Done-for-you offer · Fractional CMO with AI Swarm · orphan page detection
Done-for-you orphan page detection for multi-location franchise, multi-location retail, DTC, multi-channel retail, and PE-sponsored portfolio operators — a 5-skill Graph-Crawl + Inbound-Link- Counting + Orphan-Classification + Remediation-Recommendation + Attestation bundle on the link-graph agent.
The descriptive industry pattern at 50-1,500 locations running thousands-to-millions of URLs across multi-tenant CMS + locale + product catalog + content marketing footprint: orphan pages accumulate across 7 status types (true orphans, sitemap-orphans, partial orphans, semantic orphans, deep orphans, recently- orphaned, chronic orphans); monthly Sitebulb/Botify/Lumar/ Screaming-Frog crawls surface reports that get triaged manually; remediation routes to whoever is least busy; mean-time-to- remediation stretches into months; SEO equity dilutes across the orphan surface between crawl cycles. Sitebulb, Botify, Lumar, Screaming Frog, OnCrawl, JetOctopus, Conductor, BrightEdge, Yext, Searchmetrics, Ahrefs, Semrush, Majestic, and Moz ship excellent crawl + link-intelligence primitives. The streaming 5-skill Graph-Crawl + Inbound-Link-Counting + Orphan-Classification + Remediation-Recommendation + Attestation pipeline that classifies across the full 7-type taxonomy, routes remediation across 7 handler types, and emits WORM-storage attestation is operator- side architecture. Completions builds and operates the 5-skill bundle on the link-graph agent. Operator owns every artifact and can in-house at any time.
Published September 24, 2026
Frequently asked
What does the done-for-you orphan page detection engagement deliver?
Completions builds and operates a 5-skill bundle on the link-graph agent: Graph-Crawl, Inbound-Link-Counting, Orphan-Classification, Remediation-Recommendation, Attestation. Skill 1 (graph crawl) crawls across 8 link sources per page: sitemap-XML, HTML-anchor-text, JS-rendered link, JSON-LD link, OG link, per-locale hreflang, per-template link, per-region link. Skill 2 (inbound-link counting) counts inbound links by 8 classes per page: from header nav, footer nav, body content, related block, pagination, breadcrumb, sitemap only, external only. Skill 3 (orphan classification) classifies orphan status across 7 types: true orphan, sitemap orphan, partial orphan, semantic orphan, deep orphan, recently orphaned, chronic orphan. Skill 4 (remediation recommendation) recommends across 7 handler types with per-handler SLA, context, and priority: add-to-nav, add-to-related, add-to-sitemap, merge-with-canonical, redirect, delete, content-revival. Skill 5 (attestation) emits an attestation record with attestor identity, timestamp, WORM-storage commit, chain-of-custody, and per-vertical compliance overlay reference. The per-vertical compliance overlay covers SEO policy + accessibility policy (ADA + WCAG) + per-platform TOS + CCPA + GDPR. Operator owns every artifact: 5 registries in operator data infrastructure; 5-skill model code aligned with operator SEO-engineering team; per-vertical compliance overlay rule library; link-graph database; LLM prompts; audit trail. Completions owns the swarm-orchestration knowledge.
Why is streaming orphan detection + remediation routing typically operator-side rather than crawl-vendor-shipped?
The SEO crawl + link-intelligence vendors (Sitebulb, Botify, Lumar, Screaming Frog, OnCrawl, JetOctopus, Conductor, BrightEdge, Yext, Searchmetrics, Ahrefs, Semrush, Majestic, Moz) ship excellent crawl + link-graph primitives — periodic site crawls, sitemap parsing, internal-link extraction, basic orphan reports. They do not ship the streaming 5-skill pipeline that classifies orphan-status across the full 7-type taxonomy and routes remediation through operator-specific workflows because the orphan taxonomy reflects operator-specific CMS template architecture; the remediation handlers route into operator-owned content + engineering + SEO + product workflows; the per-vertical compliance overlay (especially ADA + WCAG accessibility policy) tracks operator legal team approved frameworks; the link-graph database integrates with operator data infrastructure. The work that remains operator-side spans five engineering surfaces: crawl-engineering across 8 link sources at scale; graph-engineering for 8-inbound-link-class counting; classification-engineering for 7-orphan-type taxonomy; routing-engineering for 7-handler remediation with SLA + priority + context; audit-engineering for WORM-storage attestation + 6-jurisdiction compliance overlay. Completions absorbs all five surfaces under one Tier 3 Fractional CMO with AI Swarm engagement and hands the artifacts back at engagement end.
