Research Session Orchestrator

Run a full multi-source research session: classify the domain, dispatch parallel agents, synthesize findings, and output a formatted report.

Workflow

Step 1: Classify Domain

Run the domain classifier on the topic:

from tome.scripts.domain_classifier import classify
result = classify(topic)
# result.domain, result.triz_depth, result.channel_weights

If confidence < 0.6, ask the user to confirm or override the domain classification before proceeding.