent.md): Extract a genome from an existing agent and seed it in Darwin.
- [Fetch agent trust constraints](https://docs.vijil.ai/api-reference/agent-environment/fetch-agent-trust-constraints.md): Returns the agent's trust constraints (Dome guard config, tool permissions, organization rules, enforcement mode) in the format consumed by the vijil-sdk Trust Runtime at boot.
- [Find Similar Genomes](https://docs.vijil.ai/api-reference/agent-environment/find-similar-genomes.md): Find similar genomes. Proxies to Darwin.
- [Genome To Agent Update](https://docs.vijil.ai/api-reference/agent-environment/genome-to-agent-update.md): Convert a genome to an agent update payload.
- [Get Agent Configuration By Id](https://docs.vijil.ai/api-reference/agent-environment/get-agent-configuration-by-id.md): Get a single agent configuration by ID.
- [Get Agent Configurations](https://docs.vijil.ai/api-reference/agent-environment/get-agent-configurations.md): List agent configurations with filtering and pagination.
- [Get Agent Dome Config](https://docs.vijil.ai/api-reference/agent-environment/get-agent-dome-config.md): Return the dome configuration this agent is using (row-bound and/or ``dome_config_id``).
- [Get Dimension](https://docs.vijil.ai/api-reference/agent-environment/get-dimension.md): Get a dimension by ID, including its values.
- [Get Dimension](https://docs.vijil.ai/api-reference/agent-environment/get-dimension-1.md): Get a dimension by ID, including its values.
- [Get Dimension By Name](https://docs.vijil.ai/api-reference/agent-environment/get-dimension-by-name.md): Get a dimension by name, including its values.
- [Get Dimension By Name](https://docs.vijil.ai/api-reference/agent-environment/get-dimension-by-name-1.md): Get a dimension by name, including its values.
- [Get Evaluation Config](https://docs.vijil.ai/api-reference/agent-environment/get-evaluation-config.md): Get agent configuration for Diamond evaluation.
- [Get Evolution Job Status](https://docs.vijil.ai/api-reference/agent-environment/get-evolution-job-status.md): Poll evolution status.
- [Get Evolution Status](https://docs.vijil.ai/api-reference/agent-environment/get-evolution-status.md): Get evolution proposal status for an agent.
- [Get Genome](https://docs.vijil.ai/api-reference/agent-environment/get-genome.md): Get a genome by ID. Proxies to Darwin.
- [Get Genome Ancestry](https://docs.vijil.ai/api-reference/agent-environment/get-genome-ancestry.md): Get ancestry chain for a genome. Proxies to Darwin.
- [Get Genome By Agent](https://docs.vijil.ai/api-reference/agent-environment/get-genome-by-agent.md): Get a genome by agent ID. Proxies to Darwin.
- [Get Genome Map](https://docs.vijil.ai/api-reference/agent-environment/get-genome-map.md): Get UMAP genome map for the caller's team.
- [Get Genome Version](https://docs.vijil.ai/api-reference/agent-environment/get-genome-version.md): Get a specific genome version. Proxies to Darwin.
- [Get Mutation History](https://docs.vijil.ai/api-reference/agent-environment/get-mutation-history.md): Get mutation history for an agent's genome. Proxies to Darwin.
- [Get Persona](https://docs.vijil.ai/api-reference/agent-environment/get-persona.md): Get a single persona by ID.
- [Get Policy](https://docs.vijil.ai/api-reference/agent-environment/get-policy.md): Get a policy by ID.
- [Get Proposal](https://docs.vijil.ai/api-reference/agent-environment/get-proposal.md): Get a single mutation proposal.
- [Get Proposal By Id](https://docs.vijil.ai/api-reference/agent-environment/get-proposal-by-id.md): Get a single mutation proposal by ID.
- [Get Rule](https://docs.vijil.ai/api-reference/agent-environment/get-rule.md): Get a rule by ID.
- [Get Trust Dashboard](https://docs.vijil.ai/api-reference/agent-environment/get-trust-dashboard.md): Return the Trust Dashboard for the authenticated user's team.
- [Import Agent Unified](https://docs.vijil.ai/api-reference/agent-environment/import-agent-unified.md): Import an agent using the unified import endpoint.
