Reach swarm · Per-location-landing-page agent · Build pillar · Published June 18, 2026
How to build per-location landing pages at scale for multi-location retail operators
A multi-location retail or franchise operator running 50-500 stores wants per-location landing pages that drive organic traffic without triggering Google March 2024 scaled-content -abuse policy + Helpful Content System demotion + Quality Rater Guidelines Section 7.4 doorway-page classification + ADA Title III accessibility serial-plaintiff exposure + Lanham Act naked-licensing posture failure. This guide walks the 4-skill bundle (Compose + Distinct + Gate + Audit) on the per-location-landing-page agent end-to-end.
The 4-skill bundle on the per-location-landing-page agent
Compose
Generate per-location page content blocks via multi -LLM ensemble (OpenAI + Anthropic + Google + Mistral + Cohere) grounded in per-location master record (hours + services + NAP + team + testimonials + neighborhood context + landmarks + local events + photos + FAQ + CTA). Brand voice spec via sibling #532 runtime brand -voice gate. Claims allowlist via sibling #496. Forbidden phrase library via sibling #507. Per-vertical compliance overlay via sibling #516. Per-LLM citation grounding to master-record source rows so per-block content is traceable. Per-vendor LLM zero-retention verified per call.
Distinct
Inter-page distinctness gate before publish. MinHash + Locality-Sensitive Hashing across all per-location pages in the portfolio for sublinear near-duplicate detection. Embedding-cosine similarity via sentence -transformer + Cohere embed-v3 + OpenAI text-embedding -3 + Voyage-3 ensemble for paraphrase-level similarity. Stylometric fingerprint distance for identical-template-with-token-substitution patterns. Pages with inter-page similarity above operator-counsel -defined threshold route back to Compose with explicit instruction to expand neighborhood + landmark + local event + per-location-team detail. Iterative: page that fails twice routes to operator-counsel review with similarity-vector evidence.
Gate
Google Quality Rater Guidelines Section 7.4 doorway -page check + Section 7.4.1 thin-content check + Section 3.2 lowest-quality check. Helpful Content System E-E-A-T signals (Experience + Expertise + Authoritativeness + Trustworthiness). ADA Title III + WCAG 2.2 AA accessibility check (alt-text + heading structure + color contrast + reading level + form labels + keyboard navigation + ARIA where applicable). Per-state accessibility (California Unruh + Colorado SB21-176 + NYC Local Law 12). FTC substantiation via sibling #496. Per-state UDAP + per-state pricing-and -discount disclosure when offer included. Lanham Act naked-licensing posture check. FTC Franchise Rule Item 12 territorial cross-check. AI-drafted content routes through sibling #520 borderline routing.
Audit
Per-page canonical record (page ID + per-location pointer + Compose ensemble snapshot + per-block citation trace to master record + Distinct similarity-vector snapshot at publish + Gate decision + per-rule citation + Section 7.4 doorway-page evaluation + ADA + WCAG accessibility audit + Lanham Act naked-licensing posture + FTC Franchise Rule Item 12 cross-check + EU AI Act Article 50 disclosure + per-vendor LLM zero-retention verification + sibling-handoff pointer to #496 + #507 + #516 + #520 + #532). WORM storage. Per-page record retains for Google policy review + Lanham Act naked -licensing defense + FTC substantiation defense + ADA serial-plaintiff defense + state-AG enforcement + EU AI Act Article 22 supervisory authority + audit committee + external counsel review.
The real ecosystem this sits above
Local-landing-page + CMS
Yext, SOCi, Rio SEO, Sterling Mesh, Surefire Local (CallSource), Reputation.com, BirdEye, Chatmeter, LocaliQ (Gannett), Hibu, Vendasta, Vivial, Brandify, Mosaic, Movable Ink, Optimizely (Episerver) local -landing-page platforms. Next.js, Astro, Remix, Nuxt, SvelteKit static-site frameworks. Headless CMS via Sanity, Contentful, Strapi, Storyblok, DatoCMS, Hygraph.
