# NeuralTrust Docs ## Docs - [Create Policy](https://docs.neuraltrust.ai/api-reference/endpoint/actions/create-policy.md): Creates a new policy with actions, telemetry and TrustLens configuration - [Execute Actions](https://docs.neuraltrust.ai/api-reference/endpoint/actions/execute.md): Executes a set of actions defined by a policy - [Create Api Key](https://docs.neuraltrust.ai/api-reference/endpoint/apikey/create.md): Generates a new API key for the specified gateway - [Delete Api Key](https://docs.neuraltrust.ai/api-reference/endpoint/apikey/delete.md): Removes an API key. If the key is scoped to a gateway (GatewayType), provide ?subject_id=. - [List Api Keys](https://docs.neuraltrust.ai/api-reference/endpoint/apikey/list.md): Returns a list of all API keys for a gateway with obfuscated key values - [Retrieve Api Key](https://docs.neuraltrust.ai/api-reference/endpoint/apikey/retrieve.md): Returns a list of all API keys for a gateway with obfuscated key values - [Create Gateway](https://docs.neuraltrust.ai/api-reference/endpoint/gateway/create.md): Creates a new gateway in the system - [Delete Gateway](https://docs.neuraltrust.ai/api-reference/endpoint/gateway/delete.md): Removes a gateway from the system - [List Gateways](https://docs.neuraltrust.ai/api-reference/endpoint/gateway/list.md): Retrieves a list of all gateways in the system - [Retrieve Gateway](https://docs.neuraltrust.ai/api-reference/endpoint/gateway/retrieve.md): Returns details of a specific gateway - [Update Gateway](https://docs.neuraltrust.ai/api-reference/endpoint/gateway/update.md): Updates an existing gateway - [Create Rule](https://docs.neuraltrust.ai/api-reference/endpoint/rule/create.md): Adds a new rule under a gateway - [Delete Rule](https://docs.neuraltrust.ai/api-reference/endpoint/rule/delete.md): Removes a rule from a gateway - [List Rules](https://docs.neuraltrust.ai/api-reference/endpoint/rule/list.md): Returns a list of all rules for a gateway - [Update Rule](https://docs.neuraltrust.ai/api-reference/endpoint/rule/update.md): Updates an existing rule - [Create Service](https://docs.neuraltrust.ai/api-reference/endpoint/service/create.md): Adds a new service under a gateway - [Delete Service](https://docs.neuraltrust.ai/api-reference/endpoint/service/delete.md): Removes a service from a gateway - [List Services](https://docs.neuraltrust.ai/api-reference/endpoint/service/list.md): Returns a list of all services for a gateway - [Retrieve Service](https://docs.neuraltrust.ai/api-reference/endpoint/service/retrieve.md): Returns details of a specific service - [Update Service](https://docs.neuraltrust.ai/api-reference/endpoint/service/update.md): Updates an existing service - [Create Upstream](https://docs.neuraltrust.ai/api-reference/endpoint/upstream/create.md): Adds a new upstream under a gateway - [Delete Upstream](https://docs.neuraltrust.ai/api-reference/endpoint/upstream/delete.md): Removes an upstream from a gateway - [List Upstreams](https://docs.neuraltrust.ai/api-reference/endpoint/upstream/list.md): Returns a list of all upstreams for a gateway - [Retrieve Upstream](https://docs.neuraltrust.ai/api-reference/endpoint/upstream/retrieve.md): Returns details of a specific upstream - [Update Upstream](https://docs.neuraltrust.ai/api-reference/endpoint/upstream/update.md): Updates an existing upstream - [NeuralTrust Docs](https://docs.neuraltrust.ai/index.md) - [Data privacy](https://docs.neuraltrust.ai/neuraltrust/data-privacy/overview.md): Data sovereignty, GDPR / HIPAA / SOX compliance, and the privacy-by-design architecture that keeps sensitive AI data inside your environment. - [AWS (EKS)](https://docs.neuraltrust.ai/neuraltrust/deployment/aws.md): Provision an Amazon EKS cluster and install the NeuralTrust Platform Helm chart with AWS-native ingress, storage, and certificates. - [Azure (AKS)](https://docs.neuraltrust.ai/neuraltrust/deployment/azure.md): Provision an Azure Kubernetes Service cluster and install the NeuralTrust Platform Helm chart with Azure-native ingress, storage, and certificates. - [Configuration scenarios](https://docs.neuraltrust.ai/neuraltrust/deployment/configuration.md): Side-by-side reference for the values files the NeuralTrust Platform Helm chart ships, and ready-made overrides for common deployment topologies. - [Firewall deployment](https://docs.neuraltrust.ai/neuraltrust/deployment/firewall.md): Deploy the optional NeuralTrust Firewall — gateway plus specialized workers for prompt and response safety, on CPU or GPU. - [GCP (GKE)](https://docs.neuraltrust.ai/neuraltrust/deployment/gcp.md): Provision