- [List Dimensions](https://docs.vijil.ai/api-reference/agent-environment/list-dimensions.md): List demographic dimensions.
- [List Dimensions](https://docs.vijil.ai/api-reference/agent-environment/list-dimensions-1.md): List demographic dimensions.
- [List Evolution Jobs](https://docs.vijil.ai/api-reference/agent-environment/list-evolution-jobs.md): List evolution jobs for an agent (paginated).
- [List Genome Versions](https://docs.vijil.ai/api-reference/agent-environment/list-genome-versions.md): List all versions of a genome. Proxies to Darwin.
- [List Genomes](https://docs.vijil.ai/api-reference/agent-environment/list-genomes.md): List genomes with filtering and pagination. Proxies to Darwin.
- [List Personas](https://docs.vijil.ai/api-reference/agent-environment/list-personas.md): List personas with filtering and pagination.
- [List Policies](https://docs.vijil.ai/api-reference/agent-environment/list-policies.md): List policies with optional filters and paging.
- [List Policy Rules](https://docs.vijil.ai/api-reference/agent-environment/list-policy-rules.md): List rules for a specific policy.
- [List Presets](https://docs.vijil.ai/api-reference/agent-environment/list-presets.md): List system preset personas.
- [List Presets](https://docs.vijil.ai/api-reference/agent-environment/list-presets-1.md): List system preset policies.
- [List Proposals](https://docs.vijil.ai/api-reference/agent-environment/list-proposals.md): List mutation proposals for an agent.
- [List Rules](https://docs.vijil.ai/api-reference/agent-environment/list-rules.md): List rules with optional filters.
- [List Values](https://docs.vijil.ai/api-reference/agent-environment/list-values.md): List values for a dimension.
- [List Values](https://docs.vijil.ai/api-reference/agent-environment/list-values-1.md): List values for a dimension.
- [Reject Proposal](https://docs.vijil.ai/api-reference/agent-environment/reject-proposal.md): Reject a mutation proposal.
- [Reject Rule](https://docs.vijil.ai/api-reference/agent-environment/reject-rule.md): Reject a rule with a reason.
- [Trigger Evolution](https://docs.vijil.ai/api-reference/agent-environment/trigger-evolution.md): Trigger evolution for an agent.
- [Update Agent Configuration](https://docs.vijil.ai/api-reference/agent-environment/update-agent-configuration.md): Update an existing agent configuration.
- [Update Agent Lifecycle](https://docs.vijil.ai/api-reference/agent-environment/update-agent-lifecycle.md): Update agent trust lifecycle stage.
- [Update Dimension](https://docs.vijil.ai/api-reference/agent-environment/update-dimension.md): Update a demographic dimension.
- [Update Dimension](https://docs.vijil.ai/api-reference/agent-environment/update-dimension-1.md): Update a demographic dimension.
- [Update Persona](https://docs.vijil.ai/api-reference/agent-environment/update-persona.md): Update an existing persona.
- [Update Policy](https://docs.vijil.ai/api-reference/agent-environment/update-policy.md): Update a policy.
- [Update Rule](https://docs.vijil.ai/api-reference/agent-environment/update-rule.md): Update a rule.
- [Update Value](https://docs.vijil.ai/api-reference/agent-environment/update-value.md): Update a value.
- [Update Value](https://docs.vijil.ai/api-reference/agent-environment/update-value-1.md): Update a value.
- [Upload File](https://docs.vijil.ai/api-reference/agent-environment/upload-file.md): Upload a policy document file (PDF, TXT, MD) using streaming.
- [Validate Agent Import](https://docs.vijil.ai/api-reference/agent-environment/validate-agent-import.md): Validate an agent import request without saving.
- [Cancel Custom Harness](https://docs.vijil.ai/api-reference/diamond/cancel-custom-harness.md): Cancel a running custom harness creation workflow.
- [Cancel Evaluation](https://docs.vijil.ai/api-reference/diamond/cancel-evaluation.md): Cancel a running evaluation (Kubernetes Job cancellation + workflow status update).
- [Create Custom Harness](https://docs.vijil.ai/api-reference/diamond/create-custom-harness.md): Create a new custom harness.
