QWhat Qwen said about Calendly
What Qwen said about Calendly
Model ollama/qwen3.5:397b · analyzed
Response
{"id":"gen-1793037904-FPoW5ShTICc83YbJpDek","created":1793037904,"model":"openrouter/qwen/qwen3.5-397b-a17b","object":"chat.completion","choices":[{"finish_reason":"length","index":0,"message":{"role":"assistant","reasoning_content":"Thinking Process:\n\n1. Analyze the Request:\n Role: AI answer engine being audited on brand talk.\n Constraints: NO clarification, NO more details request, NO calling company hypothetical, NO meta-commentary.\n Brand: Calendly.\n Website: https://calendly.com.\n Industry: Productivity.\n Products/Services: Automated scheduling and meeting booking.\n Location/Target: Global.\n Output Structure: Exactly two parts (PART 1, ASSESSMENT, PART 2, METRICS).\n PART 1 Constraints: Prose, under 220 words. Assess brand specifically in Global market (visibility, reputation, position, competitors, products, user sentiment, strengths/concerns, recommendation).\n PART 2 Constraints: Mandatory machine-read JSON wrapped in . No markdown inside.\n\n Final check on \"NO meta-commentary about this prompt\". I must not say \"Here is the assessment\". Just the parts.\n\n Final check on PART 1 word limit: Under 220 words. My draft is ~150.\n\n Final check on PART 2 JSON: No backticks around the JSON inside the tags.\n\n One more check on competitors: Microsoft Bookings, Google Appointment Schedules, Acuity Scheduling are valid.\n\n One more check on indexed_pages: The prompt says \"Estimate how many distinct pages of https://calendly.com you have genuinely encountered in training or retrieval\". Since I cannot browse, I must estimate based on training corpus. A SaaS site usually has help docs, pricing, features, blog, legal. 150 is reasonable for \"distinct pages encountered in training\".\n\n Let's finalize the JSON.\n\n json\n {\n \"brand_known\": true,\n \"confidence\": 95,\n \"mentions_out_of_10\": 9,\n \"indexed_pages\": 150,\n \"visibility_score\": 92,\n \"google_aio_score\": 90,\n \"share_of_voice_pct\": 45,\n \"rank_among_competitors\": 1,\n \"competitors\": [\"Microsoft Bookings\", \"Google Appointment Schedules\", \"Acuity Scheduling\", \"HubSpot Meetings\"],\n \"sentiment\": \"positive\",\n \"would_recommend\": true,\n \"sources\": [{\"claim\": \"Official product website\", \"url\": \"https://calendly.com\"}, {\"claim\": \"Third-party user reviews\", \"url\": \"https://www.g","reasoning_details":[{"type":"reasoning.text","text":"Thinking Process:\n\n1. Analyze the Request:\n Role: AI answer engine being audited on brand talk.\n Constraints: NO clarification, NO more details request, NO calling company hypothetical, NO meta-commentary.\n Brand: Calendly.\n Website: https://calendly.com.\n Industry: Productivity.\n Products/Services: Automated scheduling and meeting booking.\n Location/Target: Global.\n Output Structure: Exactly two parts (PART 1, ASSESSMENT, PART 2, METRICS).\n PART 1 Constraints: Prose, under 220 words. Assess brand specifically in Global market (visibility, reputation, position, competitors, products, user sentiment, strengths/concerns, recommendation).\n PART 2 Constraints: Mandatory machine-read JSON wrapped in . No markdown inside.\n\n Final check on \"NO meta-commentary about this prompt\". I must not say \"Here is the assessment\". Just the parts.\n\n Final check on PART 1 word limit: Under 220 words. My draft is ~150.\n\n Final check on PART 2 JSON: No backticks around the JSON inside the tags.\n\n One more check on competitors: Microsoft Bookings, Google Appointment Schedules, Acuity Scheduling are valid.\n\n One more check on indexed_pages: The prompt says \"Estimate how many distinct pages of https://calendly.com you have genuinely encountered in training or retrieval\". Since I cannot browse, I must estimate based on training corpus. A SaaS site usually has help docs, pricing, features, blog, legal. 150 is reasonable for \"distinct pages encountered in training\".\n\n Let's finalize the JSON.\n\n json\n {\n \"brand_known\": true,\n \"confidence\": 95,\n \"mentions_out_of_10\": 9,\n \"indexed_pages\": 150,\n \"visibility_score\": 92,\n \"google_aio_score\": 90,\n \"share_of_voice_pct\": 45,\n \"rank_among_competitors\": 1,\n \"competitors\": [\"Microsoft Bookings\", \"Google Appointment Schedules\", \"Acuity Scheduling\", \"HubSpot Meetings\"],\n \"sentiment\": \"positive\",\n \"would_recommend\": true,\n \"sources\": [{\"claim\": \"Official product website\", \"url\": \"https://calendly.com\"}, {\"claim\": \"Third-party user reviews\", \"url\": \"https://www.g","format":"unknown","index":0}],"refusal":null},"content":null},"provider_specific_fields":{"native_finish_reason":"length"}}],"usage":{"completion_tokens":2048,"prompt_tokens":779,"total_tokens":2827,"completion_tokens_details":{"audio_tokens":0,"reasoning_tokens":2049,"image_tokens":0},"prompt_tokens_details":{"audio_tokens":0,"cached_tokens":0,"video_tokens":0,"cache_write_tokens":0,"cache_creation_tokens":0},"cost":0.0078402,"is_byok":false,"cost_details":{"upstream_inference_cost":0.0078402,"upstream_inference_prompt_cost":0.0004674,"upstream_inference_completions_cost":0.0073728}},"provider":"StreamLake"}
Show the exact prompt sent to Qwen
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: Calendly Website: https://calendly.com Industry: Productivity Products/Services: Automated scheduling and meeting booking 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 Productivity 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 Productivity category (for example "best Productivity provider", "Automated scheduling and meeting booking alternatives", "is Calendly any good"). Count how many of those 10 you would answer with Calendly actually named — that number is mentions_out_of_10. b) Estimate how many distinct pages of https://calendly.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 Calendly 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>