Encapsulated agent task

Run an agent loop as one bounded activity with explicit limits and validation.

prepare objective→run agent loop→validate output→publish resultstore trace

Encapsulated agent task

Activity responsibilities

Activity	Responsibility
prepare-objective	Execute the prepare objective stage and publish its declared outputs for downstream activities.
run-agent-loop	Execute the run agent loop stage and publish its declared outputs for downstream activities.
validate-output	Execute the validate output stage and publish its declared outputs for downstream activities.
publish-result	Execute the publish result stage and publish its declared outputs for downstream activities.
store-trace	Execute the store trace stage and publish its declared outputs for downstream activities.

Inputs

• Objective and context
• Tool allowlist
• Iteration limits

Outputs

• Validated result
• Tool outputs
• Agent trace

Provenance to preserve

• Prompt and model
• Tool calls
• Cost and validation

Runnable example

This is the complete checked-in bundle for this pattern. Download the environment, scope, topology, workflow, input, container recipe, runner, and validation contract from this page before executing it.

Read setup instructions ↓Environment YAML ↓Execution scope YAML ↓Network topology YAML ↓Workflow YAML ↓Input data ↓Container recipe ↓Run the workflow ↓Validate outputs ↓Expected output manifest ↓

Verified local execution

These captures and the output manifest were produced by the fixture's local Docker run and validator. They are published with the same bundle as the runnable files.

Workflow evidence

Execution evidence

Output evidence

Open verified output manifest ↓

Execution considerations

Apply timeout, cancellation, restricted credentials, and idempotency to any external side effect.

AkôFlow boundary: the engine schedules, deploys, executes, transfers data, and records evidence. The ML or agent framework remains an implementation choice inside each activity.