- [Create Evaluation](https://docs.vijil.ai/api-reference/diamond/create-evaluation.md): Create a new evaluation job.
- [Delete Custom Harness](https://docs.vijil.ai/api-reference/diamond/delete-custom-harness.md): Delete a custom harness.
- [Delete Evaluation](https://docs.vijil.ai/api-reference/diamond/delete-evaluation.md): Delete evaluation (Kubernetes Job + repository entry + S3 storage).
- [Delete Evaluation Summary](https://docs.vijil.ai/api-reference/diamond/delete-evaluation-summary.md): Delete an evaluation summary row.
- [Generate Report On Demand](https://docs.vijil.ai/api-reference/diamond/generate-report-on-demand.md): Generate a trust report on demand (Layer 3).
- [Get Custom Harness](https://docs.vijil.ai/api-reference/diamond/get-custom-harness.md): Get a single custom harness by ID with optional workflow status.
- [Get Custom Harness Prompts](https://docs.vijil.ai/api-reference/diamond/get-custom-harness-prompts.md): Return taxonomy prompts from ``harness_prompts.jsonl`` for a custom harness.
- [Get Evaluation](https://docs.vijil.ai/api-reference/diamond/get-evaluation.md): Get evaluation status.
- [Get Evaluation Html Report](https://docs.vijil.ai/api-reference/diamond/get-evaluation-html-report.md): Get HTML trust report for an evaluation.
- [Get Evaluation Logs](https://docs.vijil.ai/api-reference/diamond/get-evaluation-logs.md): Get evaluation job logs from Kubernetes.
- [Get Evaluation Pdf Report](https://docs.vijil.ai/api-reference/diamond/get-evaluation-pdf-report.md): Get PDF trust report for an evaluation.
- [Get Evaluation Report](https://docs.vijil.ai/api-reference/diamond/get-evaluation-report.md): Download evaluation report PDF from S3 storage.
- [Get Evaluation Report Html](https://docs.vijil.ai/api-reference/diamond/get-evaluation-report-html.md): Download evaluation report HTML from S3 storage.
- [Get Evaluation Results](https://docs.vijil.ai/api-reference/diamond/get-evaluation-results.md): Get evaluation results from S3 storage.
- [Get Evaluation Summary](https://docs.vijil.ai/api-reference/diamond/get-evaluation-summary.md): Get a single evaluation summary by evaluation ID.
- [List Completed Evaluations](https://docs.vijil.ai/api-reference/diamond/list-completed-evaluations.md): List completed evaluations from S3 storage for a specific team.
- [List Custom Harnesses](https://docs.vijil.ai/api-reference/diamond/list-custom-harnesses.md): List custom harnesses for the specified team with pagination and filtering.
- [List Evaluation Summaries](https://docs.vijil.ai/api-reference/diamond/list-evaluation-summaries.md): List evaluation summaries for a team with optional filters and pagination.
- [List Harnesses](https://docs.vijil.ai/api-reference/diamond/list-harnesses.md): List all standard harnesses (global resources).
- [List Latest Evaluation Summaries By Agent](https://docs.vijil.ai/api-reference/diamond/list-latest-evaluation-summaries-by-agent.md): Return the latest completed evaluation summary per agent for the team.
- [List Team Evaluations](https://docs.vijil.ai/api-reference/diamond/list-team-evaluations.md): List all evaluations for the authenticated user's teams.
- [Apply Dome Config](https://docs.vijil.ai/api-reference/dome/apply-dome-config.md): Apply a saved dome config: promotes config_pending.json to config.json and binds it to the agent.
- [Create Detection](https://docs.vijil.ai/api-reference/dome/create-detection.md): Create a new detection request.
- [Create Dome Config](https://docs.vijil.ai/api-reference/dome/create-dome-config.md): Create a new Dome configuration.
- [Delete Dome Config](https://docs.vijil.ai/api-reference/dome/delete-dome-config.md): Delete a Dome configuration.
- [Get Counter Time Series](https://docs.vijil.ai/api-reference/dome/get-counter-time-series.md): Get counter time series.
- [Get Counter Total](https://docs.vijil.ai/api-reference/dome/get-counter-total.md): Get total counter value.
