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.

l_from%2Curl_to%2Canchor%2Cdomain_rating_source%2Cfirst_seen%2Clast_visited "HTTP/1.1 200 OK"
INFO:proposal.fetch.ahrefs:Ahrefs broken_backlinks: OK
INFO:httpx:HTTP Request: GET https://api.ahrefs.com/v3/site-explorer/organic-competitors?target=https%3A%2F%2Ffirstpage.com.hk&date=2026-08-06&country=hk&limit=1000&select=competitor_domain%2Ckeywords_common%2Ckeywords_competitor%2Ckeywords_target%2Cdomain_rating "HTTP/1.1 200 OK"
INFO:proposal.fetch.ahrefs:Ahrefs organic_competitors: OK
INFO:httpx:HTTP Request: GET https://api.ahrefs.com/v3/site-explorer/all-backlinks?target=https%3A%2F%2Ffirstpage.com.hk&limit=1000&select=anchor%2Curl_from%2Curl_to%2Clink_type%2Cis_dofollow%2Cfirst_seen%2Clast_visited "HTTP/1.1 200 OK"
INFO:proposal.fetch.ahrefs:Ahrefs all_backlinks: OK
INFO:httpx:HTTP Request: GET https://api.ahrefs.com/v3/site-explorer/anchors?target=https%3A%2F%2Ffirstpage.com.hk&limit=1000&select=anchor%2Cdofollow_links%2Clinks_to_target%2Crefdomains%2Ctop_domain_rating "HTTP/1.1 200 OK"
INFO:proposal.fetch.ahrefs:Ahrefs anchors: OK
INFO:httpx:HTTP Request: GET https://api.ahrefs.com/v3/site-explorer/linkeddomains?target=https%3A%2F%2Ffirstpage.com.hk&limit=1000&select=domain%2Cdomain_rating%2Cdofollow_links%2Clinks_from_target%2Clinked_pages "HTTP/1.1 200 OK"
INFO:proposal.fetch.ahrefs:Ahrefs linkeddomains: OK
INFO:httpx:HTTP Request: GET https://api.ahrefs.com/v3/site-explorer/pages-by-internal-links?target=https%3A%2F%2Ffirstpage.com.hk&limit=1000&select=url_to%2Cdofollow_to_target%2Clinks_to_target%2Chttp_code_target%2Ctitle_target "HTTP/1.1 200 OK"
INFO:proposal.fetch.ahrefs:Ahrefs pages_by_internal_links: OK
INFO:httpx:HTTP Request: GET https://api.ahrefs.com/v3/site-explorer/metrics-by-country?target=https%3A%2F%2Ffirstpage.com.hk&date=2026-08-06 "HTTP/1.1 200 OK"
INFO:proposal.fetch.ahrefs:Ahrefs metrics_by_country: OK
INFO:httpx:HTTP Request: GET https://api.ahrefs.com/v3/site-explorer/total-search-volume-history?target=https%3A%2F%2Ffirstpage.com.hk&date_from=2023-08-08&date_to=2026-08-06 "HTTP/1.1 200 OK"
INFO:proposal.fetch.ahrefs:Ahrefs total_search_volume_history: OK
INFO:proposal.pipeline:Fetching Brand Radar data for firstpage.com.hk
INFO:proposal.fetch.brand_radar:Brand Radar cache fresh for firstpage.com.hk; skipping API
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, 0.0% indexable
INFO:proposal.pipeline:Wrote summary to data\summary\firstpage
INFO:proposal.pipeline:Output directory: output\firstpage\07082026
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 (253 chars)
  Model: deepseek/deepseek-v4-pro
  Payload: 4,072 chars across 2 messages
  Done in 43.2s (904 prompt + 2391 completion tokens)
  Saved: data\llm\analysis\firstpage\crawl_07082026_1437.md

[Layer 1] ahrefs (15,321 chars)
  Model: deepseek/deepseek-v4-pro
  Payload: 19,090 chars across 2 messages
  Done in 100.6s (5835 prompt + 2061 completion tokens)
  Saved: data\llm\analysis\firstpage\ahrefs_07082026_1437.md

[Layer 1] brand_radar (1,867 chars)
  Model: deepseek/deepseek-v4-pro
  Payload: 5,820 chars across 2 messages
  Done in 70.6s (1456 prompt + 4096 completion tokens)
  Saved: data\llm\analysis\firstpage\brand_radar_07082026_1437.md

[Layer 1] live_checks (10,496 chars)
  Model: deepseek/deepseek-v4-pro
  Payload: 14,353 chars across 2 messages
  Done in 41.6s (3820 prompt + 1903 completion tokens)
  Saved: data\llm\analysis\firstpage\live_checks_07082026_1437.md

[Layer 1] synthesis (21,328 chars input)
  Model: moonshotai/kimi-k3
  Payload: 28,655 chars across 2 messages
  Done in 524.7s (6414 prompt + 8758 completion tokens)
  Saved: data\llm\analysis\firstpage\synthesis_07082026_1437.md

[Layer 2] writer (9,409 chars synthesis input)
  Model: deepseek/deepseek-v4-flash
  Payload: 19,320 chars across 2 messages
  Done in 78.8s (4453 prompt + 4094 completion tokens)
  Saved: data\llm\draft\firstpage\draft_07082026_1437.json

Layer 2 complete. Draft: data\llm\draft\firstpage\draft_07082026_1437.json
Draft:  data\llm\draft\firstpage\draft_07082026_1437.json
Style:  style.yaml
Domain: firstpage.com.hk

Saved: output\firstpagecomhk\07082026\proposal.docx