a Google Kubernetes Engine cluster and install the NeuralTrust Platform Helm chart with GCP-native ingress, storage, and certificates. - [Install on Kubernetes](https://docs.neuraltrust.ai/neuraltrust/deployment/kubernetes.md): Deploy the full NeuralTrust Platform (Data Plane, Control Plane, TrustGate, optional Firewall) to any Kubernetes cluster with a single Helm chart. - [OpenShift](https://docs.neuraltrust.ai/neuraltrust/deployment/openshift.md): Deploy the NeuralTrust Platform on Red Hat OpenShift 4.10+ with Routes (default) or Kubernetes Ingress. - [Architecture](https://docs.neuraltrust.ai/neuraltrust/deployment/overview.md): NeuralTrust's high-level architecture — control plane, data plane, deployment modes, and the components that run in each. - [Secrets management](https://docs.neuraltrust.ai/neuraltrust/deployment/secrets.md): How NeuralTrust Platform secrets are created, stored, rotated, and managed — including auto-generation, pre-generated secrets, and integration with Vault, Sealed Secrets, and External Secrets Operator. - [Security posture](https://docs.neuraltrust.ai/neuraltrust/security/overview.md): NeuralTrust's platform-wide security model — authentication, access control, networking, encryption, and compliance guarantees. - [Advanced](https://docs.neuraltrust.ai/platform/advanced.md): Provision a hybrid data plane in your own AWS, GCP, or Azure account — or connect one you already run — directly from Team Settings. - [Audit Logs](https://docs.neuraltrust.ai/platform/audit-logs.md): View and monitor security audit logs in NeuralTrust. Track authentication events, user management, and SSO activities. Integrate with your SIEM platform. - [Break the Glass](https://docs.neuraltrust.ai/platform/break-glass.md): Configure emergency access for administrators to bypass SSO enforcement. Ensure your team is never locked out during identity provider outages. - [Custom Domain](https://docs.neuraltrust.ai/platform/custom-domain.md): Serve the NeuralTrust app on a domain you own via a CNAME — so users reach the platform at a URL on your organization's zone. - [Feature Flags](https://docs.neuraltrust.ai/platform/feature-flags.md): Toggle preview capabilities and early-access features for your team — opt in to new functionality before it becomes default. - [General](https://docs.neuraltrust.ai/platform/general.md): Team identity basics — the team's display name and team deletion. - [Generic OIDC SSO](https://docs.neuraltrust.ai/platform/generic-oidc-sso.md): Configure Single Sign-On with any OpenID Connect compliant identity provider including Okta, Auth0, Google Workspace, and more. - [Models](https://docs.neuraltrust.ai/platform/models.md): Choose which LLM and embeddings provider NeuralTrust uses internally — for judge calls, analyzers, semantic classification, and vector operations. - [Overview](https://docs.neuraltrust.ai/platform/overview.md): Team Settings is where you manage the tenant that hosts your NeuralTrust products — team identity, identity and access, audit, infrastructure, and platform-wide configuration. - [Password Policy](https://docs.neuraltrust.ai/platform/password-policy.md): Configure password requirements for team members — minimum length, character classes, and blocks for common passwords and personal information. - [SCIM Provisioning](https://docs.neuraltrust.ai/platform/scim.md): Set up SCIM automatic user provisioning with Microsoft Entra ID. Automatically sync users between Azure AD and NeuralTrust. - [SIEM Integration](https://docs.neuraltrust.ai/platform/siem-integration.md): Forward NeuralTrust audit logs to your SIEM platform. Configure Splunk, Elastic, QRadar, Microsoft Sentinel, or Datadog for centralized security monitoring. - [Microsoft Entra ID SSO](https://docs.neuraltrust.ai/platform/sso.md): Step-by-step guide to configure Microsoft Entra ID (Azure AD) Single Sign-On for NeuralTrust. Enable corporate authentication for your team. - [Manual User Sync](https://docs.neuraltrust.ai/platform/user-sync.md): Synchronize users from Microsoft Entra ID groups on-demand. Import users with role assignments based on group mappings. - [Users](https://docs.neuraltrust.ai/platform/users.md): Manage the humans in your NeuralTrust team — members, pending invitations, team roles, and per-product access. - [API Examples](https://docs.neuraltrust.ai/trustgate/actions-api/examples.md) - [Observability](https://docs.neuraltrust.ai/trustgate/actions-api/observability.md) - [Overview](https://docs.neuraltrust.ai/trustgate/actions-api/overview.md) - [Policies](https://docs.neuraltrust.ai/trustgate/actions-api/policies.md) - [Tool