- [Get Default Dome Config](https://docs.vijil.ai/api-reference/dome/get-default-dome-config.md): Get the default Dome configuration.
- [Get Detection](https://docs.vijil.ai/api-reference/dome/get-detection.md): Get a detection by ID.
- [Get Dome Config](https://docs.vijil.ai/api-reference/dome/get-dome-config.md): Get a Dome configuration by ID.
- [Get Latency Over Time](https://docs.vijil.ai/api-reference/dome/get-latency-over-time.md): Get latency over time.
- [Get Logs](https://docs.vijil.ai/api-reference/dome/get-logs.md): Get logs.
- [Get Trace By Id](https://docs.vijil.ai/api-reference/dome/get-trace-by-id.md): Get trace by ID.
- [List Dome Configs](https://docs.vijil.ai/api-reference/dome/list-dome-configs.md): List dome configs for the team; optional filter by bound agent_id column.
- [Patch Dome Config](https://docs.vijil.ai/api-reference/dome/patch-dome-config.md): Partially update a Dome configuration (e.g. set or clear dome instance URL).
- [Register Dome](https://docs.vijil.ai/api-reference/dome/register-dome.md): Register a Dome instance URL for an agent (called by Dome at runtime).
- [Search Traces](https://docs.vijil.ai/api-reference/dome/search-traces.md): Search traces.
- [Update Dome Config](https://docs.vijil.ai/api-reference/dome/update-dome-config.md): Update a Dome configuration.
- [Cancel Campaign](https://docs.vijil.ai/api-reference/red-team/cancel-campaign.md): Cancel a running red team campaign.
- [Create Campaign](https://docs.vijil.ai/api-reference/red-team/create-campaign.md): Create a new red team campaign.
- [Delete Campaign](https://docs.vijil.ai/api-reference/red-team/delete-campaign.md): Delete a red team campaign and all its S3 artifacts.
- [Download Campaign Results](https://docs.vijil.ai/api-reference/red-team/download-campaign-results.md): Download campaign results as a JSON file (attachment).
- [Get Campaign Logs](https://docs.vijil.ai/api-reference/red-team/get-campaign-logs.md): Get logs from the campaign's Kubernetes job pod.
- [Get Campaign Results](https://docs.vijil.ai/api-reference/red-team/get-campaign-results.md): Get normalized results of a completed red team campaign.
- [Get Campaign Status](https://docs.vijil.ai/api-reference/red-team/get-campaign-status.md): Get the status of a red team campaign.
- [List Campaigns](https://docs.vijil.ai/api-reference/red-team/list-campaigns.md): List all red team campaigns across all teams the user belongs to (subject to per-team permissions).
- [List Tools](https://docs.vijil.ai/api-reference/red-team/list-tools.md): List available red team tools and their supported attack categories.
- [Accept Invite](https://docs.vijil.ai/api-reference/teams/accept-invite.md): Accept a team invitation.
- [Change Password](https://docs.vijil.ai/api-reference/teams/change-password.md): Change the current user's password.
- [Create Team](https://docs.vijil.ai/api-reference/teams/create-team.md): Create a new team.
- [Create User](https://docs.vijil.ai/api-reference/teams/create-user.md): Create a new user.
- [Get Current User](https://docs.vijil.ai/api-reference/teams/get-current-user.md): Get the current authenticated user's information.
- [Get Current User Info](https://docs.vijil.ai/api-reference/teams/get-current-user-info.md): Get the currently authenticated user's information.
- [Get My Teams](https://docs.vijil.ai/api-reference/teams/get-my-teams.md): Get the current user's team memberships.
- [Get Team](https://docs.vijil.ai/api-reference/teams/get-team.md): Get a team by ID.
- [Get Team Users](https://docs.vijil.ai/api-reference/teams/get-team-users.md): List all users in a team.
- [Get User](https://docs.vijil.ai/api-reference/teams/get-user.md): Get a user by query parameters.
- [Get User By Id](https://docs.vijil.ai/api-reference/teams/get-user-by-id.md): Get a user by ID.
- [Invite Users](https://docs.vijil.ai/api-reference/teams/invite-users.md): Invite a user to a team by email.
