Skip to content
Auteryn

Quickstart: First Agent in 10 Minutes

This guide takes you from a blank console to a running AI agent. By the end, you’ll have created an agent, given it instructions, and run your first task.

Prerequisites: An Auteryn account — sign up here (free, no credit card needed)

Step-by-step

  1. Create a new agent

    Log in to the Auteryn Console, click New Agent in the top-right corner, and give it a name — e.g., “My Research Assistant”.

    Select Internal as the agent type for now.

  2. Write instructions

    In the Instructions field, describe what this agent should do. Here’s a simple example to paste in:

    You are a research assistant. Your job is to:
    - Answer questions clearly and concisely
    - Search the web when you need up-to-date information
    - Summarize long documents into bullet points
    - Always cite your sources
    

    Be professional but conversational. If you're unsure about something, say so.

    Click Save.

  3. Run your first task

    In the Test panel on the right side of the agent page:

    • Type a question: What are the most popular AI agent frameworks in 2025?
    • Press Enter or click Run
    • Watch the agent think and respond in real time

    You’ll see tool calls (like web searches) appear inline as they happen.

  4. (Optional) Add a knowledge base

    If you want the agent to answer questions about your specific content:

    • Click Knowledge Bases in the left sidebar → New Knowledge Base
    • Upload a PDF or paste a URL to crawl
    • Go back to your agent → Knowledge tab → attach the knowledge base
    • Ask a question specific to your document

  5. (Optional) Connect a tool

    To give your agent real superpowers:

    • Click Tools in the left sidebar → Connect Tool
    • Pick an integration (e.g., GitHub, Slack, Google Drive)
    • Follow the OAuth connection flow
    • Go back to your agent → Tools tab → enable the tool

What just happened?

When you ran the task, the agent:

  1. Read your instructions to understand its role
  2. Classified the task complexity and selected the right execution mode
  3. Searched the web for up-to-date information (if web search is enabled)
  4. Synthesized the findings into a response
  5. Streamed the response back to you in real time

What’s next?

Connect Tools

GitHub, Slack, Google, Jira — give your agent real capabilities. Tools →

Deploy It

Publish your agent to Telegram, Slack, WhatsApp, or a web widget. Deploy →

Automate

Trigger your agent from events — webhooks, schedules, Slack messages. Flows →