Method Agents | Method Platform

Safely deploy AI to investigate, validate, escalate, or close Issues.

Overview

Method’s Agents framework enables safe deployment of AI agents governed by robust and granular user-defined policies. Method Agents are able to investigate Issues, validate, escalate, or close them, and draft Reports capturing their findings and reasoning. They do this using MCP Tools that ship with the platform. Users can govern their behavior with Policies that enable Agents to operate in a permissioned and transparent manner.

Agent Components

Method Agents are composed of:

A system prompt
A model
Targets
Approved Tools

Together, these define what the agent can do. Policies determine where and under what conditions it is allowed to do it.

The Agent Fleet application

The Agent Fleet application is where you create, view, and manage your Agents. Use it to configure new agents, attach MCP Tools, and adjust system prompts and models. Combine this with Policies to enforce approve, deny, or require-approval rules for agent actions across Agents, Environments, MCP Tools, and Agent Sessions.

Method-built Agent Fleet

Method ships with a set of pre-configured agents designed for common workflows—for example, investigating and triaging Issues or drafting Reports. You can use these as-is or duplicate and customize them to match your processes.

Create your own

Create custom Agents when you need behavior or tooling that the Method-built agents don’t provide. Define the name, description, system prompt, and model, then select the MCP Tools the agent may use. After that, use Policies to scope where the agent can run and whether its actions are approved, denied, or require approval.

Create an agent – system prompt and model

MCP Tools

Use the MCP Tools tab to browse and explore the tools that you can attach to agents. Each tool is described there so you can choose the right set of capabilities when configuring an agent.