LLM + embedding + distinctness
OpenAI, Anthropic, Google, Mistral, Cohere LLM under per-vendor zero-retention. sentence-transformers, Cohere embed-v3, OpenAI text-embedding-3, Voyage-3, Google Vertex AI textembedding-gecko embedding ensemble. datasketch MinHash + Locality-Sensitive Hashing library. Stylometric fingerprint via per -portfolio function-word distribution + per-author pattern analysis.
Policy + accessibility + WORM
OPA Rego, AWS Cedar, Casbin, Cerbos, Oso, Styra DAS, Permit.io policy-as-code for Gate decision. axe-core, Pa11y, WAVE, Lighthouse, Deque ARC, Tenon, UserWay, accessiBe, AudioEye accessibility scanning. Sibling #496 + #507 + #516 + #520 + #532. AWS S3 Object Lock + Azure Blob immutable + Google Cloud Storage Bucket Lock + Wasabi compliance WORM for Audit.
The 5-anchor compliance overlay
Anchor 1 — Google Helpful Content System + March 2024 Core Update + scaled-content-abuse + Quality Rater Guidelines Section 7.4 (operationally distinctive)
Per-location pages are the canonical doorway-page risk pattern. Google Helpful Content System launched September 2022 + demoted sites producing content primarily for search engines rather than people. March 2024 Core Update folded Helpful Content System into the core algorithm + made demotion sharper. March 2024 scaled-content-abuse policy explicitly targets sites that generate scaled content for the purpose of manipulating search rankings (replacing prior auto -generated-content language). March 2024 site -reputation-abuse policy + expired-domain-abuse policy round out the March 2024 enforcement package. Google FAQ rich-result restriction (August 2023; FAQ rich results restricted to government and health authority sites) + HowTo rich-result deprecation (September 2023). Google Quality Rater Guidelines Section 7.4 doorway-page detection + Section 7.4.1 thin-content + Section 3.2 lowest-quality. Operationally distinctive — Distinct enforces MinHash + LSH + embedding-cosine + stylometric inter-page similarity BELOW operator -counsel-defined threshold; audit trail documents distinctness signal at every publish.
Anchor 2 — FTC Section 5 + substantiation + Endorsement Guides + Fake Review Rule + per-state UDAP + pricing disclosure
FTC Section 5 + FTC substantiation doctrine (Pfizer 1972 reasonable-basis) when per-location page makes claims + FTC Endorsement Guides 16 CFR Part 255 (2023 AI-content update) + FTC Fake Review Rule 16 CFR Part 465 (October 2024) when page surfaces with reviews or social proof + per-state UDAP + per-state pricing-and -discount disclosure when page includes offer (regular price vs sale price + duration + auto-renewal disclosure).
Anchor 3 — ADA Title III + WCAG 2.2 AA + California Unruh + Colorado SB21-176 + NYC Local Law 12 (serial-plaintiff exposure)
ADA Title III places of public accommodation. WCAG 2.2 AA accessibility. Robles v Dominos Pizza 9th Cir 2019 confirmed web accessibility enforceable under Title III. Gil v Winn-Dixie 11th Cir 2021 added circuit-split clarity. Per-state accessibility: California Unruh Civil Rights Act + Colorado SB21 -176 web accessibility + NYC Local Law 12 + per -state accessibility statutes. Serial-plaintiff exposure is real — multi-location operators with hundreds of per-location pages face accessibility lawsuit risk at every page. Gate runs axe-core + Pa11y + WAVE + Lighthouse accessibility scanning at publish; failures block.
Anchor 4 — Lanham Act + naked-licensing doctrine + franchisor agency-theory + FTC Franchise Rule Item 12
Lanham Act 15 USC 1125(a) trademark consistency + naked-licensing doctrine (Dawn Donut v Hart Food Stores 1959 + Stanfield v Osborne Industries 1995 + Doeblers Pennsylvania Hybrids 2010) when franchisees produce per-location pages without franchisor quality control + franchisor agency-theory (Restatement Third of Agency Sec 7.07) for per-location pages on franchisor-coordinated platforms. FTC Franchise Rule 16 CFR Part 436 + FDD Item 12 territorial cross-check (per-location page that implies exclusive geography contrary to FDD Item 12 IS Franchise Rule matter).