Budget Limiter](https://docs.neuraltrust.ai/trustgate/agent-security/tool-budget-limiter.md) - [Tool Guard](https://docs.neuraltrust.ai/trustgate/agent-security/tool-guard.md) - [Tool Permission](https://docs.neuraltrust.ai/trustgate/agent-security/tool-permission.md) - [Tool Selection](https://docs.neuraltrust.ai/trustgate/agent-security/tool-selection.md) - [Code Sanitation](https://docs.neuraltrust.ai/trustgate/application-security/code.md) - [CORS](https://docs.neuraltrust.ai/trustgate/application-security/cors/cors.md) - [Injection Protection](https://docs.neuraltrust.ai/trustgate/application-security/injection-protection.md) - [IP Whitelist](https://docs.neuraltrust.ai/trustgate/application-security/ip-whitelist.md) - [Overview](https://docs.neuraltrust.ai/trustgate/application-security/overview.md) - [Local Setup](https://docs.neuraltrust.ai/trustgate/benchmark/local.md) - [Overview](https://docs.neuraltrust.ai/trustgate/benchmark/overview.md) - [TrustGate vs Others](https://docs.neuraltrust.ai/trustgate/benchmark/trustgate-vs-others.md) - [Semantic Cache](https://docs.neuraltrust.ai/trustgate/cache/semantic-cache.md): Cache AI responses based on semantic similarity to reduce latency and costs - [Document Analyzer](https://docs.neuraltrust.ai/trustgate/content-security/content-analyzers/doc-analyzer.md): Analyze uploaded documents for PII detection, jailbreak detection, and content security - [Overview](https://docs.neuraltrust.ai/trustgate/content-security/content-analyzers/overview.md): Analyze documents and URLs for security threats and sensitive data - [URL Analyzer](https://docs.neuraltrust.ai/trustgate/content-security/content-analyzers/url-analyzer.md): Analyze URLs in requests for jailbreak attempts and PII exposure - [Contextual Security](https://docs.neuraltrust.ai/trustgate/content-security/context-security/context-security.md) - [AWS Bedrock Guardrail](https://docs.neuraltrust.ai/trustgate/content-security/jailbreaks/bedrock.md) - [NeuralTrust Jailbreak Detection](https://docs.neuraltrust.ai/trustgate/content-security/jailbreaks/neuraltrust.md) - [Overview](https://docs.neuraltrust.ai/trustgate/content-security/jailbreaks/overview.md) - [Language Validator](https://docs.neuraltrust.ai/trustgate/content-security/language-validator.md) - [Keywords & Regex](https://docs.neuraltrust.ai/trustgate/content-security/moderation/keywords.md) - [NeuralTrust Content Moderation](https://docs.neuraltrust.ai/trustgate/content-security/moderation/neuraltrust.md) - [Overview](https://docs.neuraltrust.ai/trustgate/content-security/overview.md) - [Azure Toxicity Detection](https://docs.neuraltrust.ai/trustgate/content-security/toxicity/azure.md) - [NeuralTrust Toxicity Detection](https://docs.neuraltrust.ai/trustgate/content-security/toxicity/neuraltrust.md) - [OpenAI Toxicity Detection](https://docs.neuraltrust.ai/trustgate/content-security/toxicity/openai.md) - [Overview](https://docs.neuraltrust.ai/trustgate/content-security/toxicity/overview.md) - [Consumer Groups](https://docs.neuraltrust.ai/trustgate/core-concepts/consumer-groups.md) - [Overview](https://docs.neuraltrust.ai/trustgate/core-concepts/gateway-overview.md) - [Plugin Scopes & Configuration](https://docs.neuraltrust.ai/trustgate/core-concepts/plugin.md) - [Rules & Policies](https://docs.neuraltrust.ai/trustgate/core-concepts/rules.md) - [Upstream Services & Routing](https://docs.neuraltrust.ai/trustgate/core-concepts/upstream-services-overview.md) - [Custom Rules](https://docs.neuraltrust.ai/trustgate/data-masking/custom-rules.md) - [PII Entities](https://docs.neuraltrust.ai/trustgate/data-masking/entities.md) - [Configuration Examples](https://docs.neuraltrust.ai/trustgate/data-masking/examples.md) - [Overview](https://docs.neuraltrust.ai/trustgate/data-masking/overview.md) - [Architecture](https://docs.neuraltrust.ai/trustgate/deployment/architecture.md) - [Installing with Docker](https://docs.neuraltrust.ai/trustgate/deployment/docker/installation.md) - [Installing on Kubernetes](https://docs.neuraltrust.ai/trustgate/deployment/kubernetes/installation.md) - [Overview](https://docs.neuraltrust.ai/trustgate/deployment/overview.md) - [How to Extend TrustGate](https://docs.neuraltrust.ai/trustgate/extending/how-to.md) - [Integrate External API's](https://docs.neuraltrust.ai/trustgate/extending/integrate-external-api.md) - [Testing Your Plugins](https://docs.neuraltrust.ai/trustgate/extending/testing-plugins.md) - [Writing Custom