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)

Prefer a template?

This guide builds an Internal agent from scratch. If you’d rather start from a template and deploy a customer-support agent to your website, follow the Interactive Quickstart Tutorial →.

---

Step-by-step

1. Create a new agent

   Log in to the Auteryn Console. If you have no agents yet, the home screen offers three ways to begin — Describe it, Start from a template and Start blank. Pick Start blank and give the agent a name — e.g., “My Research Assistant”. (Once you have an agent, Agents → New agent opens the same thing.)

   Select Internal as the agent type for now.

   Agent types

   Internal agents are for your team’s use — with an optional Allow external guests toggle to invite people outside your org to specific conversations. Customer-Facing agents are for deployment to external users via channels. You can change the type later.

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

   Your first agent lands you back on the Console home with a Say hello card — click Open in workspace. (For later agents you stay on the agent’s page; the button there is Start chat.)

   In the chat workspace:

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

   The first reply takes a little longer while the agent’s computer starts — it stays warm after that. You’ll see its steps, like web searches, appear inline as they happen.

4. (Optional) Add a knowledge

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

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

5. (Optional) Connect an integration

   To give your agent access to external services:

   • Click Integrations in the left sidebar → New Connection
   • Pick a service (e.g., GitHub, Slack, Google Drive)
   • Follow the OAuth connection flow
   • Go back to your agent → Integrations tab → enable the connection

---

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?

Better Instructions

Learn how to write instructions that make your agent far more reliable. Writing Instructions →

Connect Integrations

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

Deploy It

Publish your agent to Telegram, WhatsApp, or a web widget. Internal agents can use Slack via Channels. Deploy →

Automate

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