- [Jwt Login](https://docs.vijil.ai/api-reference/teams/jwt-login.md): Authenticate with email + password, sets JWT token in httpOnly cookie.
- [Jwt Logout](https://docs.vijil.ai/api-reference/teams/jwt-logout.md): Logout user by clearing the authentication cookie.
- [Jwt Refresh](https://docs.vijil.ai/api-reference/teams/jwt-refresh.md): Refresh JWT token.
- [Detector](https://docs.vijil.ai/concepts/defense/detector.md): The detection engines that identify threats within Guards.
- [Guard](https://docs.vijil.ai/concepts/defense/guard.md): Specialized protection modules that defend against specific threat categories.
- [Guardrail](https://docs.vijil.ai/concepts/defense/guardrail.md): Configurable pipelines that orchestrate Guards into complete protection policies.
- [How Defense Works](https://docs.vijil.ai/concepts/defense/introduction.md): The architecture of runtime agent protection: Guardrails, Guards, and Detectors.
- [Observe](https://docs.vijil.ai/concepts/defense/observe.md): Telemetry, metrics, and logging for production agent visibility.
- [Detector](https://docs.vijil.ai/concepts/evaluation-components/detector.md): Response analyzers that determine whether an agent passed or failed a Probe.
- [Harness](https://docs.vijil.ai/concepts/evaluation-components/harness.md): The top-level container that defines what you are testing and produces a score.
- [How Evaluation Works](https://docs.vijil.ai/concepts/evaluation-components/introduction.md): The architecture of systematic agent testing: from test definition through execution to trust scoring.
- [Probe](https://docs.vijil.ai/concepts/evaluation-components/probe.md): Individual test cases: specific prompts designed to elicit specific behaviors.
- [Scenario](https://docs.vijil.ai/concepts/evaluation-components/scenario.md): Groups of related Probes that test for a specific attack vector or failure mode.
- [Glossary](https://docs.vijil.ai/concepts/glossary.md): Key terms and concepts in AI agents and cybersecurity.
- [The Trust Score](https://docs.vijil.ai/concepts/trust-score/introduction.md): A quantitative framework for measuring agent trustworthiness across reliability, security, and safety.
- [Reliability](https://docs.vijil.ai/concepts/trust-score/reliability.md): Measuring whether agents do what they are supposed to do correctly, consistently, and robustly. Reliability is the oldest form of trust.
- [Safety](https://docs.vijil.ai/concepts/trust-score/safety.md): Measuring whether agents operate within acceptable boundaries and minimize harm when things go wrong.
- [Security](https://docs.vijil.ai/concepts/trust-score/security.md): Measuring whether agents can resist adversarial attacks on confidentiality, integrity, and availability.
- [Welcome to Vijil](https://docs.vijil.ai/concepts/welcome.md): The trust layer for AI agents measure reliability, security, and safety, then ship with evidence.
- [MCP](https://docs.vijil.ai/developer-guide/agentic/mcp.md): This guide walks through setting up the Vijil MCP server so Claude Code can interact with your Vijil Console deployment. By the end you will have Claude Code listing your agents, running evaluations, and retrieving results — all through natural language.
- [Vijil Console](https://docs.vijil.ai/developer-guide/deploy-vijil/deploy-vijil-console.md): This guide walks through deploying the full Vijil Console stack on Kubernetes (AWS EKS). It covers AWS infrastructure setup, IAM configuration, Helm deployment, DNS, and post-install steps.
- [Cloud Provider Integrations](https://docs.vijil.ai/developer-guide/evaluate/cloud-providers.md): Evaluate agents hosted on major cloud platforms.
- [Custom Harnesses](https://docs.vijil.ai/developer-guide/evaluate/custom-harnesses.md): Create targeted evaluations with custom Harnesses, personas, and policies.
- [Evaluation Overview](https://docs.vijil.ai/developer-guide/evaluate/overview.md): Test your agent's trustworthiness before deployment with Diamond.
- [Run Evaluations](https://docs.vijil.ai/developer-guide/evaluate/running-evaluations.md): Execute and monitor agent evaluations programmatically.
- [Understand Results](https://docs.vijil.ai/developer-guide/evaluate/understanding-results.md): Interpret evaluation scores, analyze failures, and plan remediation.
