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

Section titled “Agent ”

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
  • Integrations — the services it can connect to and act on
  • Knowledge — retrievable context it can search
  • Skills — reusable workflows for specific task types

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

Integration Core

Section titled “Integration ”

An integration is a connectable external service (Slack, GitHub, Notion, and more). When you authenticate one, you create a connection — a live instance agents can use. Every connection has an identity: signing in with your own account creates a personal connection (acts as you; on a team it is shared with your team unless you choose otherwise when you connect), while bot tokens, API keys, and service accounts create a shared team connection anyone in the org can use.

Category Examples
Messaging Slack
Version Control GitHub
Productivity Google Workspace (Docs, Sheets, Drive, Calendar), Notion
Project Management Jira, Confluence
Custom Custom MCP (any service with an MCP endpoint)

When you attach an integration to an agent, you control exactly what it is allowed to do (e.g., read issues but not delete repositories).

Knowledge Core

Section titled “Knowledge ”

Knowledge is retrievable context your agent can search 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
  • ServiceNow — sync knowledge articles and incidents

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

Skill Core

Section titled “Skill ”

A skill is a reusable workflow 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.

Loop Core

Section titled “Loop ”

A Loop starts your agent when an event arrives or on a schedule.

Trigger → Agent runs → Takes action


Triggers:
  • An event from a connection: a GitHub issue opened, a Slack bot
    mention, a Jira issue created, an email received
  • A schedule: once, hourly, daily, weekly, monthly, or a cron expression

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

Section titled “Credit ”

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
  • On Pro and Business, you can buy additional credits at any time
  • Auto top-up buys more only up to a monthly cap you set

See Credits & Billing → for the full breakdown.

How these concepts connect

Section titled “How these concepts connect”
User message / Loop trigger
         ↓
      [Agent]
     ↙   ↓   ↘
Integrations  Knowledge  Skills
   ↓            ↓           ↓
Action       Answer      Method