Callable surface
The set of actions an organization exposes so AI agents can invoke them directly, each described precisely enough to be agent-ready: meaning, inputs, permissions, side effects and recovery.
The callable surface is what an agent can actually call: the actions an organization has made available as defined operations rather than as screens. "We have APIs" is not the same answer, because an API built for developers may not tell an agent what an action means, what it changes, or what to do when the situation does not fit the happy path.
A callable action is agent-ready only when its meaning, permissions, constraints, side effects and recovery path are legible without a human operator filling the gaps.
Why it matters
The callable surface is part of the reasoning environment: a well-described action makes better agent behavior possible, a vague one invites guesses. Tool design is becoming product design, and the question moves from "do we have an interface?" to "what should the organization make callable?" Assess it as capability readiness, expose it through standards such as the Model Context Protocol and remember that capability is not authority.
Read more in The next AI interface may never be seen.
Related terms
Capability readiness
How ready an organization's actions are to be used by AI agents: whether each action is a real business capability, exposed cleanly, with clear permissions, side effects and recovery.
Model Context Protocol
An open standard, usually called MCP, for connecting AI models and agents to external tools and data sources in a consistent way, so they can discover and call an organization's capabilities.
Computer use
An AI agent operating software the way a person would — looking at screens, clicking and typing — which gives it an execution surface when cleaner integrations or APIs are unavailable.
Capability is not authority
A design principle for AI agents: being technically able to perform an action does not mean the agent should be permitted to perform it. Delegation needs gradients of authority.
Used in these essays
OpenAI Dots is a test of whether AI can carry a goal, not just complete a task
Dots matters less as another capable assistant than as a test of persistent delegation: can AI keep carrying a goal without giving the user a new system to manage?
The next AI interface may never be seen
Agents are turning software capabilities into an interface of their own. The next enterprise design problem is deciding what should be callable, by whom, and under which boundaries.