Brantial
Get Audit

PLATFORM / FANOUT QUERIES

The Question the User Asks Is Not the Query the Model Runs

A user asks one question; the model runs 8–12 sub-queries behind it and assembles the answer from their results. Fanout Queries captures that invisible tree: which sub-questions you have a source for, where a rival is the only answer, and which are entirely empty — all on one map.

PRODUCT VIEWFrom the live product interface
The Invisible Sub-queriesBehind "which collagen is best"
Collagen types compared
When to take it?
User reviews
Price comparison
Coverage ScoreAn 11-branch sample tree
6/11COVERED
CoveredPartialEmpty
From Tree to TaskRe-derived weekly
Fanout captured: 11 branchesOK
Intent groups splitOK
Coverage matchedRUN
2 gaps → Workflow Agent
Coverage and CitationsAs branches close, 8 weeks
CoverageCitations

What Are Fanout Queries?

A user asks one question; the model runs 8–12 sub-queries behind it and assembles the answer from their results. Fanout Queries captures that invisible tree: which sub-questions you have a source for, where a rival is the only answer, and which are entirely empty — all on one map.

A shortened example from a real customer cluster; the full tree has 11 branches.

Behind "which Collagen Is Best?"
  • Difference between collagen types: Informational — Covered — Maintain and refresh
  • When to take collagen: Usage — Empty — New page → Workflow Agent
  • [Brand] collagen reviews: Trust — Partial — Add FAQ block and schema
  • Collagen price comparison: Commercial — Empty — rival is sole answer — Comparison page, priority 1
  • Who should avoid collagen: Safety — Covered — Citation tracked
Eighty Percent of the Answer Comes from Questions You Never Asked
  • True Query Visibility: Classic keyword research sees the user's question; fanout sees what the model actually searches.
  • Sub-branch Risk: A sub-branch where a rival is the sole answer can push you out of the main answer entirely.
  • The Connected Tree: Covering informational branches lifts citation odds on trust branches too — the tree is connected.
  • Impact-ranked Calendar: The content calendar is built from the impact ranking of empty branches, not guesswork.
From Tree to Action
  • Prompt Volumes: Validates which branch carries real demand with volume data.
  • Workflow Agent: Empty branches become rewrite tasks in one click.
  • Site Auditor: Verifies the new page is readable by models.

From Invisible Query to Covered Answer

The fanout tree is re-derived weekly for every prompt cluster; as model behaviour shifts, so does the map.

Capture

For every tracked prompt, the searches the model runs behind the scenes and the sources it pulls are recorded.

Tree

Sub-queries are grouped by intent — informational, comparison, trust, commercial — and every branch carries its own volume estimate.

Coverage

Each sub-question is matched against your site: a page that answers it directly, one that touches it, or nothing.

Feed

Empty branches are ranked by impact and sent to Workflow Agent as rewrite or new-page tasks in one click.