What does the engagement look like across Tier 1 to Tier 2 to Tier 3?
Tier 1 AI Readiness Assessment (2-3 weeks, diagnostic): audits five axes. Tier 2 AI Swarm Setup Sprint (4-8 weeks): builds 5-skill bundle on link-graph agent — completing the 15th 5-skill bundle + Detect-Orphan canonical signature architecture. Tier 3 Fractional CMO with AI Swarm (6-month minimum, 1-2 days/wk embedded): continues operating end-to-end + cross-agent swarm coordination.
Who owns the registries?
Operator owns 100% of every artifact: 5 registries (in operator data infrastructure), 5-skill bundle model code (operator-owned + operator-SEO-engineering-team-aligned), per-vertical compliance overlay (rule library in operator repo with attorney-approved updates), link-graph database, LLM prompts, audit trail. Completions owns the orchestration knowledge.
What measurement and reporting does Completions commit to on Tier 3?
Measured against the operator pre-engagement baseline across six workstreams, reported weekly. (1) Graph-crawl coverage trajectory — share of URLs under active crawl across the 8 link sources; per-source crawl health. (2) Inbound-link counting quality — per-link-class counting accuracy against an operator-labeled validation set across the 8 classes. (3) Orphan-classification quality — per-type precision + recall + confidence distribution across the 7 orphan-status types against an operator-labeled holdout; reported against pre-engagement labeling baseline rather than at a 95-percent promised precision target because precision depends on the labeled-validation regime + orphan taxonomy operator approves. (4) Remediation-routing distribution — share of recommendations across the 7 handler types; per-handler SLA-adherence; per-handler queue depth. (5) Mean-time-to-remediation trajectory — time from orphan detection to handler-completed remediation, segmented by orphan type (true orphan + sitemap orphan + partial orphan + semantic orphan + deep orphan + recently orphaned + chronic orphan); reported against the operator pre-engagement remediation cadence rather than at a sub-7-day or sub-30-day promised target because remediation time depends on operator engineering + content + SEO team capacity and the handler-type the recommendation routes to. (6) Attestation completeness — per-recommendation WORM-storage commit rate; attestor-identity + chain-of-custody completeness; per-jurisdiction compliance-overlay rule-evaluation completeness. Process commitments are firm: weekly per-source crawl health check; weekly orphan-taxonomy calibration queue; weekly per-handler routing rule sync; weekly per-vertical compliance overlay update; weekly audit-trail emission. Outcome targets are not promised because mean-time-to-remediation + orphan-reduction depend on operator engineering + content + SEO team capacity and CMS-side remediation pipelines Completions does not control.
How does engagement end and what is the operator transition path?
Tier 3 engagements are 6-month minimum with 90-day notice. At engagement end, Completions transitions back to operator in-house in 30-60 days: operating-playbook hand-off + in-house staff training + 5 registries hand-off + 5-skill bundle model code hand-off + per-vertical compliance overlay rule library hand-off + link-graph database hand-off + LLM prompts hand-off + audit trail hand-off; Completions credentials revoke immediately.
Engage Completions
Start with the AI Readiness Assessment (Tier 1, 2-3 weeks). Hand off to Tier 2 (4-8 weeks). Continue under Tier 3 Fractional CMO with AI Swarm (6-month minimum, 1-2 days/wk embedded).
Or take the 3-question shape diagnostic first — no email required.