Plugins](https://docs.neuraltrust.ai/trustgate/extending/write-plugins.md) - [Quickstart: Hello Gateway](https://docs.neuraltrust.ai/trustgate/getting-started/hello-gateway.md) - [Installation & Running](https://docs.neuraltrust.ai/trustgate/getting-started/installation-and-running.md) - [Overview](https://docs.neuraltrust.ai/trustgate/getting-started/overview.md) - [Masking Exposed Data](https://docs.neuraltrust.ai/trustgate/getting-started/tutorial/masking-data.md) - [Load Balancing Between AI Providers](https://docs.neuraltrust.ai/trustgate/getting-started/tutorial/provider-load-balancing.md) - [Open AI Token-Based Rate Limiting](https://docs.neuraltrust.ai/trustgate/getting-started/tutorial/token-rate-limiting.md) - [Enable TrustLens Metrics](https://docs.neuraltrust.ai/trustgate/getting-started/tutorial/trustlens-metrics.md) - [Websocket](https://docs.neuraltrust.ai/trustgate/non-rest/websocket.md) - [Kafka Exporter](https://docs.neuraltrust.ai/trustgate/observability/connectors/kafka.md) - [Available Metrics](https://docs.neuraltrust.ai/trustgate/observability/prometheus/metrics.md) - [Prometheus Integration](https://docs.neuraltrust.ai/trustgate/observability/prometheus/prometheus.md) - [Load balancing](https://docs.neuraltrust.ai/trustgate/platform/ai-gateway/load-balancing.md): Strategies the AI Gateway uses to distribute traffic across upstreams — for resilience, cost control, and routing requests by meaning. - [AI Gateway overview](https://docs.neuraltrust.ai/trustgate/platform/ai-gateway/overview.md): The NeuralTrust AI Gateway — a first-party, AI-aware gateway that sits in front of LLMs, routes traffic across providers, load-balances, and governs traffic between your applications and the models they call. - [Routes & forwarding](https://docs.neuraltrust.ai/trustgate/platform/ai-gateway/routes.md): How the AI Gateway matches incoming traffic to upstreams — the route model, matching order, typical patterns, and request transformations. - [Traffic control](https://docs.neuraltrust.ai/trustgate/platform/ai-gateway/traffic-control.md): Rate limits, token and size caps, bot detection, and anomaly detection at the AI Gateway surface — the controls that keep upstream providers and your own infrastructure healthy. - [Alerts](https://docs.neuraltrust.ai/trustgate/platform/alerts.md): Metric and change alerts on runtime traffic — fire when latency, message volume, jailbreak attempts, or other live signals cross a threshold. - [Architecture](https://docs.neuraltrust.ai/trustgate/platform/architecture.md): How TrustGate Runtime is put together — control plane vs data plane, the four enforcement surfaces, runtime primitives, plugins, the policy engine, and the request, tool, and document lifecycles. - [Deployment modes](https://docs.neuraltrust.ai/trustgate/platform/deployment-modes.md): SaaS, hybrid, and on-prem options for running TrustGate — and when to use inline enforcement versus out-of-band observation. - [Developers](https://docs.neuraltrust.ai/trustgate/platform/developers.md): Low-level TrustGate Runtime reference — gateway objects, rules, plugins, data masking entities, HTTP/WebSocket, rate limiting, deployment, and the Actions API. - [Surfaces](https://docs.neuraltrust.ai/trustgate/platform/enforcement-surfaces.md): The four places where TrustGate can enforce a policy — Gateway, Browser, API, and Endpoint. How they differ, how to combine them, and which one to start with. - [API surface](https://docs.neuraltrust.ai/trustgate/platform/enforcement/api.md): Security enforcement via direct server-to-server calls to a TrustGate API engine — how to provision one, how to call it, and how Log / Mask / Block translate. - [Browser surface](https://docs.neuraltrust.ai/trustgate/platform/enforcement/browser.md): Security enforcement at the browser — what the TrustGate browser extension sees on web-based LLMs, how it enforces Log / Mask / Block, and how to roll it out as an integration. - [Endpoint surface](https://docs.neuraltrust.ai/trustgate/platform/enforcement/endpoint.md): Security enforcement for AI traffic on managed devices — a transparent MITM proxy that desktop apps, IDE plugins, and CLIs route to via a PAC file, with zero software installed on the device. - [Gateway surface](https://docs.neuraltrust.ai/trustgate/platform/enforcement/gateway.md): Security enforcement for LLM traffic flowing through a TrustGate Gateway — how to create the integration, author routes, and what Log / Mask / Block do on the wire. - [FAQ & concepts](https://docs.neuraltrust.ai/trustgate/platform/faq.md): Common questions about TrustGate Runtime, how