- [Console API](https://docs.vijil.ai/developer-guide/getting-started/api.md): This guide walks through the Vijil Console REST API using `curl`. By the end you will have registered an AI agent, run a trust evaluation against it, and retrieved the results.
- [Console CLI](https://docs.vijil.ai/developer-guide/getting-started/cli.md): This guide walks through the `vijil` command-line tool. By the end you will have registered an AI agent, run a trust evaluation against it, and retrieved the results.
- [Building Trusted Agents](https://docs.vijil.ai/developer-guide/getting-started/introduction.md): Integrate evaluation and protection into your development workflow, catch failures before they reach production.
- [Configure Guardrails](https://docs.vijil.ai/developer-guide/protect/configuring-guardrails.md): Detailed configuration options for Dome Guards and Detectors.
- [Custom Detectors](https://docs.vijil.ai/developer-guide/protect/custom-detectors.md): Build custom detection methods for Dome Guardrails.
- [Detection Methods](https://docs.vijil.ai/developer-guide/protect/detection-methods.md): Detailed list of every built-in Detector, grouped by category. Each entry shows the method name used in TOML/dict configuration, the underlying model or service, and all configurable parameters.
- [Observability](https://docs.vijil.ai/developer-guide/protect/observability.md): Monitor Dome Guardrails with OpenTelemetry, tracing, and logging.
- [Protection Overview](https://docs.vijil.ai/developer-guide/protect/overview.md): Guard your agent at runtime with Dome Guardrails.
- [Use Guardrails](https://docs.vijil.ai/developer-guide/protect/using-guardrails.md): Runtime patterns and best practices for Dome Guardrails.
- [Detector](https://docs.vijil.ai/legacy/core-concepts/components/detector.md)
- [Guard](https://docs.vijil.ai/legacy/core-concepts/components/guard.md)
- [Guardrail](https://docs.vijil.ai/legacy/core-concepts/components/guardrail.md): Learn about Guardrails
- [Harness](https://docs.vijil.ai/legacy/core-concepts/components/harness.md): Learn about Harnesses
- [Introduction](https://docs.vijil.ai/legacy/core-concepts/components/introduction.md): Discover Vijil’s evaluation service
- [Probe](https://docs.vijil.ai/legacy/core-concepts/components/probe.md): Learn about Probes
- [Scenario](https://docs.vijil.ai/legacy/core-concepts/components/scenario.md): Learn about Scenarios
- [Introduction](https://docs.vijil.ai/legacy/core-concepts/dimensions/introduction.md): Discover Vijil's LLM trustworthiness along 3 dimensions
- [Reliability](https://docs.vijil.ai/legacy/core-concepts/dimensions/reliability.md): Vijil's Reliability dimension of trust tests for correctness, robustness, and consistency.
- [Safety](https://docs.vijil.ai/legacy/core-concepts/dimensions/safety.md): Vijil's Safety dimension of trust tests for compliance, ethical behavior, and harm prevention.
- [Security](https://docs.vijil.ai/legacy/core-concepts/dimensions/security.md): Vijil's Security dimension of trust tests for confidentiability, integrity, and availability.
- [Introduction](https://docs.vijil.ai/legacy/core-concepts/introduction.md): Learn the concepts that stand at the core of Vijil
- [Introduction](https://docs.vijil.ai/legacy/evaluate-agents/introduction.md): Learn how to evaluate agents with Vijil
- [Quickstart](https://docs.vijil.ai/legacy/get-started/quickstart.md): Get started with Vijil in minutes
- [Welcome](https://docs.vijil.ai/legacy/get-started/welcome.md): Vijil is the trust infrastructure that makes AI agents reliable, secure, and safe for enterprises.
- [Anthropic (Legacy)](https://docs.vijil.ai/legacy/manage-agents/integrations/anthropic.md): Legacy Anthropic integration docs copied from the integrations-section branch.
- [AWS Bedrock/Bedrock Agents (Legacy)](https://docs.vijil.ai/legacy/manage-agents/integrations/bedrock.md): Legacy AWS Bedrock and Bedrock Agents integration docs copied from the integrations-section branch.