Anchor 5 — EU AI Act + NIST AI RMF + ISO 42001 + per-vendor LLM zero-retention
EU AI Act Article 50 transparency for AI-generated content when per-location page is AI-drafted + Article 13 transparency + Article 14 human oversight + Article 15 accuracy + Article 22 transparency of automated decision-making + Article 26 deployer obligations. NIST AI RMF Govern + Map + Measure + Manage. ISO 42001 AI Management System. Per-vendor LLM zero-retention posture verified per Compose call.
The 6-workstream pre-engagement-baseline reporting cycle
Completions does not commit to numeric organic-traffic-uplift targets before engagement scope is documented. The Q6 pre -engagement-baseline reporting cycle covers the six workstreams that ship in every engagement.
- Compose coverage. Per-location master record completeness + per-block content generation freshness + per-LLM citation grounding to source rows + brand-voice spec (#532) integration + claims-allowlist (#496) + forbidden-phrase library (#507) + per-vertical compliance overlay (#516).
- Distinct quality. MinHash + LSH inter -page similarity freshness + embedding-cosine ensemble freshness + stylometric fingerprint distance + operator -counsel-defined threshold + iterative rewrite cadence + operator-counsel review on twice-failing pages.
- Gate quality. Google Quality Rater Guidelines Section 7.4 + 7.4.1 + 3.2 check + Helpful Content System E-E-A-T signals + ADA Title III + WCAG 2.2 AA accessibility scanning + per-state accessibility + FTC substantiation + Lanham Act naked-licensing posture + FTC Franchise Rule Item 12 + sibling #520 borderline routing integration.
- Audit quality. Per-page canonical record completeness + WORM storage posture + per-page Distinct similarity-vector retention + per-page accessibility audit retention + sibling-handoff pointer freshness.
- Compliance posture. Google Helpful Content System + March 2024 Core Update + scaled -content-abuse + site-reputation-abuse + expired-domain -abuse + FAQ rich-result August 2023 + HowTo deprecation September 2023 + Quality Rater Guidelines Section 7.4 + 7.4.1 + 3.2 + FTC Section 5 + Pfizer 1972 + Endorsement Guides + Fake Review Rule + per-state UDAP + ADA Title III + WCAG 2.2 AA + California Unruh + Colorado SB21-176 + NYC Local Law 12 + Lanham Act + naked-licensing doctrine + franchisor agency-theory + FTC Franchise Rule Item 12 + EU AI Act Article 50 + 13 + 14 + 15 + 22 + 26 + NIST AI RMF + ISO 42001 + per -vendor LLM zero-retention freshness.
- Audit-trail completeness. Per-Compose + per-Distinct + per-Gate + per-Audit canonical record retention in versioned-history substrate readable by Google policy review + Lanham Act naked-licensing defense + FTC substantiation + ADA serial-plaintiff defense + state-AG enforcement + EU supervisory authority + audit committee.
Frequently asked questions
What problem does per-location landing pages at scale solve for a multi-location retail operator?
A multi-location retail or franchise operator running 50-500 stores wants per-location landing pages that drive organic traffic to per-location buyer queries (services + hours + directions + pricing + neighborhood relevance). The naive approach is a single template populated by token substitution per location. Google has been demoting that pattern since at least the September 2022 Helpful Content System launch; the March 2024 Core Update made the demotion sharper, and the March 2024 scaled-content-abuse policy explicitly targets sites that generate scaled content for the purpose of manipulating search rankings. Google Quality Rater Guidelines Section 7.4 doorway-page detection + Section 7.4.1 thin-content + Section 3.2 lowest-quality direct human raters to flag pages that are near-duplicates of each other with the same content rewritten per location. The skill ships the substrate that composes per-location pages with substantive distinctness, gates against doorway-page classification, and retains the audit trail that proves quality control + Lanham Act naked-licensing posture + ADA Title III + WCAG 2.2 AA + FTC substantiation chain.
What is the 4-skill bundle and what does each skill do?