it relates to existing security tooling, and the vocabulary we use across these docs. - [Overview](https://docs.neuraltrust.ai/trustgate/platform/index.md): Runtime protection for generative AI — inspect prompts, responses, documents, and tool calls in flight, and enforce policy at the boundary of your LLMs and agents. - [Azure AI Foundry](https://docs.neuraltrust.ai/trustgate/platform/integration-guides/azure-foundry.md): Apply Runtime security to Azure AI Foundry agents by routing Agent Application traffic through a TrustGate Gateway. - [AWS Bedrock Agents](https://docs.neuraltrust.ai/trustgate/platform/integration-guides/bedrock-agents.md): Protect Bedrock-based agents with a TrustGate Gateway via the Strands Agents SDK, or with the API enforcement surface for managed Bedrock Agents. - [Cursor, Copilot & AI IDEs](https://docs.neuraltrust.ai/trustgate/platform/integration-guides/cursor.md): Protect Cursor, GitHub Copilot, Windsurf, and other AI IDEs on managed developer machines using the Endpoint and Browser enforcement surfaces. - [LangChain & LangGraph](https://docs.neuraltrust.ai/trustgate/platform/integration-guides/langchain.md): Point LangChain and LangGraph model clients at a TrustGate Gateway to secure every LLM hop in your chain or graph. - [LLM SDKs](https://docs.neuraltrust.ai/trustgate/platform/integration-guides/openai-sdk.md): Route OpenAI, Anthropic, Google, Azure OpenAI, and Bedrock SDK calls through a TrustGate Gateway with a single base-URL change. - [Integration guides](https://docs.neuraltrust.ai/trustgate/platform/integration-guides/overview.md): Apply Runtime security to your agent stack — SDKs, frameworks, managed agent platforms, and developer tools. - [Strands Agents SDK](https://docs.neuraltrust.ai/trustgate/platform/integration-guides/strands-agents.md): Put a TrustGate Gateway in front of every model call your Strands agent makes — a single swap on the model client covers the whole agentic loop. - [Integrations](https://docs.neuraltrust.ai/trustgate/platform/integrations.md): How TrustGate plugs into your AI stack — LLM providers, AI platforms, APIs, gateways, MCP servers, and observability pipelines. - [MCP & tool security](https://docs.neuraltrust.ai/trustgate/platform/mcp-tool-security.md): Govern agent behavior — control which tools can be called, validate arguments, and stop dangerous tool invocations before they execute. - [Observability](https://docs.neuraltrust.ai/trustgate/platform/observability.md): Logs, traces, and alerts for every runtime decision — so security teams can audit AI traffic, investigate incidents, and feed SIEM pipelines. - [Policies & Enforcement](https://docs.neuraltrust.ai/trustgate/platform/policies.md): How TrustGate turns detections into decisions — the Where / When / Then model, action semantics, precedence, and the policy lifecycle. - [Security capabilities](https://docs.neuraltrust.ai/trustgate/platform/security-capabilities.md): A map of the detectors and controls TrustGate ships with, grouped by the risk they address. - [Application security](https://docs.neuraltrust.ai/trustgate/platform/security/application-security.md): Classic application-layer controls adapted to LLM traffic — injection protection, code sanitation, CORS, and IP allow-listing. Applied at the Gateway surface before prompts reach the model. - [Content moderation](https://docs.neuraltrust.ai/trustgate/platform/security/content-moderation.md): Keep prompts and responses on-topic and on-policy. Pick from a built-in Topics catalog in the policy `When` picker and apply to Input or Output. - [Data protection & masking](https://docs.neuraltrust.ai/trustgate/platform/security/data-protection.md): Detect and mask PII, credentials, and custom sensitive entities on prompts and responses — before they leave your perimeter or come back from the model. - [Document analyzer](https://docs.neuraltrust.ai/trustgate/platform/security/document-analyzer.md): Inspect uploaded files before they reach the model — extract content via OCR and parsing, then run PII and jailbreak detections over the full document. - [Prompt security](https://docs.neuraltrust.ai/trustgate/platform/security/prompt-security.md): Detect jailbreaks and prompt injections before they reach the model. Powered by the Prompt Guard detection, configured inline on a policy. - [URL analyzer](https://docs.neuraltrust.ai/trustgate/platform/security/url-analyzer.md): Fetch and inspect the content behind URLs in prompts and responses — detect indirect prompt injection and PII hidden in linked pages before the model sees