Multi-agent review

Run specialists concurrently, critique their findings, and synthesize one result.

prepare shared context→research agentcode agentdomain agent→critic review→synthesize answer→publish evidence

Multi-agent review

Activity responsibilities

Activity	Responsibility
prepare-shared-context	Execute the prepare shared context stage and publish its declared outputs for downstream activities.
research-agent	Execute the research agent stage and publish its declared outputs for downstream activities.
code-agent	Execute the code agent stage and publish its declared outputs for downstream activities.
domain-agent	Execute the domain agent stage and publish its declared outputs for downstream activities.
critic-review	Execute the critic review stage and publish its declared outputs for downstream activities.
synthesize-answer	Execute the synthesize answer stage and publish its declared outputs for downstream activities.
publish-evidence	Execute the publish evidence stage and publish its declared outputs for downstream activities.

Inputs

• Shared brief
• Role definitions
• Source policy

Outputs

• Specialist findings
• Critique
• Final result

Provenance to preserve

• Context version
• Per-role traces
• Accepted claims

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

Synthesis waits for terminal specialist states or an explicit partial-result policy. Models and resources may differ by role.

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