SEATTLE - s4story -- Prompt Research, a new ThriveStack citedby feature launched today, builds AI search prompt panels from 12 brand signals so marketers can measure how often AI engines name their brand.

AI engines like ChatGPT, Google Gemini and Claude publish no query data, so brands guess which questions to track, and the same question can return a different brand list on every run. Prompt Research replaces the guesswork with a prompt panel: a fixed set of real buyer questions run on a schedule, tracking share of voice and other CMO metrics brands need to win AI SEO.

"An AI visibility score is only as good as the prompts that track it," said Gururaj Pandurangi, Founder and CEO of ThriveStack. "If you track vanity prompts, your dashboard says you are winning while buyers never see you. ThriveStack citedby's Prompt Research picks the questions from your brand, and 11 other buyer signals, making it the best in the industry."

More on S For Story

• AthleteMerch.com Surpasses 100,000 Custom Items Delivered to Fans Nationwide
• Steve Weclew is Appointed by STS Capital Partners as Managing Director
• New Finnish Affiliate Site Ilmaiskierrokset.com Puts Wager-Free Spins in the Spotlight
• "From Rural Haiti to AI" Now Available on Amazon in English and French, With New Book Trailers
• Major FDA Victory; Preservative-Free Ketamine Approved Ahead of November 10 Goal Date as Commercial Launch Opportunity Comes Into Focus for NRx Pharma

Prompt Research takes a brand kit, topics, personas, competitors, markets, languages and buyer intent, then returns a panel users can edit before anything runs.

• Tagged by signal. Every prompt carries its topic, persona, intent, market, language and branded or unbranded tag.
• Weighted toward revenue. The default mix is 20% informational, 40% commercial and 40% transactional, with 80% to 90% unbranded.
• Sized by formula. A startup panel runs about 45 prompts, a growing brand about 360 and an enterprise over 10,000.
• Run on your schedule. Each prompt runs on every AI engine at least weekly, up to daily. University of St. Gallen researchers found one run has a 0.370 standard error and seven runs bring it under 0.10, so results are reported as a range.

Mention rate, share of voice and citation rate are reported by engine, persona, intent, market and others. A team can track, for example, that it wins buyer prompts in the U.S. and does not appear in Germany. The same panel works for AI search tracking, also called AEO (answer engine optimization) or GEO (generative engine optimization).

More on S For Story

• Rebuilding Justice: An Employment-Based House Arrest Story of Redemption — available now
• A Children's Book for Valentine's Day Lovers is Coming Soon!
• Immerse Yourself in the Historic Tochigi Autumn Festival, Celebrated Every Two Years Since 1874
• New Book - Heartland Ecology: Exploring Prairies, Woods, Farms, and Waters
• New Publication - Joyce Castle: An Operatic Life by Paul R. Laird

Prompt Research is available today in all ThriveStack citedby plans. The full method, including all 12 signals, is at thrivestack.ai/citedby/features/prompt-research (https://www.thrivestack.ai/citedby/features/prompt-research).

About ThriveStack

ThriveStack citedby is an AI visibility tool for brands and agencies that measures citation gaps across 10+ AI engines, fixes them and attributes revenue to AI search. It is a product of ThriveStack Corporation, based in Seattle, Washington, and led by Founder and CEO Gururaj Pandurangi (ex-Microsoft, Oracle, Zscaler). Learn more at thrivestack.ai/citedby (https://www.thrivestack.ai/citedby).