Compose generates per-location page content blocks (hero + services + NAP + hours + team + testimonials + neighborhood context + landmarks + local events + FAQ + CTA + photos) via multi-LLM ensemble (OpenAI + Anthropic + Google + Mistral + Cohere) grounded in per-location master record + brand voice spec (sibling #532) + claims allowlist (sibling #496) + forbidden-phrase library (sibling #507) + per-vertical compliance overlay (sibling #516). Per-LLM citation grounding to master-record source rows. Per-vendor LLM zero-retention verified per call. Distinct runs inter-page distinctness gate before publish: MinHash + Locality-Sensitive Hashing across all per-location pages in the portfolio, embedding-cosine similarity via sentence-transformer + Cohere embed-v3 + OpenAI text-embedding-3 + Voyage-3 ensemble, stylometric fingerprint distance. Pages with inter-page similarity above operator-counsel-defined threshold route to Compose for substantive rewrite (more neighborhood + landmark + local-event + per-location-team detail). Gate runs Google Quality Rater Guidelines Section 7.4 doorway-page check + Section 7.4.1 thin-content check + Section 3.2 lowest-quality check + Helpful Content System E-E-A-T signals + ADA Title III + WCAG 2.2 AA accessibility check + per-state UDAP + per-state pricing-and-discount disclosure when offer included + FTC substantiation check via sibling #496 + Lanham Act naked-licensing posture check + FTC Franchise Rule Item 12 territorial cross-check. AI-drafted content routes through sibling #520 borderline routing before publish. Audit retains per-page canonical record + per-page distinctness signal + per-page Gate decision in WORM for Google policy review + Lanham Act + FTC + state-AG enforcement defense.
Why is Google March 2024 scaled-content-abuse + Helpful Content System + Quality Rater Guidelines Section 7.4 the operationally distinctive anchor for this skill?
Per-location pages are the canonical doorway-page risk pattern. Google Helpful Content System launched September 2022 and demoted sites that produce content primarily for search engines rather than people. The March 2024 Core Update folded the Helpful Content System into the core algorithm and made the demotion sharper. The March 2024 scaled-content-abuse policy explicitly targets sites that generate scaled content for the purpose of manipulating search rankings, replacing the prior auto-generated-content language; auto-generated per-location pages with minimal substantive difference between locations are the textbook case. Google Quality Rater Guidelines Section 7.4 instructs raters to flag doorway pages (multiple similar pages targeted at slightly different queries that lead users to the same destination). Section 7.4.1 thin-content covers pages that lack substantive original content. Section 3.2 lowest-quality covers pages designed primarily to rank rather than serve users. Operationally distinctive frame: Distinct enforces MinHash + LSH + embedding-cosine + stylometric inter-page similarity below operator-counsel-defined threshold, and the audit trail documents the distinctness signal at every publish. A franchisor that ships per-location pages without distinctness discipline is shipping doorway pages by another name.
What real regulatory and standards-body hooks does the compliance overlay anchor on?
Anchor 1 is Google Helpful Content System (September 2022) + Google March 2024 Core Update + Google March 2024 site-reputation-abuse policy (third-party content published on a host site for ranking purposes) + Google March 2024 scaled-content-abuse policy (replacing the prior auto-generated-content language) + Google March 2024 expired-domain-abuse policy + Google FAQ rich-result restriction (August 2023; FAQ rich results restricted to government and health authority sites) + Google HowTo rich-result deprecation (September 2023) + Google Quality Rater Guidelines Section 7.4 doorway-page detection + Section 7.4.1 thin-content + Section 3.2 lowest-quality + distinctness-gate cost-discipline (MinHash + LSH + embedding-cosine + stylometric fingerprint). Anchor 2 is FTC Section 5 + FTC substantiation doctrine (Pfizer 1972 reasonable-basis) when per-location page makes claims + FTC Endorsement Guides 16 CFR Part 255 (2023 update on AI-generated content) + FTC Fake Review Rule 16 CFR Part 465 (Oct 2024) when page surfaces with reviews or social proof + per-state UDAP + per-state pricing-and-discount disclosure when page includes offer. Anchor 3 is ADA Title III places of public accommodation + WCAG 2.2 AA accessibility (Robles v Dominos Pizza 9th Cir 2019 + Gil v Winn-Dixie 11th Cir 2021 circuit-split) + California Unruh Act + Colorado SB21-176 + NYC Local Law 12 web accessibility + per-state accessibility statutes + serial-plaintiff exposure. Anchor 4 is Lanham Act 15 USC 1125(a) trademark consistency + naked-licensing doctrine (Dawn Donut v Hart Food Stores 1959 + Stanfield v Osborne Industries 1995 + Doeblers Pennsylvania Hybrids 2010) when franchisees produce per-location pages without franchisor quality control + franchisor agency-theory exposure (Restatement Third of Agency Sec 7.07) + FTC Franchise Rule 16 CFR Part 436 + FDD Item 12 territorial cross-check (per-location page that implies exclusive geography contrary to FDD Item 12 is a Franchise Rule matter). Anchor 5 is EU AI Act Article 50 transparency for AI-generated content + Article 13 + Article 14 human oversight + Article 15 accuracy + Article 22 transparency of automated decision-making + Article 26 deployer obligations + NIST AI RMF + ISO 42001 + per-vendor LLM zero-retention.
