How The Answer Index is measured

1. What is measured

The index measures which firms AI engines actually name when asked the questions real clients ask. Four engines: ChatGPT, Gemini, Perplexity and Google AI Overviews. Each edition covers one market and practice area with its own question set and firm universe.

2. The question set

Each edition tracks a fixed question set (typically 300) spanning practice areas, matter types and location phrasings, drawn from real search demand data for the market. Questions are weighted equally. The set is frozen once live: any change requires a version bump noted in the changelog, since changing questions breaks month-over-month comparability. Exact prompt strings are private: publishing them would let firms optimize for the test instead of the market and would contaminate the engines being measured. Journalists and researchers may review the full set under NDA by writing to team@aeoengine.ai.

3. Collection

Every question is run against every engine during the measurement window (days 1 to 3 of the month), producing the edition’s answer corpus. Runs use clean sessions with no account personalization. Answer text is stored unmodified for audit.

4. Entity resolution

Each firm has a maintained entity record: legal name, d/b/a brands, common misspellings and domains. Mentions are matched against this table. Firms may submit corrections to their entity record at any time.

5. Scoring

Share of voice: a firm's total mentions divided by all tracked firm mentions in the corpus. Appearance rate: the share of questions naming the firm at least once. Ranking is by share of voice. Exact tie rule: ties on share of voice break on appearance rate, then on engine coverage (the number of engines naming the firm), then alphabetically by display name. DR is pulled from Ahrefs and estimated monthly organic traffic from DataForSEO at measurement time. Both are context only and never affect rank.

Domain Rating by Ahrefs.

6. Engine and model configuration

Each edition records the engine and model configuration used at measurement time. The August 2026 editions ran against ChatGPT, Gemini, Perplexity and Google AI Overviews, using clean sessions with no account personalization. The exact model versions measured are recorded in the immutable edition answer set; future editions list their configuration on this page before publication.

7. Question set versioning

The National 100 question set is frozen at v1.0 through the end of 2026. Any change is announced one edition ahead on this page, and every movement statistic that crosses a version change carries a flag so month-over-month comparisons stay honest.

8. Retired sample prompts: Personal Injury 100

Ten retired sample prompts from the inaugural Personal Injury 100 question set (retired on publication, never measured again): (1) top personal injury attorney in Jacksonville; (2) top personal injury attorney in Atlanta; (3) best personal injury lawyers in the country; (4) my baby was deprived of oxygen during labor; (5) best auto accident attorney in the US; (6) best law firm for construction accident victims; (7) best slip and fall attorney for a settlement; (8) best law firm for birth injury victims; (9) I was T boned at an intersection, what attorney should I call; (10) best motorcycle accident attorney for a settlement.

9. Retired sample prompts: Criminal Defense & DUI 100

Ten retired sample prompts from the inaugural Criminal Defense & DUI 100 question set (retired on publication, never measured again): (1) best criminal defense law firm in the US; (2) can a first DUI be dismissed; (3) can assault charges be dropped; (4) best law firm for a probation violation; (5) do I need a lawyer for a white collar crime; (6) I was charged with resisting arrest, do I need a lawyer; (7) I was charged with a federal crime, how is that different; (8) false domestic violence accusation defense; (9) best criminal defense lawyer in Phoenix; (10) top DUI attorney in Charlotte.

10. Retired sample prompts: Family Law 100

Ten retired sample prompts from the inaugural Family Law 100 question set (retired on publication, never measured again): (1) best family law firm in the US; (2) top divorce lawyers in America; (3) which family law firm should I hire; (4) best divorce law firm in the country; (5) who are the top rated family law attorneys; (6) best divorce attorney in the US; (7) top family law attorney for a contested divorce; (8) best law firm for an uncontested divorce; (9) which firm is best for a high net worth divorce; (10) best law firm for a child custody battle.

11. Eligibility

Each edition measures an eligible universe of 100 firms selected from firms actively marketing the practice area in the market, using directories, advertising presence and market research. Practice-area editions require the edition’s practice to be the firm’s primary or flagship practice. Firms may request consideration for a future edition through the firm lookup. Being a client of AEO Engine neither includes nor excludes a firm.

12. Client disclosure

Some measured firms are AEO Engine clients. Every client firm is tagged on the board. Measurement and parsing run identically for every firm, client or not.

13. Limitations

Generative engines are probabilistic: results vary by phrasing, session and time. Each edition is a snapshot of the window, not a permanent standing. Month-to-month movement below 0.5 points should be read as noise. Single market, single practice area per edition. The interval between the inaugural edition and the second is approximately five weeks; every interval after that is an exact calendar month.

14. No sponsorship

The index carries no advertising and no sponsors. Rankings are never for sale. The index is funded entirely by AEO Engine’s operating business.

15. Corrections and changelog

Errors reported to team@aeoengine.ai are investigated and resolved within 48 hours. Every correction is logged in the public correction log and summarized here with date and description.

• 2026-07-28 (National 100 · All Practice Areas): Inaugural August 2026 edition published. National 100 question set frozen at v1.
• 2026-08-07 (National 100 · All Practice Areas): Correction: Updated the concentration summary to use a one-decimal complement totaling 100.0%, and removed a stale zero-score summary that did not match the 100 published rows.
• 2026-07-31 (Personal Injury 100): Inaugural August 2026 edition published. Personal Injury 100 national universe.
• 2026-08-07 (Personal Injury 100): Correction: 27 firms tied at 0.0% are now unranked and listed alphabetically.
• 2026-07-31 (Criminal Defense & DUI 100): Inaugural August 2026 edition published. Criminal Defense & DUI 100 national universe.
• 2026-08-07 (Criminal Defense & DUI 100): Correction: 8 firms tied at 0.0% are now unranked and listed alphabetically.
• 2026-07-31 (Family Law 100): Inaugural August 2026 edition published. Family Law 100 national universe.
• 2026-08-07 (Family Law 100): Correction: 29 firms tied at 0.0% are now unranked and listed alphabetically.

16. No sponsorship

The index carries no advertising and no sponsors. Rankings are never for sale. The Answer Index is never included in any paid third-party listicle. The index is funded entirely by AEO Engine's operating business.

17. Edition data sample

Every edition publishes a public CSV data sample: rank, firm, share of voice, appearance rate, per-engine flags, DR, organic estimate and client flag. No prompts, no answer text. Download from any edition page or directly: National 100 · All Practice Areas data.csv · Personal Injury 100 data.csv · Criminal Defense & DUI 100 data.csv · Family Law 100 data.csv.