liveBook · Manning

Action

As explained in Designing AI Agents

An agent capability for executing external operations or producing artifacts in response to reasoning.

Action turns a reasoning proposal into an interaction with an external system or a structured artifact. It can read a document, call an API, write a file, update a database, send a message, initiate a payment, or deploy code. Tools may be selected at runtime, and their outcomes are uncertain. section 6.1 section 2.2.1

For a state-changing task, the action is a bounded, verifiable change—not merely a tool call. A successful return, a green test, or a model saying “done” is evidence only of what that signal observes. Completion requires task-specific evidence that the intended effect was accepted. section 6.0 section 6.1 section 2.2.1

An action contract connects the intended effect, execution boundary, state basis, commit identity, and acceptance evidence. Governance limits what may execute; reflection compares the result with the intent and can trigger revision or termination. Some effects are irreversible, so controls must operate before execution as well as after it. section 6.9 section 2.2.1

Choose controls for the task’s failure modes rather than adding every pattern:

  • Prompt chaining passes named artifacts through checked gates when the sequence is known. section 6.9
  • Tool dispatch restricts the eligible capabilities before selection and rechecks the exact call’s authority, provenance, and freshness. Discovery and schema conformance do not grant permission. section 6.9
  • Plan-and-execute persists dependencies, progress, uncertain effects, and evidence when restarting after interruption would be unsafe. section 6.9
  • A guardrail sandwich places lower-trust execution between protected preconditions and independent postconditions. Containment limits reach; acceptance still requires task-specific evidence. section 6.9

A valid image can still be the wrong result

An agent publishes a map imagery layer and receives a valid PNG, but the intended viewer shows an opaque white rectangle over the basemap. Verification in that viewer checks the requested overlay effect, which the image response alone cannot establish. section 6.0

A paid status can hide a duplicate transfer

A payroll agent makes an authorized payment, then follows an instruction planted in imported data to submit it again. A PAID status does not reveal the duplicate; the action needs a record connecting the authorization to attempts and actual transfers. section 6.0

How Designing AI Agents covers it

How deep it goes
Defines action contracts and summarizes dispatch, chaining, planning, and guardrail controls, including acceptance evidence and recovery concerns.
Examples
Uses map-layer publication, duplicate payroll transfers, and a structured code-review output to illustrate action and its failure modes.
What you can do after
Evaluate action boundaries and completion evidence, and choose controls for failures such as duplicate calls, stale state, and missing receipts.
How it connects
Connects reasoning to tool use, reflection, governance, prompt injection, and task-specific verification.

Also explained in

Compare how 17 books explain action →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Designing AI Agents. The section links point to the parts of the book it draws on.