How does Distinct actually enforce inter-page distinctness across hundreds of pages?
Inter-page similarity at scale is a near-duplicate detection problem. MinHash plus Locality-Sensitive Hashing (LSH) is the canonical sublinear approach: every page is hashed into a fixed-length MinHash signature, LSH buckets near-duplicate signatures together, and pairwise Jaccard similarity is computed only within buckets. Embedding-cosine similarity via sentence-transformer + Cohere embed-v3 + OpenAI text-embedding-3 + Voyage-3 ensemble catches paraphrase-level similarity that MinHash misses. Stylometric fingerprint distance catches identical-template-with-token-substitution patterns. Distinct enforces operator-counsel-defined threshold on all three measures. Pages above the threshold route back to Compose with explicit instruction to expand neighborhood detail + landmark mention + local-event tie-in + per-location-team detail + per-location-testimonial. Distinct is iterative: a page that fails the gate twice routes to operator-counsel review with the specific similarity-vector evidence so the team can decide whether the per-location reality genuinely supports more distinctness or whether the page should not exist at this location.
What does Completions ship and how does an engagement start?
Completions ships the per-location-landing-page agent + 4-skill bundle (Compose + Distinct + Gate + Audit) + 5-anchor compliance overlay (Google Helpful Content System + March 2024 Core Update + scaled-content-abuse + site-reputation-abuse + expired-domain-abuse + FAQ rich-result August 2023 + HowTo deprecation September 2023 + Quality Rater Guidelines Section 7.4 + 7.4.1 + 3.2 + distinctness-gate cost-discipline + FTC Section 5 + substantiation + Endorsement Guides + Fake Review Rule + per-state UDAP + ADA Title III + WCAG 2.2 AA + California Unruh + Colorado SB21-176 + NYC Local Law 12 + Lanham Act + naked-licensing doctrine + franchisor agency-theory + FTC Franchise Rule Item 12 + EU AI Act Article 50 + 13 + 14 + 15 + 22 + 26 + NIST AI RMF + ISO 42001 + per-vendor LLM zero-retention) + the Q6 6-workstream pre-engagement-baseline reporting cycle. Tier 1 AI Readiness Assessment (2-3 weeks) audits the current per-location-page posture against Google policy + ADA + Lanham Act naked-licensing posture + FTC substantiation. Tier 3 Fractional CMO with AI Swarm (6-month minimum, 1-2 days/wk embedded) runs the per-location-landing-page agent on the operator CMS + page-publish + accessibility stack on an ongoing basis.
Engage Completions on the per-location-landing-page agent
Tier 1 AI Readiness Assessment (2-3 weeks) audits the current per-location-page posture against Google policy + ADA + Lanham Act naked-licensing posture + FTC substantiation. Tier 3 Fractional CMO with AI Swarm ($15 -25k/month, 6-month minimum, 1-2 days/wk embedded) runs the per-location-landing-page agent on the operator CMS + page-publish + accessibility stack on an ongoing basis.