An API contract defines how a software component invokes an operation and what response it receives. For an agent that can freeze customer accounts, the contract makes the permitted request, required confirmation, and out-of-bounds response explicit. section 1.5.1
A contract can specify an endpoint, method, request and response schemas, status codes, and authentication. Those details define the callable interface, not the full business purpose, delegated authority, decision context, or evidence obligations behind a call. A technically valid request may still exceed the agent’s authority. section 6.2.3
Table 6.3 API, event, and conversational contracts
|
Contract type
|
Primary design concern
|
Typical contents
|
What it does not carry by itself
|
|
API contract
|
A callable operation’s request and response shape
|
Endpoint, method, request and response schemas, status
codes, authentication scheme
|
Runtime intent, delegated authority, decision context, and
evidence obligations
|
|
Event contract
|
A published fact, state change, or signal
|
Topic, event type, payload schema, producer, timestamp,
version
|
Why downstream action should occur, who owns the outcome,
and how causation is reconstructed
|
|
Conversational contract
|
The meaning and boundaries of an agentic interaction
|
Intent, context, constraints, authority, outcome, evidence
obligations
|
Transport mechanism, endpoint implementation, and full
payload schema
|
Compare API, event, and conversational contracts by the interaction each defines and the information each leaves unspecified. section 6.2.3
Production-history lookup
In a quality investigation, the API contract defines how an agent retrieves production history from a manufacturing execution system. A separate conversational contract sets the purpose and limits of that lookup: assess whether a lot needs containment without placing it on hold or contacting outside parties. section 6.2.3

























































