Agency delivery — Technical specification

White-Label GEO Diagnostic Reports for Agencies

A white-label Generative Engine Optimization (GEO) delivery pack provides digital agencies with a structured, timestamped audit of a client's AI visibility. It separates empirical crawling evidence and labeled LLM response samples from recommended code fixes, carrying full agency branding throughout. This specification details the delivery pack architecture, ticket verification lifecycles, and pre-handoff quality checks.

Updated 24 August 2026 · 12 min read · Technical specification

Editorial Transparency: Fact-checked against search engine specifications and empirical crawling tests. Our Editorial Standards →

1 — Purpose and core principles

A technical diagnostic report differs fundamentally from a marketing dashboard or speculative forecast. It serves as a timestamped, verifiable audit artifact designed for client review and engineering handoff:

Delivery readiness tracks three distinct phases: diagnosis (site crawl completed), visibility (prompt cohort sampled), and implementation (remediation code generated and reviewed). A delivery pack can be finalized for diagnostic review while generated code assets remain in draft status.

A delivery package is an immutable point-in-time snapshot. If target websites, prompt banks, audit configurations, or verification tests change, compile a new build rather than editing past archives.

Sources

2 — Delivery pack structure: documents, evidence, and assets

CiteAura compiles client deliverables into a standardized archive from work/<tenant>/<slug>/delivery/. The compiler reads active audit.json, tasks.json, metrics/, and delivery/ states, bundling numbered HTML reports, implementation assets, raw evidence JSONL files, and comparative visibility deltas with cryptographic SHA-256 manifests.

# Document Filename Contents
01 Executive Summary 01-Audit-Report.html One-page verdict: visibility posture (Blocked / Partial / Exposed), cohort mention rate with n and mode, top 3 blockers, and ticket count by severity. Written for the client decision-maker; no tool chrome.
02 Site Audit Report 02-Execution-Plan.html Per-URL findings: crawlability, HTTP status, HTML extractability, heading hierarchy, structured data (JSON-LD / Open Graph), robots.txt mapping, and WAF/auth wall detection. Each row links to raw evidence.
03 AI Visibility Matrix 03-Ticket-Log.html Cohort table: question × sampling mode × mention (yes/no) × citation (yes/no). Cohort definition, question set hash, model IDs, dates, and market. Unmeasured providers shown as unmeasured, never 0%.
04 Action Matrix & Tickets 04-Acceptance-Checklist.html Ticket log with ID, severity (P0/P1/P2), target file/URL, requested change (diff), owner, dependency, and acceptance check. Exported from tasks.json with lifecycle state.
05 Verification Evidence 05-Draft-Risks.html Before/after evidence per ticket: crawl snapshots, HTTP headers, HTML diff hash, structured data validator output, and re-sample cohort if applicable. Each ticket references its evidence page.
06 Implementation Guide 06-Build-Map.html Sequenced rollout plan: prerequisites, deploy order, rollback notes, and re-verification triggers. Links into the assets/ folder for the exact files to ship.
— Implementation Assets assets/ Generated files ready for review: llms.txt, robots.txt.patch, JSON-LD blocks, page patches, and validation reports. Every asset carries a status: draft | reviewed | approved flag. Draft assets are listed but flagged not for deploy.

Evidence attachments are organized systematically: 07-Evidence/raw-ai-answers.jsonl, 07-Evidence/raw-ai-answers.html, and 07-Evidence/citation-evidence.csv contain complete model completions and extracted source links. When comparing consecutive cycles under matching parameters, 08-Before-After/visibility-delta.md details relative cohort movement.

Archive root files:

3 — White-label branding and styling

Branding parameters are configured under Delivery → White-Label Branding and applied during pack compilation:

Configuration parameters

Compilation pipeline

  1. When an operator triggers Build Pack, the compiler captures the current branding profile into delivery/branding.json.
  2. Templates inject agency metadata directly into the document layout before rendering static HTML pages.
  3. The manifest stamps a branding_hash to verify visual configuration integrity across builds.
  4. Raw data exports in raw/ remain unstyled JSON/CSV files.

4 — Technical ticket lifecycle

Audit findings requiring code or server adjustments are tracked as structured tickets in tasks.json and exported to the action matrix:

State Meaning Exit condition
OPEN Finding confirmed by audit; ticket created, not yet assigned. Owner assigned, target file/URL specified.
IN_PROGRESS Owner is implementing the diff. Change deployed to the canonical host (not staging).
IN_REVIEW Change is live; awaiting verification evidence. Re-crawl or re-sample evidence collected.
VERIFIED Acceptance check passed against live evidence. Agency marks ticket verified; evidence page linked.
CLOSED Verified and included in the delivery pack snapshot. Pack rebuilt; manifest hashes the closed state.
BLOCKED External dependency (e.g. client CMS access, CDN cache) prevents verification. Dependency resolved; ticket returns to IN_REVIEW.

