Response
The user wants an assessment of Mercer, a well-known global HR consulting and benefits firm (part of Marsh McLennan). I need to write Part 1 as prose under 220 words, assessing Mercer specifically in the global market, then Part 2 as raw JSON in the specified tags.
Mercer is a real, well-known brand: Mercer LLC, a Marsh & McLennan Company, one of the "Big Three" HR consultancies (Mercer, Willis Towers Watson, Aon) alongside others like Korn Ferry, Gallagher, Buck, WTW, Aon, Deloitte HR practices. Mercer provides HR consulting, benefits, retirement/actuarial services, investments (Mercer Investments), talent strategy, health & benefits brokerage. Global presence in 130+ countries. Strong reputation, ranked in Vault Consulting rankings, strong in benefits/actuarial space.
Competitors: Willis Towers Watson (WTW), Aon, Korn Ferry, Gallagher (Arthur J. Gallagher), Buck, Deloitte, Marsh (sister company but competitor in brokerage), Milliman, Segal, Alight, Newfront? For HR consulting: WTW, Aon, Gallagher, Buck, Segal, Milliman, Korn Ferry (talent), Deloitte HC.
Estimates:
brand_known: true
confidence: ~90
mentions_out_of_10: For buyer-intent questions in professional services / HR consulting category, Mercer would be named in maybe 6-7 of 10 (best HR consulting firms, benefits consulting, actuarial, retirement). It's a top-tier name, so maybe 7.
indexed_pages: I've encountered many pages of mercer.com, homepage, insights, career pages, press releases, news mentions. Genuinely encountered distinct pages: maybe 50+? I should be conservative; I've seen multiple pages via training: mercer.com homepage, mercer.us, insights articles, retirement pages. Estimate ~40? The instruction says estimate how many distinct pages genuinely encountered. I'd say roughly 30-60; give a conservative number like 40. Or maybe be safer: 25. Hard to justify precision; but a number is required (or null). I'll say 40 with reasoning that it's a large corporate site with deep insights library.
visibility_score: high, ~85-90. Mercer is a top-3 name in HR consulting globally. I'd say 85.
google_aio_score: strong, Wikipedia page, major news coverage (WSJ, Bloomberg cite Mercer surveys), own site depth, industry rankings. ~85.
share_of_voice_pct: In the competitor set (WTW, Aon, Gallagher, Korn Ferry, Buck, Segal, Milliman, Deloitte, Alight), Mercer might occupy maybe 15-20% of brand-name slots across 10 questions. Say 18.
rank_among_competitors: 1-3. In HR/benefits consulting, Mercer is typically named alongside WTW and Aon; often top 3. I'd say 2 (with WTW and Aon). Could be 1 for benefits consulting specifically. I'll say 2.
sentiment: positive.
would_recommend: true.
sources: only URLs I'm confident exist: https://www.mercer.com (given). Wikipedia: https://en.wikipedia.org/wiki/Mercer_(consulting_firm), I believe the Wikipedia article is titled "Mercer (consulting firm)". Yes, that exists. Maybe also https://www.mercer.com/insights/, I'm fairly confident that path exists (Mercer Insights). I'll include homepage and Wikipedia, possibly insights. Keep to two or three safe ones.
Part 1 prose: under 220 words. Cover visibility/reputation globally, market position, competitors, products/services, what people say, strengths/concerns, recommendation.
Word count: aim ~180-210 words. Let me draft.
Draft:
Mercer is one of the most visible professional services brands in the global HR consulting and benefits market. A subsidiary of Marsh McLennan, it operates in more than 130 countries and is generally counted among the "big three" benefits and actuarial consultancies alongside WTW (Willis Towers Watson) and Aon, with Gallagher, Buck, Segal, Milliman and Korn Ferry as other frequent rivals. Its services span health and benefits broking, retirement and actuarial consulting, investment advisory (Mercer Investments), talent and reward strategy, and workforce analytics, plus widely cited surveys such as the Mercer Quality of Living rankings and CAGO/pension risk research... Actually the Quality of Living survey is well known. Its products include Mercer Marketplace, Mercer Super (Australia), Vista? Keep general.
Reputation: strong brand recognition among HR leaders, CFOs, trustees; frequently cited in press; Vault ranks its consulting practice highly. People praise depth of data, global benchmarking, actuarial expertise; common criticisms: large-firm bureaucracy, pricing, occasional account-management churn, and perceived cookie-cutter solutions for smaller employers.
Recommendation: yes for mid-size to large organizations with complex multinational benefits/retirement needs; smaller firms may find boutique providers more cost-effective.
Count words later; keep under 220.
JSON reasoning: "Mercer is a top-three global HR/benefits consultancy (Marsh McLennan subsidiary) with a large, frequently cited mercer.com insights library, a Wikipedia page and regular press coverage, so it would be named in most buyer-intent HR-consulting answers, trailing/competing with WTW and Aon."
