Scientific pipeline with AI interpretation

Keep deterministic science and AI-assisted interpretation independently reproducible.

prepare experiment→run simulation→extract measurements→statistical analysisAI interpretation→validate conclusions→publish report

Scientific pipeline with AI interpretation

Activity responsibilities

Activity	Responsibility
prepare-experiment	Execute the prepare experiment stage and publish its declared outputs for downstream activities.
run-simulation	Execute the run simulation stage and publish its declared outputs for downstream activities.
extract-measurements	Execute the extract measurements stage and publish its declared outputs for downstream activities.
statistical-analysis	Execute the statistical analysis stage and publish its declared outputs for downstream activities.
ai-interpretation	Execute the AI interpretation stage and publish its declared outputs for downstream activities.
validate-conclusions	Execute the validate conclusions stage and publish its declared outputs for downstream activities.
publish-report	Execute the publish report stage and publish its declared outputs for downstream activities.

Inputs

• Experiment definition
• Domain software
• Interpretation model

Outputs

• Simulation data
• Analyses
• Validated report

Provenance to preserve

• Parameters and software
• Raw data
• Prompt 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

Separate scientific computation from interpretation so reviewers can reproduce the results without the AI model.

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