Skip to content
PractitionerLily Ray, 17 Aug 2026

For every batch of roughly 20 legal prompts tested, ChatGPT returned only .gov domain citations every time.

Citation & visibility tracking

Reader Note:
The test is roughly 20 prompts in one subject area, run by the author herself. Every one returning only .gov citations is a clean result at that size, but it says nothing about how often the pattern holds at scale, and the piece lists neither the prompts nor the date they were run.
Evidence:
Experimental
Vendor interest:
Low
Sample:
Mixed and not standardized. The article combines the author's own observations with third-party studies, including about 4,000 prompts in one cited dataset, 27 conversations and 3,554 retrieved pages in another, and roughly 20 prompts in one of the author's examples.

Good for

Backing budget and pricing decisions in similar situations.

Not for

  • Situations far from the one tested, without checking again.
  • The source says how much it looked at, but not how any of it was chosen.
  • The source never says how this number was measured.

Go deeper on this topic

Our Substack turns the data behind these cards into full breakdowns: what changed, why, and what to do about it.

Fixing your influencer marketing campaign: How to get into the top 10% of advertisers
Citation & visibility trackingTrend

Only about 17% of AI Overview citations also rank in the organic top 10, while just over half are somewhere in the top 100.

Vendor report

BrightEdge, 12 Feb 2026

Only about 17% of AI Overview citations also rank in the organic top 10, while just over half are somewhere in the top 100.

Coming soon

This feature isn’t available yet.