- [Custom Endpoints](https://docs.vijil.ai/legacy/manage-agents/integrations/custom.md): Legacy Custom Endpoints integration docs copied from the integrations-section branch.
- [DigitalOcean (Legacy)](https://docs.vijil.ai/legacy/manage-agents/integrations/digitalocean.md): Legacy DigitalOcean integration docs copied from the integrations-section branch.
- [Fireworks AI (Legacy)](https://docs.vijil.ai/legacy/manage-agents/integrations/fireworks.md): Legacy Fireworks AI integration docs copied from the integrations-section branch.
- [Groq (Legacy)](https://docs.vijil.ai/legacy/manage-agents/integrations/groq.md): Legacy Groq integration docs copied from the integrations-section branch.
- [Mistral AI (Legacy)](https://docs.vijil.ai/legacy/manage-agents/integrations/mistral.md): Legacy Mistral AI integration docs copied from the integrations-section branch.
- [NVIDIA NIM (Legacy)](https://docs.vijil.ai/legacy/manage-agents/integrations/nvidia.md): Legacy NVIDIA NIM integration docs copied from the integrations-section branch.
- [OpenAI](https://docs.vijil.ai/legacy/manage-agents/integrations/openai.md): Legacy OpenAI integration docs copied from the integrations-section branch.
- [OpenRouter (Legacy)](https://docs.vijil.ai/legacy/manage-agents/integrations/openrouter.md): Legacy OpenRouter integration docs copied from the integrations-section branch.
- [Together AI (Legacy)](https://docs.vijil.ai/legacy/manage-agents/integrations/together.md): Legacy Together AI integration docs copied from the integrations-section branch.
- [Google Vertex AI](https://docs.vijil.ai/legacy/manage-agents/integrations/vertex.md): Legacy Google Vertex AI integration docs copied from the integrations-section branch.
- [Introduction](https://docs.vijil.ai/legacy/manage-agents/introduction.md): Legacy Manage Agents introduction copied from the integrations-section branch.
- [List of Detection Methods](https://docs.vijil.ai/legacy/protect-agents/detection-methods.md): List of all built-in detection methods grouped by category
- [Introduction](https://docs.vijil.ai/legacy/protect-agents/introduction.md): Learn how to protect agents with Vijil
- [Glossary](https://docs.vijil.ai/legacy/references/glossary.md): Discover Vijil's terminology
- [Client](https://docs.vijil.ai/legacy/references/python-client/client.md): Discover the `client.py` docs
- [Introduction](https://docs.vijil.ai/legacy/references/python-client/introduction.md): Discover the documentation of the Vijil's Python client
- [Release Notes](https://docs.vijil.ai/legacy/references/release-notes.md): Discover Vijil's current version and the release history
- [Custom Harnesses](https://docs.vijil.ai/legacy/tutorials/evaluate-agents/custom-harnesses.md): Create a custom Harness to evaluate your agent against your own policies and use case
- [Working with Detections](https://docs.vijil.ai/legacy/tutorials/evaluate-agents/detections.md)
- [Deploying Vijil Evaluate with Helm](https://docs.vijil.ai/legacy/tutorials/evaluate-agents/enterprise/deployment.md)
- [Introduction](https://docs.vijil.ai/legacy/tutorials/evaluate-agents/enterprise/introduction.md)
- [Prerequisites](https://docs.vijil.ai/legacy/tutorials/evaluate-agents/enterprise/prerequisites.md)
- [Evaluations](https://docs.vijil.ai/legacy/tutorials/evaluate-agents/evaluations.md): Learn how to create, view, summarize, export, cancel, and delete evaluations.
