Find recurring openings with Hook Miner

Analyze a connected research dataset for repeatable hook patterns instead of judging examples one by one.

Where: Flowgen → Add → Research → Hook Miner

Key ideas

• Dataset-led analysis: Hook Miner analyzes connected content rows and emits structured hook patterns plus a readable report.
• Model choice: The card and sidebar expose the analyst model; the selected model changes how the evidence is interpreted, not what was collected.
• Patterns are starting points: A recurring hook can inform a brief, but each recommendation should stay traceable to actual examples in the input data.
• Hook Miner card: HookAnalysisNode uses the generic shared-card path. Analyze connected content data for recurring hook patterns and a readable report.
• Properties sidebar: researchNodes.tsx
• Opened surfaces: Structured result preview

Steps

1. Connect a Content Harvest or compatible dataset output.
2. Choose the analyst model in the card or properties sidebar.
3. Run the node and compare each proposed hook pattern with the cited/input examples.
4. Send useful patterns to a text brief, script, QA checklist, or Brain record.

Hook Miner controls and presets

• Add path: Flowgen → Add → Research & Insights → Hook Miner.
• Card: HookAnalysisNode.
• Properties: researchNodes.tsx.
• Controls: Dataset input; analyst model; structured hooks; report.
• Opened surfaces: Structured result preview.

Tips

• Use a dataset collected for one audience and platform context.
• Keep the original rows connected so a later reviewer can inspect the evidence.

Limitations and important notes

• Frequency does not prove causation or future performance.

Troubleshooting

The hooks are too vague to use

Connect a narrower dataset with captions or transcripts and rerun with one content goal in mind.

Related guides

• Choose a Flowgen research or analysis node
• Collect posts with Content Harvest
• Check a result against the brief with QA Review