AI Agent OSGuarded mainnet beta. .rama identity, smart wallets, sponsored gas, permissions and scheduling are available for controlled testing.Open Agent OS
Learning center

AI Agent OS

Classifying Risk in Agent Workflows

Separate information retrieval, low-value execution, treasury activity and contract changes into clear risk tiers before automation.

In this guide

Practical outcomes

  • Define risk tiers
  • Map required approvals
  • Escalate sensitive actions

How this works in practice

Separate information retrieval, low-value execution, treasury activity and contract changes into clear risk tiers before automation.

A controlled agent separates the controller from the runtime. The controller owns the agent identity and defines policy, while a smart wallet, permission rules, quotas, relayer and scheduler constrain what the runtime can actually execute.

Implementation sequence

Turn the topic into a controlled implementation rather than a one-off transaction. Each step below should leave evidence a teammate, user or auditor can independently review.

  1. 01. Define risk tiers. Define the expected result, capture the relevant onchain or operational evidence, and stop for review if the result differs from the plan.
  2. 02. Map required approvals. Define the expected result, capture the relevant onchain or operational evidence, and stop for review if the result differs from the plan.
  3. 03. Escalate sensitive actions. Define the expected result, capture the relevant onchain or operational evidence, and stop for review if the result differs from the plan.

Evidence to retain

Record the .rama identity, controller, wallet, policy version, approval event, task identifier and resulting transaction hash. This makes a decision traceable without giving the agent unrestricted custody.

Control point

Start with small allocations, explicit recipient and contract allowlists, bounded session keys and a tested pause path. An automated workflow must never be the only place where authority or recovery knowledge exists.

Open Agent OSOpen RamaScan

Related guides

What Is Ramestta AI Agent OS?

An introduction to controlled onchain agents using .rama identity, smart wallets, scoped permissions, sponsored gas and scheduling.

Onchain AI Agents: A Practical Architecture

Learn how an AI runtime can coordinate with verifiable onchain identity, wallet permissions and bounded execution.

.rama Identity for AI Agents

Use readable .rama names to make agent ownership, discovery and wallet relationships understandable across the ecosystem.