- [Evaluating Agents with Custom Endpoints](https://docs.vijil.ai/legacy/tutorials/evaluate-agents/local-agent-evaluation.md)
- [Testing OWASP LLM Top 10 Vulnerabilities](https://docs.vijil.ai/legacy/tutorials/evaluate-agents/owasp.md)
- [Evaluating RAGs through Vijil Evaluate](https://docs.vijil.ai/legacy/tutorials/evaluate-agents/rag.md)
- [Evaluation Reports](https://docs.vijil.ai/legacy/tutorials/evaluate-agents/reports.md)
- [Set up Evaluate](https://docs.vijil.ai/legacy/tutorials/evaluate-agents/setup-evaluate.md): Learn how to setup Vijil Evaluate
- [Manage Agents](https://docs.vijil.ai/legacy/tutorials/manage-agents.md): Learn how to manage agent configurations using the Vijil Python SDK
- [Manage API Keys](https://docs.vijil.ai/legacy/tutorials/manage-api-keys.md): Learn how to manage API keys in Vijil
- [Using Dome Guardrails with Google ADK Agents](https://docs.vijil.ai/legacy/tutorials/protect-agents/adk.md): Learn how to use Dome Guardrails with Google ADK
- [Configure Guardrails](https://docs.vijil.ai/legacy/tutorials/protect-agents/configuring-guardrails.md)
- [Create your own Detectors](https://docs.vijil.ai/legacy/tutorials/protect-agents/custom-detectors.md): Learn how to make custom Detectors
- [Apply Dome to Clients](https://docs.vijil.ai/legacy/tutorials/protect-agents/domed-clients.md): Learn how to apply Dome to Clients
- [Use Dome Guardrails with LangChain](https://docs.vijil.ai/legacy/tutorials/protect-agents/langchain.md): Learn how to use Dome Guardrails with LangChain
- [Enable Observability in Dome](https://docs.vijil.ai/legacy/tutorials/protect-agents/observability.md)
- [Set up Dome](https://docs.vijil.ai/legacy/tutorials/protect-agents/setup-dome.md): Learn how to setup Vijil Dome
- [Set Up Guards and Detectors](https://docs.vijil.ai/legacy/tutorials/protect-agents/setup-guards.md): Users can configure Guards by selecting and combining different Detectors based on their specific needs. This customization allows for flexible and robust Guardrails that cater to diverse application requirements.
- [Use Guardrails](https://docs.vijil.ai/legacy/tutorials/protect-agents/using-guardrails.md): This example shows how to use Dome to scan inputs to and outputs from an LLM.
- [Get Started with Console](https://docs.vijil.ai/owner-guide/getting-started/introduction.md): Why teams use Vijil for trust evidence, then register an Agent, run an Evaluation, and turn on Dome from the Console.
- [Configure Guardrails](https://docs.vijil.ai/owner-guide/protect-in-production/configuring-guardrails.md): Set up runtime protection for your AI agents with Dome Guardrails.
- [Observe Traces and Metrics](https://docs.vijil.ai/owner-guide/protect-in-production/observability.md): Monitor Guardrail performance and agent traffic in real time.
- [Register Agents](https://docs.vijil.ai/owner-guide/register-agents/registering-agents.md): Add your AI agents to Vijil for evaluation and protection.
- [Run Evaluations](https://docs.vijil.ai/owner-guide/run-evaluations/running-evaluations.md): Test your AI agents with Diamond to measure trustworthiness.
- [Understand Results](https://docs.vijil.ai/owner-guide/run-evaluations/understanding-results.md): Interpret evaluation findings using the Taxonomy of Trust framework.
- [Build Custom Harnesses](https://docs.vijil.ai/owner-guide/simulate-environment/custom-harnesses.md): Combine agents, personas, and policies into targeted evaluation configurations.
- [Trust Score Harness](https://docs.vijil.ai/owner-guide/simulate-environment/harnesses/trust-score.md): Evaluate your agent across reliability, security, and safety dimensions.
- [Define Personas](https://docs.vijil.ai/owner-guide/simulate-environment/personas.md): Create user profiles that represent who interacts with your agent during evaluation.
- [Define Policies](https://docs.vijil.ai/owner-guide/simulate-environment/policies.md): Specify organizational rules your agent must follow during evaluation.
- [Playground](https://docs.vijil.ai/tutorials/evaluate-agents/examples/playground.md)
- [Use Dome as a Containerized Deployment](https://docs.vijil.ai/tutorials/protect-agents/dome-containerized-deployment.md): Dome can be deployed as a containerized service for easy integration with other frameworks. You can deploy the container on a CPU or GPU compute instance and wire your requests to it to protect agent inputs and outputs.

## OpenAPI Specs

- [api](https://docs.vijil.ai/openapi/api.json)

## Optional

- [Blog](https://www.vijil.ai/blog)