Generate a proposal

# Strategic Preferences — Global

## Narrative focus
- Lead with the single finding that is most actionable and most impactful.
- The centrepiece should be something the client's team can verify themselves in week 1.
- Prioritise findings in this order: GEO/AI visibility = onsite (architecture, templates, indexation) > internal linking > authority/backlinks. Weight GEO and onsite equally; never rank a link-centric finding above them unless the data proves links are the bottleneck.

## Adversarial positioning
- Where the data contradicts a prior vendor's approach, name it explicitly.
- Frame as "the data shows X, not Y" — not as a personal attack.
- If the prior vendor is backlink-heavy and the data shows on-site issues are the bottleneck, make that contrast the core argument.

## Client priorities
- Default priority order: GEO/AI visibility = crawlability/indexation + on-page templates > internal linking > backlinks.
- Backlinks are a supporting point, never the headline. Only elevate backlinks if the data shows they are the primary bottleneck (rare).
- AI/GEO visibility is always worth highlighting — it's a differentiator. Brand Radar data (share of voice, AI question demand, cited pages/domains) is the strongest GEO evidence; use it concretely.

## Desired outcome
- The proposal should land on: "this is fixable, it's faster than you think, and we've already found the root cause."
- End with a clear next step that requires signature (GSC access, server logs, etc.)
- The implicit message: "the answer is on-site and technical, not off-site and link-based."

## Emphasis control
- Emphasise: template bugs, indexation gaps, crawl architecture, AI citation gaps, on-page signal failures, Brand Radar share of voice, AI question demand, cited-page/cited-domain gaps.
- Deprioritise: backlink acquisition, domain rating, referring domain counts. Mention only when directly relevant to another finding.
- Never lead with "you need more links." If links are mentioned, frame as cleanup/risk (toxic links, broken links) rather than acquisition opportunity.
- AI visibility findings always get their own emphasis — citation counts, platform gaps, bot access, share of voice, cited pages.

&select=question%2Cdata_source%2Cvolume%2Ccountry%2Clast_updated "HTTP/1.1 200 OK"
INFO:proposal.fetch.brand_radar:Brand Radar ai_responses: OK
INFO:httpx:HTTP Request: GET https://api.ahrefs.com/v3/brand-radar/cited-pages?brand=Firstpage&data_source=chatgpt%2Ccopilot%2Cgemini%2Cgoogle_ai_mode%2Cgoogle_ai_overviews%2Cgrok%2Cperplexity&country=hk&limit=1000&select=url%2Cresponses "HTTP/1.1 200 OK"
INFO:proposal.fetch.brand_radar:Brand Radar cited_pages: OK
INFO:httpx:HTTP Request: GET https://api.ahrefs.com/v3/brand-radar/cited-domains?brand=Firstpage&data_source=chatgpt%2Ccopilot%2Cgemini%2Cgoogle_ai_mode%2Cgoogle_ai_overviews%2Cgrok%2Cperplexity&country=hk&limit=1000&select=domain%2Cpages%2Cresponses "HTTP/1.1 200 OK"
INFO:proposal.fetch.brand_radar:Brand Radar cited_domains: OK
INFO:httpx:HTTP Request: GET https://api.ahrefs.com/v3/brand-radar/sov-overview?brand=Firstpage&data_source=chatgpt%2Ccopilot%2Cgemini%2Cgoogle_ai_mode%2Cgoogle_ai_overviews%2Cgrok%2Cperplexity&country=hk "HTTP/1.1 200 OK"
INFO:proposal.fetch.brand_radar:Brand Radar sov_overview: OK
INFO:httpx:HTTP Request: GET https://api.ahrefs.com/v3/brand-radar/sov-history?brand=Firstpage&data_source=chatgpt%2Ccopilot%2Cgemini%2Cgoogle_ai_mode%2Cgoogle_ai_overviews%2Cgrok%2Cperplexity&country=hk&date_from=2025-08-13&date_to=2026-08-12 "HTTP/1.1 200 OK"
INFO:proposal.fetch.brand_radar:Brand Radar sov_history: OK
INFO:httpx:HTTP Request: GET https://api.ahrefs.com/v3/brand-radar/impressions-overview?brand=Firstpage&data_source=chatgpt%2Ccopilot%2Cgemini%2Cgoogle_ai_mode%2Cgoogle_ai_overviews%2Cgrok%2Cperplexity&country=hk&select=brand%2Cno_tracked_brands%2Conly_competitors_brands%2Conly_target_brand%2Ctarget_and_competitors_brands%2Ctotal "HTTP/1.1 200 OK"
INFO:proposal.fetch.brand_radar:Brand Radar impressions_overview: OK
INFO:httpx:HTTP Request: GET https://api.ahrefs.com/v3/brand-radar/mentions-overview?brand=Firstpage&data_source=chatgpt%2Ccopilot%2Cgemini%2Cgoogle_ai_mode%2Cgoogle_ai_overviews%2Cgrok%2Cperplexity&country=hk&select=brand%2Cno_tracked_brands%2Conly_competitors_brands%2Conly_target_brand%2Ctarget_and_competitors_brands%2Ctotal "HTTP/1.1 200 OK"
INFO:proposal.fetch.brand_radar:Brand Radar mentions_overview: OK
INFO:proposal.fetch.brand_radar:Wrote Brand Radar raw data for firstpage.com.hk to data/raw/brand_radar/firstpage
INFO:proposal.pipeline:Running live bot checks for firstpage.com.hk
INFO:proposal.fetch.live_checks:Completed 21 live checks for firstpage.com.hk
INFO:proposal.pipeline:Wrote Ahrefs raw data to data/raw/ahrefs/firstpage
INFO:proposal.pipeline:Wrote live checks to data/raw/live_checks/firstpage
INFO:proposal.pipeline:Running all Ahrefs analysis tools
INFO:proposal.pipeline:Wrote Ahrefs summary to data/summary/firstpage
INFO:proposal.pipeline:Running all Brand Radar analysis tools
INFO:proposal.pipeline:Wrote Brand Radar summary to data/summary/firstpage
INFO:proposal.pipeline:Running all live checks analysis tools
INFO:proposal.pipeline:Wrote live checks summary to data/summary/firstpage
INFO:proposal.pipeline:Crawl summary: 1 URLs, 100.0% indexable
INFO:proposal.pipeline:Wrote summary to data/summary/firstpage
INFO:proposal.pipeline:Output directory: output/firstpage/13082026
Pipeline: layer=chain, source=all
Domain:   firstpage.com.hk
Models:   L1=deepseek/deepseek-v4-pro
          synthesis=moonshotai/kimi-k3
          L2=deepseek/deepseek-v4-flash
API:      https://openrouter.ai/api/v1