them. - [Tool guard](https://docs.neuraltrust.ai/trustgate/platform/tools/tool-guard.md): Scan the agent's own definition — system prompt, tool descriptions, and function descriptions — for jailbreak attempts and prompt injections planted in the agent itself. - [Tool permission](https://docs.neuraltrust.ai/trustgate/platform/tools/tool-permission.md): Filter the `tools` array in LLM requests with an allow-list or deny-list so unauthorized tools never reach the model. - [Tool selection](https://docs.neuraltrust.ai/trustgate/platform/tools/tool-selection.md): Validate the tool call the model actually emits — name, schema, and optional semantic check — to catch hallucinated tools and malformed arguments. - [By Fingerprint](https://docs.neuraltrust.ai/trustgate/rate-limit/fingerprint.md) - [Global System-Wide Limits](https://docs.neuraltrust.ai/trustgate/rate-limit/global.md) - [By IP Address](https://docs.neuraltrust.ai/trustgate/rate-limit/ip-address.md) - [Overview](https://docs.neuraltrust.ai/trustgate/rate-limit/overview.md) - [Request Size Limiting](https://docs.neuraltrust.ai/trustgate/rate-limit/size-limiting.md) - [By Tokens](https://docs.neuraltrust.ai/trustgate/rate-limit/token.md): Rate limit AI API requests based on actual token consumption using a sliding window counter - [By User ID](https://docs.neuraltrust.ai/trustgate/rate-limit/user.md) - [HTTP Security](https://docs.neuraltrust.ai/trustgate/server-security/http-security.md) - [TLS](https://docs.neuraltrust.ai/trustgate/server-security/tls.md) - [Anomaly Detection](https://docs.neuraltrust.ai/trustgate/traffic-management/anomaly-detection/anomaly-detector.md) - [Bot Detection](https://docs.neuraltrust.ai/trustgate/traffic-management/bot-detector/bot-detector.md) - [Least Connections](https://docs.neuraltrust.ai/trustgate/traffic-management/load-balancing/least-connections.md) - [Overview](https://docs.neuraltrust.ai/trustgate/traffic-management/load-balancing/overview.md) - [Random Balancing](https://docs.neuraltrust.ai/trustgate/traffic-management/load-balancing/random.md) - [Round-Robin](https://docs.neuraltrust.ai/trustgate/traffic-management/load-balancing/round-robin.md) - [Semantic](https://docs.neuraltrust.ai/trustgate/traffic-management/load-balancing/semantic.md) - [Weighted Round-Robin](https://docs.neuraltrust.ai/trustgate/traffic-management/load-balancing/w-round-robin.md) - [Rule Object](https://docs.neuraltrust.ai/trustgate/traffic-management/rules-forwarding/rule-object.md) - [Service Object](https://docs.neuraltrust.ai/trustgate/traffic-management/rules-forwarding/service-object.md) - [Upstream Object](https://docs.neuraltrust.ai/trustgate/traffic-management/rules-forwarding/upstream-object.md) - [Alerts](https://docs.neuraltrust.ai/trustlens/alerts.md): Rule-based alerts that notify your team when an AI resource crosses a risk threshold — so posture regressions never sit unnoticed. - [Data handling](https://docs.neuraltrust.ai/trustlens/data-handling.md): What TrustLens collects, what it never collects, where it stores data, and how to revoke access. - [How it works](https://docs.neuraltrust.ai/trustlens/how-it-works.md): The five stages of the TrustLens lifecycle — connect, discover, assess, monitor, and alert — and how data flows from your environment into a single AI inventory. - [Azure](https://docs.neuraltrust.ai/trustlens/integrations/azure.md): Azure AI Foundry (v2), AI Hub (classic Foundry), Azure OpenAI Classic (v1), and legacy ML Workspaces — all under one integration. - [Endpoint Discovery (MDM)](https://docs.neuraltrust.ai/trustlens/integrations/endpoint-mdm.md): Deploy a read-only Device Discovery script via Microsoft Intune or Kandji to inventory AI tools — IDEs, browsers, extensions, agent CLIs, MCP servers, and agent configs — across macOS and Windows endpoints. - [GCP Vertex AI](https://docs.neuraltrust.ai/trustlens/integrations/gcp-vertex-ai.md): Discover and monitor Vertex AI Reasoning Engines, models, datasets, and Model Armor guardrails across your Google Cloud project. - [GitHub](https://docs.neuraltrust.ai/trustlens/integrations/github.md): Discover agent configs, MCP server definitions, and agent source code across your GitHub organization using a read-only GitHub App. - [M365 Copilot & Copilot Studio](https://docs.neuraltrust.ai/trustlens/integrations/m365-copilot.md): Discover Copilot Studio bots via Dataverse and Microsoft 365 Copilot agents via the Microsoft Graph Agent Registry. - [Mistral AI](https://docs.neuraltrust.ai/trustlens/integrations/mistral.md): Discover and monitor Mistral