Skip to main content
This guide walks through every step of getting started with Orq.ai. By the end, a working AI agent that can search the web and answer questions is live, with full visibility into every call it makes.
The CLI is the fastest way through this guide. Studio and API alternatives are included where they exist.

Set up an Account

1

Create an Orq.ai account

Sign up for a free Orq.ai account and create a workspace.
2

Install the CLI

The Orq.ai CLI installs with a single command and walks through the first request. It links directly to the account, no manual key setup needed.
After installation, the CLI prompts for authentication and asks what to build: AI Gateway, Observability, or MCP.
See CLI reference for the full command list and configuration options.
3

Capture the API key

During setup, the CLI mints a project-scoped API key and saves it locally. The terminal shows a masked preview; the full key is written to .env:
The full key is also displayed once in the AI Studio getting-started screen. Source the .env file to export it for the terminal:
The code samples in the next steps read the key from this environment variable.

Create and run an Agent

1

Build an agent

Build an Agent named my-assistant with OpenAI GPT-5.6 Sol and the Web Search and Web Scraper tools.See Build Agents for the full field reference and configuration options.
See CLI reference for the full command reference. Run orq agents create --help for the full flag reference.
2

Call the agent

Send a message to my-assistant and read the response.
See CLI reference for the full command reference. Run orq responses create --help for the full flag reference.
3

View traces

Every Agent call is automatically traced. Execution history, token counts, latency, and cost are visible in the AI Studio, from the CLI, or queryable through MCP.
See the full execution history, including model calls, tool use, token counts, and latency.
Run orq traces search --help for the full flag reference.

Run the first experiment

Compare prompts, models, and configurations side by side to find what performs best before shipping.

Add an evaluator

Score the Agent’s outputs automatically with LLM-based, code, or human Evaluators.

Connect a knowledge base

Give the Agent access to documents and data with built-in RAG.

Log the first trace

Already running agents elsewhere? Connect via OpenTelemetry to get full trace visibility and cost tracking.