Step 1
Frame the research question
The workflow captures the question, expected output and boundaries that should shape the research task.
A clear task gives later review a defined purpose.
Product tour 02
This representative research tour retrieves approved material, asks a selected model to prepare a structured view and pauses for a subject-matter reviewer before continuing.
Interactive walkthrough
The workflow supports a reviewer. It does not claim to replace professional judgement or regulatory responsibility.
Step 1
The workflow captures the question, expected output and boundaries that should shape the research task.
A clear task gives later review a defined purpose.
Step 2
Pūnaha searches the selected knowledge collection for material relevant to the question.
The organisation chooses which sources belong in the approved collection.
Step 3
The configured model receives the task and retrieved context, then prepares the requested structure.
The output is assistance for review, not automatic authority.
Step 4
A person examines the evidence and proposed analysis, then approves or rejects the workflow continuation.
The decision becomes part of the workflow state.
Step 5
The accepted material can be merged into the final output or passed to another configured step.
Execution history preserves the path taken through the workflow.
Controls in the flow
The workflow searches the selected knowledge collection rather than treating any available content as equal.
The AI step uses the supported deployment selected for this task and environment.
The workflow cannot cross the approval step until the configured reviewer acts.
The published workflow version and execution history provide a clearer operational boundary.
Bring the evidence sources, AI assistance and reviewer decisions you want to understand.