agents, models, files, document libraries, and native moderation guardrails using a single API key. - [Inventory](https://docs.neuraltrust.ai/trustlens/inventory.md): The unified catalog of every AI surface across your organization — agents, models, datasets, IDEs, browsers, extensions, agent CLIs, MCP servers, agent configs, and managed endpoints. - [Overview](https://docs.neuraltrust.ai/trustlens/overview.md): Discover and continuously assess every AI surface across your organization — agents, models, IDEs, browsers, MCP servers, and managed endpoints — from a single inventory. - [Risk & findings](https://docs.neuraltrust.ai/trustlens/risk-and-findings.md): How TrustLens scores posture — the security controls evaluated per resource type, their weights, and how individual control results roll up to a 0–100 score and a risk level. - [Trusttest sample code](https://docs.neuraltrust.ai/trusttest-sample-code.md) - [Connect to NeuralTrust](https://docs.neuraltrust.ai/trusttest/connect/client.md) - [Custom Targets](https://docs.neuraltrust.ai/trusttest/connect/custom.md) - [HTTP Target](https://docs.neuraltrust.ai/trusttest/connect/http.md) - [LLMs & Embeddings](https://docs.neuraltrust.ai/trusttest/connect/llms.md) - [Overview](https://docs.neuraltrust.ai/trusttest/connect/overview.md) - [Evaluation](https://docs.neuraltrust.ai/trusttest/core-concepts/evaluation-scenarios.md) - [Overview](https://docs.neuraltrust.ai/trusttest/core-concepts/overview.md) - [Test Generation](https://docs.neuraltrust.ai/trusttest/core-concepts/test-cases.md) - [Agentic Behavior](https://docs.neuraltrust.ai/trusttest/create/agentic-behavior.md) - [Test Generation](https://docs.neuraltrust.ai/trusttest/create/automatic-test-generation.md) - [Content Bias](https://docs.neuraltrust.ai/trusttest/create/content-bias.md) - [Creating Custom Probes](https://docs.neuraltrust.ai/trusttest/create/creating-custom-probes.md): Developer guide for building custom attack probes in TrustTest - [Crescendo](https://docs.neuraltrust.ai/trusttest/create/crescendo.md) - [From Dataset](https://docs.neuraltrust.ai/trusttest/create/dataset.md) - [Echo Chamber](https://docs.neuraltrust.ai/trusttest/create/echo-chamber.md) - [From Dataset](https://docs.neuraltrust.ai/trusttest/create/functional/from-dataset.md): Create functional tests from existing question-answer datasets - [From Prompt](https://docs.neuraltrust.ai/trusttest/create/functional/from-prompt.md): Generate functional tests dynamically using LLM-powered prompt generation - [From RAG](https://docs.neuraltrust.ai/trusttest/create/functional/from-rag.md): Generate functional tests from your Retrieval-Augmented Generation knowledge base - [Overview](https://docs.neuraltrust.ai/trusttest/create/functional/overview.md): Evaluate your AI model's functional correctness and quality - [Input Leakage](https://docs.neuraltrust.ai/trusttest/create/input-leakage.md) - [Capture the Flag](https://docs.neuraltrust.ai/trusttest/create/iterate.md) - [Azure](https://docs.neuraltrust.ai/trusttest/create/knowledge-base/connectors/azure.md) - [In memory](https://docs.neuraltrust.ai/trusttest/create/knowledge-base/connectors/in-memory.md) - [Neo4j](https://docs.neuraltrust.ai/trusttest/create/knowledge-base/connectors/neo4j.md) - [Postgres](https://docs.neuraltrust.ai/trusttest/create/knowledge-base/connectors/postgres.md) - [Upstash](https://docs.neuraltrust.ai/trusttest/create/knowledge-base/connectors/upstash.md) - [Overview](https://docs.neuraltrust.ai/trusttest/create/knowledge-base/overview.md) - [Off-Topics](https://docs.neuraltrust.ai/trusttest/create/off-topic.md) - [Overview](https://docs.neuraltrust.ai/trusttest/create/overview.md) - [From Prompt](https://docs.neuraltrust.ai/trusttest/create/prompt-dataset.md) - [Prompt Injections](https://docs.neuraltrust.ai/trusttest/create/prompt-injections.md) - [Sensitive Data Leak](https://docs.neuraltrust.ai/trusttest/create/sensitive-data-leak.md) - [System Prompt Disclosure](https://docs.neuraltrust.ai/trusttest/create/system-prompt-disclosure.md) - [Overview](https://docs.neuraltrust.ai/trusttest/create/threat-detection/overview.md): Complete reference of all TrustTest attack probes and techniques - [From Dataset](https://docs.neuraltrust.ai/trusttest/create/threat-detection/prompt-injections/from-dataset.md): Load prompt injection attacks from curated or custom datasets - [Crescendo Attack](https://docs.neuraltrust.ai/trusttest/create/threat-detection/prompt-injections/multi-turn/crescendo.md): Test resistance to gradual escalation attacks across multiple turns - [Echo Chamber Attack](https://docs.neuraltrust.ai/trusttest/create/threat-detection/prompt-injections/multi-turn/echo-chamber.md): Test resistance to reinforcement-based manipulation through positive feedback - [Multi-Turn Manipulation](https://docs.neuraltrust.ai/trusttest/create/threat-detection/prompt-injections/multi-turn/multi-turn-manipulation.md): Test resistance to gradual conditioning across multiple conversation turns - [Multi-Turn Attacks](https://docs.neuraltrust.ai/trusttest/create/threat-detection/prompt-injections/multi-turn/overview.md): Sophisticated attacks across multiple conversation turns - [Prompt Injections Overview](https://docs.neuraltrust.ai/trusttest/create/threat-detection/prompt-injections/overview.md): Complete catalog of prompt injection attack techniques in TrustTest - [Best-of-N Jailbreaking](https://docs.neuraltrust.ai/trusttest/create/threat-detection/prompt-injections/single-turn/best-of-n.md): Test against multiple jailbreak variations to find model weaknesses - [DAN Jailbreak](https://docs.neuraltrust.ai/trusttest/create/threat-detection/prompt-injections/single-turn/dan-jailbreak.md): Test resistance to "Do Anything Now" persona-based jailbreak attacks - [Single Turn Attacks](https://docs.neuraltrust.ai/trusttest/create/threat-detection/prompt-injections/single-turn/overview.md): Direct prompt injection attacks delivered in a single message - [Unsafe Outputs](https://docs.neuraltrust.ai/trusttest/create/unsafe-outputs.md) - [Evaluation Context](https://docs.neuraltrust.ai/trusttest/evaluate-result/evaluation-strategy.md) - [BLEU](https://docs.neuraltrust.ai/trusttest/evaluate-result/heuristics/bleu.md) - [Equals](https://docs.neuraltrust.ai/trusttest/evaluate-result/heuristics/equals.md) - [Language](https://docs.neuraltrust.ai/trusttest/evaluate-result/heuristics/language.md) - [Overview](https://docs.neuraltrust.ai/trusttest/evaluate-result/heuristics/overview.md) - [Regex](https://docs.neuraltrust.ai/trusttest/evaluate-result/heuristics/regex.md) - [Completeness](https://docs.neuraltrust.ai/trusttest/evaluate-result/llm-as-a-judge/completeness.md) - [Correctness](https://docs.neuraltrust.ai/trusttest/evaluate-result/llm-as-a-judge/correctness.md) - [Custom](https://docs.neuraltrust.ai/trusttest/evaluate-result/llm-as-a-judge/custom.md) - [Overview](https://docs.neuraltrust.ai/trusttest/evaluate-result/llm-as-a-judge/overview.md) - [RAG Poisoning](https://docs.neuraltrust.ai/trusttest/evaluate-result/llm-as-a-judge/rag-poisoning.md) - [Tone](https://docs.neuraltrust.ai/trusttest/evaluate-result/llm-as-a-judge/tone.md) - [True/False](https://docs.neuraltrust.ai/trusttest/evaluate-result/llm-as-a-judge/true-false.md) - [URL Correctness](https://docs.neuraltrust.ai/trusttest/evaluate-result/llm-as-a-judge/url-correctness.md) - [Overview](https://docs.neuraltrust.ai/trusttest/evaluate-result/overview.md) - [Installation](https://docs.neuraltrust.ai/trusttest/getting-started/installation.md) - [Overview](https://docs.neuraltrust.ai/trusttest/getting-started/overview.md) - [Quickstart](https://docs.neuraltrust.ai/trusttest/getting-started/quickstart.md) - [Run Basic Red Teaming](https://docs.neuraltrust.ai/trusttest/getting-started/tutorials/basic-red-teaming.md) - [Save and load Scenarios](https://docs.neuraltrust.ai/trusttest/getting-started/tutorials/client.md) - [Run Responsibility Evaluation](https://docs.neuraltrust.ai/trusttest/getting-started/tutorials/compliance.md) - [Custom LLM as a Judge](https://docs.neuraltrust.ai/trusttest/getting-started/tutorials/custom-llm-judge.md) - [Http Target](https://docs.neuraltrust.ai/trusttest/getting-started/tutorials/http-model.md) - [Run Capture The Flag Evaluation](https://docs.neuraltrust.ai/trusttest/getting-started/tutorials/iterate.md) - [LLM as a Judge](https://docs.neuraltrust.ai/trusttest/getting-started/tutorials/llm-as-judge.md) - [Quickstart with Local LLM](https://docs.neuraltrust.ai/trusttest/getting-started/tutorials/local-llm.md) - [Test generation with Prompt](https://docs.neuraltrust.ai/trusttest/getting-started/tutorials/prompt-dataset.md) - [Test generation with RAG](https://docs.neuraltrust.ai/trusttest/getting-started/tutorials/rag.md) ## OpenAPI Specs - [openapi](https://docs.neuraltrust.ai/api-reference/openapi.json) - [openapi-actions](https://docs.neuraltrust.ai/api-reference/openapi-actions.json) ## Optional - [Blog](https://neuraltrust.ai/blog) - [Github](https://github.com/NeuralTrust) - [Community](https://neuraltrustcommunity.slack.com/join/shared_invite/zt-2xl47cag6-_HFNpltIULnA3wh4R6AqBg)