Skip to main content
Agents are reusable AI configurations you build once and run on demand. An agent pairs a system prompt with the connectors, apps, skills, and permissions it’s allowed to use — so it can autonomously query your data, call your APIs, and take action within boundaries you define.

​
What makes up an agent

FieldDescription
System promptThe instructions that define the agent’s behavior and goals.
ModelThe Claude model the agent runs on. Defaults to Claude Opus; you can switch to Sonnet or Haiku.
ConnectorsThe resources the agent may query (Postgres, Slack, Salesforce, …).
ApplicationsDeployed Major apps the agent may invoke.
SkillsReusable instruction bundles that extend the agent’s abilities. See Skills.
Tool permissionsPer-tool allow/ask/deny rules for connectors and app endpoints. See Tool Permissions.
Environment variablesKey/value pairs made available to the agent at runtime, encrypted at rest.

​
Building with chat

Everything in the agents platform is built the same way: you describe what you want in chat and Major configures it for you. This applies to agents, their skills, and their schedules — there are no forms to fill out. Major drafts the configuration, wires up the right connectors and permissions, and you refine it by just asking (“use the production database”, “only run on weekdays”). The same conversation can research your connectors and apps to write a better system prompt. For an agent specifically:
  1. Create a new agent — it starts as a private draft.
  2. Describe its purpose; Major drafts the system prompt and attaches connectors, apps, and skills as needed.
  3. Review the auto-applied tool permissions and adjust if needed.
  4. Publish the agent to make it available to run.
Drafts stay private to you until you publish. Published agents can be shared with others in your organization.

​
Running an agent

Start a new chat and pick your agent, and it runs with the prompt, connectors, skills, and permissions you configured. Agents can also run without a person in the loop:

Schedules

Run an agent automatically on a cron schedule.

App triggers

Let your deployed apps start and manage agent runs.

​
Sharing and access

Agent access is role-based — User (run), Editor (edit and publish), and Admin (share) — and an agent can be shared with individuals or groups. When an agent is shared and run by someone other than its author, Major uses per-user credentials where a connector requires them, so each runner acts as themselves.

Access & Permissions

Full RBAC details for agents, skills, and schedules.