liveBook · Manning

Intent

As explained in Architecting for Autonomy

The desired purpose or objective that motivates an interaction or requested action.

Intent states why an interaction exists. In a conversational contract, it helps bound an agent’s actions alongside context, constraints, authority, expected outcome, and evidence obligations. State the purpose specifically enough to distinguish permitted interactions, without reducing it to an operation name. section 6.2.2

Quality investigation

“Assess whether lot 2418 requires containment” communicates why production history is relevant; “query production history” names an operation but not its purpose or when it is appropriate. section 6.2.2

Figure 6.2 Anatomy of a conversational contract. A conversational contract carries an agentic interaction from intent toward outcome. Context shapes how the intent is interpreted, constraints and authority define the boundary within which the agent may act, and the evidence obligation defines what must remain after the agent has acted.

See how intent moves toward an outcome while context, constraints, authority, and evidence obligations shape the interaction. section 6.2.2

How Architecting for Autonomy covers it

How deep it goes
Defines intent and contrasts it with an operation name through a concrete example.
Examples
Contrasts querying production history with assessing whether lot 2418 requires containment.
What you can do after
Understand how to state an agent’s purpose so it bounds an interaction rather than merely naming an operation.
How it connects
Links intent to context, constraints, authority, expected outcome, and evidence obligations in a conversational contract.

Also explained in

Compare how 9 books explain intent →

Related concepts

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