For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Trust CenterStatusSupportGet a demoPlatform
DocumentationEvals API ReferenceIntegrations & OTELPlatform SettingsSelf-HostingChangelog
DocumentationEvals API ReferenceIntegrations & OTELPlatform SettingsSelf-HostingChangelog
    • Platform Settings
    • Data Residency
    • RBAC
  • Project Settings
    • API Keys
    • Team Members
    • Roles & Permissions
    • Transformers
    • Integrations
    • Alerts
    • AI Connections
      • Confident Agent
    • Model Costs
    • Data Usage
    • Evaluation Models
    • Evaluation Rules
    • Annotation Options
    • Classifiers
    • Data Sources
    • Data Retention
    • Audit Logs
  • Organization Settings
    • Projects
    • Users
    • Roles & Permissions
    • Model Credentials
    • SSO
    • Data Retention
    • Audit Logs
    • Feature Access
LogoLogo
Trust CenterStatusSupportGet a demoPlatform
On this page
  • How It Works
  • Requirements
  • Quick Start
  • Docker Container (CLI)
  • Docker Compose
  • Environment Variables
  • Using with AI Connections
Project SettingsAI Connections

Confident Agent

Connect to internal AI endpoints behind firewalls without opening inbound ports.
Was this page helpful?
Previous

Model Costs

Configure LLM model costs for usage tracking and cost estimation for LLM tracing.
Next
Built with

The Confident Agent is a lightweight bridge agent that allows Confident AI’s evaluation server to reach internal API endpoints behind firewalls, without opening inbound ports. This is a feature available as part of AI Connections.

GitHub Repository

View the source code, report issues, and find the latest releases.

How It Works

The agent connects outbound via WebSocket Secure (WSS) to Confident AI’s evaluation server and waits for work. When an evaluation runs, requests are forwarded through the WebSocket tunnel to your internal endpoint and responses are relayed back.

The Confident Agent supports the following response modes:

  • HTTP Response — standard JSON responses
  • HTTP Streaming — chunked HTTP streaming responses
  • SSE Streaming — Server-Sent Events streaming responses

Requirements

  • Outbound internet access on port 443 (WSS) from the machine running the agent
  • Network access from the agent to your internal API endpoint
  • No inbound ports need to be opened

Quick Start

Docker Container (CLI)

Run the agent as a Docker container:

$docker run -d \
> -e CONFIDENT_API_KEY=<your-api-key> \
> -e CONFIDENT_WS_BASE_URL=wss://deepeval.confident-ai.com/ws/relay \
> confidentai/confident-agent

Docker Compose

Create a compose.yaml file:

1services:
2 confident-agent:
3 image: confidentai/confident-agent
4 restart: unless-stopped
5 environment:
6 - CONFIDENT_API_KEY=${CONFIDENT_API_KEY}
7 - CONFIDENT_WS_BASE_URL=${CONFIDENT_WS_BASE_URL:-wss://deepeval.confident-ai.com/ws/relay}

Then start the agent:

$docker compose up -d

Environment Variables

VariableDescriptionRequired
CONFIDENT_API_KEYYour Confident AI API keyYes
CONFIDENT_WS_BASE_URLWebSocket relay URLYes

Using with AI Connections

Once the Confident Agent is running and connected, your AI Connections can target internal endpoints that are not publicly accessible. The agent transparently tunnels requests from Confident AI’s evaluation server to your internal endpoint—no changes to your AI Connection configuration are needed beyond pointing it to the internal URL.

The agent handles reconnection automatically. If the WebSocket connection drops, it will re-establish the tunnel without manual intervention.