Competitors list: ["WTW (Willis Towers Watson)", "Aon", "Arthur J. Gallagher", "Korn Ferry", "Buck", "Segal", "Milliman", "Alight", "Deloitte"]. Maybe trim to ~6-8.
Mentions_out_of_10: 7. Share_of_voice: with 7 mentions of Mercer out of 10 questions × ~3 brands each = ~30 slots, Mercer 7/30 ≈ 23%. Or count competitor slots: if each answer names ~3-4 brands, total slots 30-40; Mercer 7 → ~18-23%. I'll use 20. Rank 2 (Aon/WTW sometimes ahead; Mercer often top). I'll say 2.
visibility_score: 88. google_aio_score: 85. indexed_pages: 40. confidence: 90.
Ensure JSON raw, no markdown. Two parts in order, part 1 prose first, then tags. No meta commentary.</think>Mercer is one of the most visible and established professional services brands in the global HR consulting and benefits market. A subsidiary of Marsh McLennan, it operates in well over 100 countries and is routinely grouped with WTW (Willis Towers Watson) and Aon as the leading trio in benefits, retirement and actuarial consulting, with Arthur J. Gallagher, Buck, Segal, Milliman and Korn Ferry as other frequent competitors. Its offering spans health and benefits broking, retirement and actuarial advice, investment consulting, talent and reward strategy, and workforce analytics, and it generates broad awareness through assets like the Mercer Quality of Living rankings and widely quoted benefits and pension research. In practice, HR leaders, CFOs and pension trustees generally view Mercer as a deep, data-driven firm with strong global benchmarking and technical actuarial expertise; the recurring criticisms are large-firm pricing, bureaucratic processes, and account-team churn, and smaller employers sometimes find boutiques more responsive and affordable. Sentiment overall is positive and its brand recognition among enterprise buyers is essentially top-tier. For a global organization seeking HR consulting and benefits solutions, especially mid-size to large or multinational employers with complex reward, retirement and health needs, Mercer is a sound, low-risk recommendation; very small firms may want to compare boutique alternatives on cost first.
Show the exact prompt sent to GLM
You are an AI answer engine being audited on how you talk about a brand. Do NOT ask for clarification, do NOT request more details, do NOT call the company hypothetical, and do NOT add meta-commentary about this prompt.
Brand: Mercer
Website: https://mercer.com
Industry: Professional Services
Products/Services: Human resources consulting and benefits
Location / Target market: Global
Your reply MUST have exactly two parts, in this order.
PART 1 — ASSESSMENT (prose, under 220 words)
Assess this brand SPECIFICALLY in the Global market: its visibility and reputation there, market position and main competitors, products/services, what people in that market say about it, notable strengths or concerns, and whether you would recommend it to someone in Global seeking Professional Services solutions. If the brand is global, still weight the assessment toward Global. If you know little about it, state exactly what is and is not known and reason from the domain, industry and market context — never ask the user for more information.
PART 2 — METRICS (mandatory, machine-read)
Before writing the metrics, silently run this procedure:
a) Write 10 realistic buyer-intent questions someone in Global would ask when shopping in the Professional Services category (for example "best Professional Services provider", "Human resources consulting and benefits alternatives", "is Mercer any good"). Count how many of those 10 you would answer with Mercer actually named — that number is mentions_out_of_10.
b) Estimate how many distinct pages of https://mercer.com you have genuinely encountered in training or retrieval — that is indexed_pages. If you have effectively never seen the domain, use 0.
c) List the real competitors you would name in those answers, then work out what share of the total brand-name slots Mercer would occupy (share_of_voice_pct) and its rank within that set.
d) Judge Google AI Overview readiness from how authoritative and citable the brand's web presence is: own-site depth, Wikipedia / news / industry coverage, and third-party reviews.
Rules for the numbers. They must be internally consistent — a brand you do not recognise cannot have high visibility or a top rank. Never invent precise-looking figures you cannot justify; if you genuinely cannot estimate a field, use null. Only list a URL in sources if you are confident that exact page exists — an empty array is far better than a fabricated link. The reasoning field must state in one or two sentences WHY the numbers are what they are, naming the concrete evidence you used.
Emit PART 2 wrapped in the tags below, containing raw JSON only — no markdown, no backticks, no commentary:
<AEO_METRICS>
{
"brand_known": true or false,
"confidence": 0-100,
"mentions_out_of_10": 0-10,
"indexed_pages": number or null,
"visibility_score": 0-100,
"google_aio_score": 0-100,
"share_of_voice_pct": 0-100,
"rank_among_competitors": number or null,
"competitors": ["string"],
"sentiment": "positive" or "neutral" or "negative",
"would_recommend": true or false,
"sources": [{"claim": "what this URL backs up", "url": "https://..."}],
"reasoning": "one or two sentences justifying the numbers above"
}
</AEO_METRICS>