[Layer 1] crawl (255 chars)
  Model: deepseek/deepseek-v4-pro
  Payload: 4,074 chars across 2 messages
  Done in 15.8s (904 prompt + 1144 completion tokens)
  Saved: data/llm/analysis/firstpage/crawl_13082026_0133.md

[Layer 1] ahrefs (15,321 chars)
  Model: deepseek/deepseek-v4-pro
  Payload: 19,090 chars across 2 messages
  Done in 86.2s (5913 prompt + 4096 completion tokens)

[Layer 1] brand_radar (1,096 chars)
  Model: deepseek/deepseek-v4-pro
  Payload: 5,049 chars across 2 messages
  Done in 37.0s (1233 prompt + 1536 completion tokens)
  Saved: data/llm/analysis/firstpage/brand_radar_13082026_0133.md

[Layer 1] live_checks (10,496 chars)
  Model: deepseek/deepseek-v4-pro
  Payload: 14,353 chars across 2 messages
  Done in 43.6s (3820 prompt + 1766 completion tokens)
  Saved: data/llm/analysis/firstpage/live_checks_13082026_0133.md

[Layer 1] synthesis (9,159 chars input)
  Model: moonshotai/kimi-k3
  Payload: 16,486 chars across 2 messages
  Done in 88.7s (3560 prompt + 5762 completion tokens)
  Saved: data/llm/analysis/firstpage/synthesis_13082026_0133.md

[Layer 2] writer (6,605 chars synthesis input)
  Model: deepseek/deepseek-v4-flash
  Payload: 16,516 chars across 2 messages
  Done in 53.5s (3715 prompt + 3941 completion tokens)
  Saved: data/llm/draft/firstpage/draft_13082026_0133.json

Layer 2 complete. Draft: data/llm/draft/firstpage/draft_13082026_0133.json
Draft:  data/llm/draft/firstpage/draft_13082026_0133.json
Style:  style.yaml
Domain: firstpage.com.hk

Saved: output/firstpagecomhk/13082026/proposal.docx