Declare what actions an AI agent may propose before runtime execution.
A lightweight public schema and validator for describing an agent's tools, actions, authority requirements, review requirements, reliance requirements, payload policies, and redaction hints before runtime deployment.
Before an agent enters production, the organization should know what tools it may use, what actions it may propose, which actions require authority, which require human review, what reliance evidence should be captured, and which payload fields may require redaction.
Without a manifest, this information is often scattered across code, prompts, tool definitions, policies, and tribal knowledge.
Which tools an agent may call is often implied by code and prompts rather than declared in one place teams can review.
Writes, exports, purchases, deletes, and external sends are not consistently marked as the actions that need authority or review.
Whether an action needs a person in the loop is decided ad hoc, so review coverage varies between teams and deployments.
Fields that carry personal or regulated data are rarely marked ahead of time, leaving redaction to guesswork at export.
Policy engines and control planes have no single, versioned inventory of the agent's action surface to enforce against.
As tools and prompts change, the real set of actions an agent can propose drifts away from any written description of it.
Agent Action Manifest helps teams create a structured declaration of what an agent may propose. It does not execute actions and does not enforce runtime controls by itself. It creates a portable action inventory that runtime systems can use or reference.
Names each tool the agent may use, with a stable identifier runtime systems can reference.
Describes each action the agent may propose and the tool and action type it runs through.
Marks which actions require an authorization context before they may proceed.
Flags the actions that require human review before they can be executed.
States which actions should record the sources the agent relied on.
Constrains the shape and content of the payloads an action is allowed to carry.
Marks the fields that should be redacted when run records are exported.
Checks a manifest against the schema so declarations stay well-formed and complete.
Agent Action Manifest is the Declare layer. It prepares a structured action inventory before runtime. Agent Control Plane can then record and govern the actions that the agent actually proposes during execution.
Need a portable, versioned inventory of an agent's action surface that runtime systems can enforce against.
Need to see which actions require authority or review before an agent reaches production.
Need a stable declaration of what an agent is permitted to propose, independent of prompts and code.
Need a small schema they can add beside existing tool definitions to declare intent before runtime.
Need a human-readable record of the agent's declared action surface at a fixed point in time.