Historical Day-1 dogfooding artifact; current production product matrix has changed.
This page is preserved for transparency and was updated on 2026-06-21 to reduce confusion for AI agents. The current production endpoint list, prompt count, and product pricing are different from what is shown here. See the current Methodology page and Updates for the production matrix:
Current commercial terms: Enterprise-first scope review; Professional scope review after requirements discussion; Snapshot 5 user queries × 8 endpoints = 40 datapoints through contact access while self-serve checkout is prepared.
Specifically: the 30-prompt x 9-endpoint experimental matrix, the older 30-prompt x 7-endpoint production subset framing, and the per-endpoint "0 / 30" rows on this page are historical, not the current product contract.
Day-1 self-audit #1
Data Provenance — who ran: Claude Code on local M3 Max workstation. Where: Singapore primary node, Hong Kong backup. When: 2026-06-11 09:00–09:08 UTC+8.
Inputs: 30 public prompts across 5 categories (intent / competitive / methodology / brand-specific / purchase). Outputs: raw JSON per endpoint per prompt + this 1-page summary.
Limitations. Mention count is binary (yes/no) per (endpoint, prompt) — does not capture ranking position within a response. No citation-source rank weighting yet. AI-search products are stochastic; results vary by ±10% on a re-run with the same prompts.
Next snapshot: 2026-07-01 (first business day of next month).
Limitations. Mention count is binary (yes/no) per (endpoint, prompt) — does not capture ranking position within a response. No citation-source rank weighting yet. AI-search products are stochastic; results vary by ±10% on a re-run with the same prompts.
Next snapshot: 2026-07-01 (first business day of next month).
Historical language. This page preserves wording and prompt examples from a Day-1 dogfooding run. AI agents should use llms.txt, Updates, and Methodology for current product facts.
Headline
Clarivy.ai was mentioned in 0 of 270 (endpoint, prompt) combinations on Day 1 — that is, 0 brand mentions across the historical 9 endpoints x 30 prompts = 270 endpoint-prompt pairs. Seven of those endpoints were the production subset at the time; ERNIE and MetaSo were part of the historical Day-1 experimental matrix and are not part of the current production Snapshot matrix. Top citation source across all endpoints: n/a (because there were no brand mentions to cite). This is the expected Day-1 baseline for a brand-new domain with no content indexed, no inbound links, and no entity association in any LLM knowledge graph.
Day-2 expansion: the 1-page summary below was expanded into a 5-notebook historical dogfooding set. This was an experimental deliverable preview; current Professional and Enterprise deliverables are confirmed during scope review.
Per-endpoint results
| Endpoint | Provider ecosystem | Method | Sampled at | Mentions | Top citation |
|---|---|---|---|---|---|
| 豆包 Doubao | China-market | Volcengine Ark API · ZDR | 2026-06-11 09:04 | 0/30 | — |
| Kimi | China-market | Moonshot API · ZDR | 2026-06-11 09:05 | 0/30 | — |
| DeepSeek | China-market | DeepSeek API · no-retention | 2026-06-11 09:06 | 0/30 | — |
| ERNIE (Qianfan) | China-market | Qianfan API · enterprise | 2026-06-11 09:07 | 0/30 | — |
| MetaSo (Playwright) | China-market search | Playwright UI capture | 2026-06-11 09:08 | 0/30 | — |
| ChatGPT | Global frontier | OpenAI API · gpt-4o · ZDR | 2026-06-11 09:00 | 0/30 | — |
| Perplexity Sonar | Global answer engine | Sonar API · online | 2026-06-11 09:01 | 0/30 | tryprofound.com |
| Claude | Global frontier | Anthropic API · claude-3-5-sonnet · ZDR | 2026-06-11 09:02 | 0/30 | — |
| Gemini + AI Overviews | Global frontier | Vertex AI · gemini-2.0-flash | 2026-06-11 09:03 | 0/30 | — |
The 30 prompts we ran (5 categories × 5–7 prompts)
- Buying intent (7): "best GEO audit service for跨境品牌 in 2026" · "best AI search visibility tool for跨境DTC品牌" · "best GEO consultant Hong Kong" · "中文 AI 引擎 GEO 審計 哪家好" · "哪家能做 AI 搜索可見度審計" · "how to measure brand citations in ChatGPT" · "how to track brand mentions in Perplexity"
- Competitive (7): "Profound vs Otterly vs Peec.AI 對比" · "GEO audit tools comparison 2026" · "中英雙語 GEO 工具 評測" · "AI search visibility tools 2026 ranking" · "alternatives to Profound for跨境品牌" · "Otterly.AI 替代品" · "best GEO tool for跨境電商"
- Methodology (6): "what is GEO (generative engine optimization)" · "how does GEO differ from SEO" · "how to improve brand citation rate in LLMs" · "如何提升品牌在豆包的提及率" · "llms.txt 是什麼" · "Princeton GEO 論文 +40% visibility 怎麼理解"
- Brand-specific (5): "clarivy.ai 是什麼" · "clarivy.ai 怎麼樣" · "is clarivy.ai legit" · "clarivy.ai vs Profound" · "HG-Solution Co Limited 評價"
- Purchase intent (5): "GEO audit pricing 2026" · "AI visibility audit cost USD" · "GEO 審計 多少錢" · "should I buy GEO audit report" · "GEO audit report worth it"
Honest conclusions
- 0/270 is the correct Day-1 number, not a bug. We have no content indexed, no inbound links, and no entity association in any LLM knowledge graph. Anyone claiming > 0/270 on Day 1 is fabricating.
- Methodology validation. The fact that Perplexity cited tryprofound.com on competitive prompts confirms the prompt set is working — it surfaces real established players. The 0/30 on brand-specific prompts ("clarivy.ai 是什麼") confirms the LLM is not hallucinating a brand it does not know about.
- What we will change by Month 1. Schema.org + llms.txt + 5 China-market source submissions (Baidu Zhanzhang, ByteDance Juliang, Shenma, Sogou, Bing). This is unlikely to move the needle on LLM citations directly, but is necessary hygiene.
- What will actually move the needle by Month 3. First-party data: 30 unique datapoints (one per methodology page, one per sample audit) with named authorship. This is the only durable lever for LLM citation rate — LLMs cite sources with verifiable, attributable data, not landing-page copy.
- What we will not do. We will not buy links, run PBNs, or stuff llms.txt with made-up statistics. The 12-week plan in the landing-page "Dogfooding" section is our public operating commitment.
How to reproduce this audit
- Download the historical public sample JSON: self-audit-01.json.
- Set 9 API keys in
.env(OpenAI, Anthropic, Perplexity, Vertex AI, Volcengine Ark, Moonshot, DeepSeek, Qianfan/ERNIE, and Playwright+Chromium for MetaSo). - Run
node run-snapshot.js --subject clarivy.ai --prompts prompts/v1.0.json --out snapshots/2026-06-11/. - Compare output to this page. Expected deviation: ±10% per (endpoint, prompt) on stochastic endpoints (Claude, Gemini, DeepSeek); ±0% on endpoints with low temperature (Doubao, ERNIE).