Each ticket includes:

5 — Verification and acceptance testing

Verification provides empirical proof that deployed adjustments resolved the underlying audit defect:

The automated Verify & Deliver pipeline executes acceptance probes, stores response snapshots under delivery/evidence/<ticket_id>/, and updates ticket statuses upon successful validation.

Technical verification confirms infrastructure compliance (e.g. crawler accessibility). AI mention changes represent a separate statistical measurement tracked across subsequent cohorts.

6 — End-to-end agency workflow

  1. Project setup & site audit: Configure client domain parameters, locale, and target markets. Run automated crawling and review P0 blockers.
  2. Cohort sampling: Establish the prompt bank, select sampling modes (e.g. api_param), and collect baseline responses.
  3. Ticket triage: Convert technical findings into scoped tickets with assigned developers and acceptance checks.
  4. Branding review: Verify agency visual assets and confidentiality notices in the white-label settings.
  5. Compile initial pack: Build the delivery package containing diagnostic summaries, visibility matrices, and draft remediation assets.
  6. Deploy & verify: Once client developers deploy fixes, run verification probes to confirm resolution and transition tickets to VERIFIED.
  7. Deliver final package: Rebuild the delivery ZIP and provide technical stakeholders with verified diffs and updated cohort measurements.

7 — Common engagement models

Tier Scope Deliverables Verification
Diagnostic Audit
One-time
Full site crawl + 1 baseline cohort + ticket backlog. Documents 01–04 + manifest. Implementation assets marked as draft. Diagnosis only; tickets delivered in OPEN state.
Audit + Implementation
Project-based
Audit, cohort sampling, code diff generation, and 1 verification cycle. Full documents 01–06 + evidence logs + approved assets. Post-deploy re-crawl to verify resolved tickets.
Ongoing GEO Retainer
Monthly / Quarterly
Recurring site audits + longitudinal cohort tracking + monthly verification. Updated monthly delivery packs + longitudinal deltas in Doc 08 + raw data exports. Continuous ticket verification and comparative cohort reporting.

Deliver branded GEO audit packs with verifiable technical tickets and automated client reporting in CiteAura for Agencies.

Start free trial

8 — Client handoff checklist

Review these quality gates before transmitting reports to clients:

9 — Case walkthrough: B2B SaaS platform

Profile: Mid-market B2B SaaS platform with ~180 marketing URLs, subdomain documentation, and client-rendered pricing calculators. Evaluated across US/en-US buyer prompts.

Initial diagnostic baseline: An initial crawl identified that documentation was blocked in robots.txt and pricing tables were rendered entirely via client-side JavaScript. A 20-prompt baseline cohort (API · Model knowledge) recorded a 10% mention rate (2/20). The agency delivered an initial diagnostic pack with P0 tickets for robots.txt and server-side rendering.

Remediation and verification: The client engineering team updated robots.txt rules, migrated key product descriptions to server-side HTML, and added structured SoftwareApplication JSON-LD schemas. Automated verification confirmed crawler access and HTML extractability across target pages.

Follow-up sampling: Running an identical 20-prompt cohort 7 days post-deployment recorded an 8/20 mention rate (40%). The delivery pack documented the two cohorts side-by-side with identical prompt hashes, detailing the structural improvements without asserting speculative universal visibility claims.

10 — Professional reporting boundaries

FAQ: white-label GEO reports

What belongs in a white-label GEO diagnostic report?

Site findings with evidence pointers, labeled samples, action tickets with acceptance checks, raw answer and citation exports, before/after visibility when comparable, and clear readiness states.

Can a GEO diagnostic report guarantee AI mentions?

No. It provides an empirical audit of crawlability, extractability, and sample responses; it does not guarantee a future mention, citation, or ranking. Subsequent sampling tracks relative movement without making absolute promises.

When should an agency rebuild a GEO diagnostic pack?

Rebuild whenever site infrastructure, prompt banks, white-label branding, or verification test results are updated.

How does white-label header injection work?

Agency branding parameters are configured in project settings and compiled into the document layout templates during pack generation.

What triggers a ticket state transition?

Automated re-crawling or sample verification probes that satisfy the ticket's acceptance test transition tickets to VERIFIED status.

About the Author: CiteAura Research Team

Search Systems Engineers & Evaluation Analysts

The CiteAura Research Team is the engineering working group behind the CiteAura GEO diagnostic engine, empirical crawler audits, and verifiable citation benchmarks across generative AI search systems.

Explore Team & Research → Editorial Standards →