Skip to content
Follow one Task from request to outcome
Public Preview

Agent harness: Task execution model and Tool Call outcomes

Explains the Duale AI Task execution model, Tool Call outcomes, and how to separate capability, authority, and Effect.

This page covers the Agent harness execution model, Task lifecycle, Tool Call outcomes, and the distinction between capability, authority, and Effect.

  • Task lifecycle from request to outcome.
  • Execution model terms and definitions.
  • Tool Call outcomes and recommended next actions.
  • Capability, authority, and Effect separation.
  • Continuation Tasks and Recall behavior.

Summaries were generated by AI.

Duale AI runs Tasks for your application. You submit an objective with its starting material, an answer format, and a deadline. The Task works toward that objective with Tools, and your application receives one outcome. The Agent harness is how Tasks behave; it is not a service or an API resource that you call.

A Task uses Tools from three places: Built-in Tools that Duale AI supplies, SDK Tools that your application serves, and MCP Tools from the servers you connect. A Task request carries no Tool definitions and cannot add, remove, or narrow Tools. The model chooses which Tool to use, and an available Tool can go unused. Tools explains each source.

An Agent is software that works toward an objective on behalf of an accountable person or organization. An Agent Identity supplies the credentials, attribution, and Platform permissions that an application uses. It does not define the application’s behavior. Identity owns credentials and access; your application keeps any behavior-version records it needs.

Follow one Task from request to outcome

One Task from request to outcomeYour application submits a Task with an objective, material, an answer format, a deadline and the Task ID it generated. While the Task works, it can stream answer text to your application. The Task sends Tool requests to Built-in Tools, to your SDK Tool Host and to your MCP servers, and each returns a Tool Result to the Task. Your application can request a Stop. The Task ends with one outcome: a completed answer, a failure, or a stopped Task.

Your application generates and keeps the Task ID, can show streamed answer text, and serves the Tool requests for its SDK Tools. It receives exactly one Task Outcome: a completed answer, a failure, or a stopped Task. The requested answer format or schema applies to the completed answer. A Tool Call or a Tool Result alone does not prove that an external operation succeeded.

Task execution explains the deadline, Stop, and delegated work. The SDK reference defines the submission, streaming, result, and Stop methods.

Use the current execution model

TermWhat it means
Task InputThe instruction, content, and data references supplied for one objective
TaskA request with its own identifier, deadline, response contract, and outcome
Task historyThe instructions, messages, Tool Calls, and Tool Results that a Task records
Model turnOne step in which the model reads the Task’s context and chooses its next action. One model turn can make several provider requests
ToolA named capability that can retrieve information or request an operation
Built-in ToolA Tool that Duale AI supplies to Tasks. Built-in Tools lists each one and the page that owns its behavior
Tool CallA request to use a Tool with particular arguments
Tool ResultThe Tool’s reported response, which the Task can use to continue its work
Tool Call outcomeHow a Tool Call ended, as the Dashboard shows it: Succeeded, Failed, Outcome unknown, or Blocked. Read a Tool Call outcome gives the next action for each
Task OutcomeA completed answer, a stopped Task, or a failure with typed problem information
Continuation TaskA new request that builds on selected history from a previous Task
RecallThe Built-in Tools with which the model rereads the Task’s own earlier work and searches the requests and final answers of earlier Tasks of the same Agent Identity. What a Task can recall from earlier Tasks
Delegated workA focused part of the Task’s work that the Task hands off and receives back inside the same Task. How a Task divides its work
To-do listThe steps a Task tracks for its own multi-step work. A continuation inherits it; your application does not read or change it
ExecutorThe Dashboard’s name for one part of a Task’s work, shown in the Task view

Use response.next() when you want a new instruction to build on an earlier Task. The continuation has its own result, deadline, and Stop. Context continuity explains the inherited history and independent branches. Start a new Task with ask() when you do not want the request to inherit that Task history. A new Task inherits nothing, but Recall can still find earlier Tasks of the same Agent Identity.

Read a Tool Call outcome

Every Tool Call ends with one outcome. The outcomes mean the same for Built-in Tools, SDK Tools, and MCP Tools, and the Dashboard Task view shows the outcome of each Tool Call.

OutcomeWhat it meansWhat to do
SucceededThe Tool reported a result.Use the result. Verify any material change at the system that owns it.
FailedThe Tool ran and did not succeed, including when the target refused the request.Fix the cause. Repeat the operation only when a repeat is safe.
Outcome unknownThe Tool stopped before it knew whether its effect happened, for example when a request timed out after it was sent to its target.Read the destination system before you repeat or compensate the operation.
BlockedDuale AI refused or limited the request under a policy, a safety rule, or a limit, for example a disabled MCP Connection or a refused package.Change the request, the policy, or the limit.
  • Outcome
    Succeeded
    What it means
    The Tool reported a result.
    What to do
    Use the result. Verify any material change at the system that owns it.
  • Outcome
    Failed
    What it means
    The Tool ran and did not succeed, including when the target refused the request.
    What to do
    Fix the cause. Repeat the operation only when a repeat is safe.
  • Outcome
    Outcome unknown
    What it means
    The Tool stopped before it knew whether its effect happened, for example when a request timed out after it was sent to its target.
    What to do
    Read the destination system before you repeat or compensate the operation.
  • Outcome
    Blocked
    What it means
    Duale AI refused or limited the request under a policy, a safety rule, or a limit, for example a disabled MCP Connection or a refused package.
    What to do
    Change the request, the policy, or the limit.

The Task view shows Timed out for a Tool Call that did not answer in time. A timeout does not confirm whether the Tool succeeded, so its outcome is Outcome unknown: read the destination system before any repeat. Tools Analytics adds categories for MCP Connections and a confirmed success rate: Operate Tools defines them. A Tool Result is a report, not proof that an Effect occurred.

Separate capability, authority, and Effect

These properties answer different questions:

PropertyQuestion it answers
AutonomyWhich actions can the application choose without a fresh external decision?
CapabilityWhich operations can it request through its available Tools?
Platform access authorizationWhich Platform resources does the caller have permission to use?
External-action authorityWhich action and arguments does the customer system permit?
EffectWhich state change actually occurred?
ImpactWhat consequence can that change have for people, systems, or the business?
  • Property
    Autonomy
    Question it answers
    Which actions can the application choose without a fresh external decision?
  • Property
    Capability
    Question it answers
    Which operations can it request through its available Tools?
  • Property
    Platform access authorization
    Question it answers
    Which Platform resources does the caller have permission to use?
  • Property
    External-action authority
    Question it answers
    Which action and arguments does the customer system permit?
  • Property
    Effect
    Question it answers
    Which state change actually occurred?
  • Property
    Impact
    Question it answers
    What consequence can that change have for people, systems, or the business?

An Action is an attempted operation. An Effect is a state change that actually occurs; an External Effect occurs outside the Platform. A read-only Task can choose many actions, while one Tool Call can send a message or delete information. Make the required authorization or approval part of the Tool or external system before it acts.

In ask(action=...), the word “action” supplies an instruction and contextual material. It does not report an operation that has occurred. The effect field on a Library Grant means allow or deny; it is an access decision.

Continue with the owner of the next question:

Follow one Task from request to outcomeUse the current execution modelRead a Tool Call outcomeSeparate capability, authority, and Effect
Last updatedOctober 21, 2026