Skip to content
Auteryn

Key Concepts

Before you build, it helps to understand the vocabulary. Read these once and the rest of the docs will make much more sense.

Agent Core

An agent is an AI assistant you configure for a specific purpose. It has:

  • An identity — its name, role, and personality
  • Instructions — what it should do and how it should behave
  • Tools — the services and APIs it can use
  • Knowledge — the information it can look up
  • Playbooks — reusable skills it can execute

You can have as many agents as you need — one per use case, or one shared agent for your whole team.

Tool Core

A tool is an integration that gives your agent the ability to take real-world actions. Tools are organized by category:

CategoryExamples
MessagingSlack, Telegram, WhatsApp
Version ControlGitHub
ProductivityGoogle Workspace (Docs, Sheets, Drive, Calendar), Notion
Project ManagementJira, Confluence
Customer SupportZendesk, Salesforce
E-CommerceShopify, WooCommerce
MonitoringDatadog, Sentry
CustomAny REST API via webhooks

When you connect a tool, you control exactly what the agent is allowed to do (e.g., “read issues” but not “delete repositories”).

Knowledge Base Core

A knowledge base is a collection of documents or content that your agent can search through when answering questions or completing tasks.

Supported sources:

  • Documents — upload PDFs, Word docs, text files
  • Notion — sync pages and databases
  • Confluence — sync spaces and pages
  • Google Drive — sync folders and documents
  • GitHub — sync repositories (README, docs, code)
  • Web Crawler — crawl any public website

The agent retrieves the most relevant chunks automatically — you don’t need to manage this manually.

Playbook Core

A playbook is a reusable skill template that tells your agent how to approach a specific type of task. Think of it as a standard operating procedure for the agent.

Coding

Write, debug, and review code following best practices.

Research

Search, read, and synthesize information from multiple sources.

Customer Support

Handle questions, escalations, and follow-ups professionally.

DevOps

Monitor systems, respond to incidents, manage deployments.

Flow Core

A flow is an automation that triggers your agent based on an event or schedule — without you having to manually start it.

Trigger → Agent runs → Takes action


Triggers:
  • Webhook / API event
  • Scheduled time (cron)
  • Slack message mention
  • New email
  • GitHub issue opened

Examples:

  • Every time a new GitHub issue is opened → agent triages and labels it
  • Every Monday at 9am → agent generates a weekly report and posts to Slack

Credit Billing

Credits are the unit of measurement for your Auteryn usage. Each agent run consumes credits based on the complexity and length of the task.

  • Your plan includes a monthly credit allowance
  • You can purchase additional credits at any time
  • You can set budget limits per agent to prevent overspend

See Credits & Billing → for the full breakdown.

How these concepts connect

User message / Flow trigger
         ↓
      [Agent]
     ↙   ↓   ↘
  Tools  KB  Playbooks
   ↓     ↓      ↓
Action Answer  Method