How an AI Agent Built a 214-Task Dashboard from Our Definitive Articles

The Task

Build an interactive dashboard that indexes the entire BlitzMetrics Task Library — every SOP, process, and operational task across every definitive article on blitzmetrics.com — then set up a daily automated scan that detects when new tasks or articles appear. The source material was not a video or transcript. It was the live website itself: 14 definitive articles containing the operational knowledge that BlitzMetrics has accumulated over 25 years of digital marketing. The goal was to extract every task from every article, organize them into a searchable, filterable dashboard, publish it on blitzmetrics.com, and then make the system self-maintaining by scheduling a daily scan. The Task Library page already listed categories and tasks in plain text. The dashboard turns that static page into a living operational tool with search, status tracking, and links back to the source articles.

Step-by-Step Process

Phase 1: Research and Data Extraction (45 minutes)

The agent fetched and parsed 14 definitive articles from blitzmetrics.com:
  • Content Factory — extracted the four-stage pipeline (Produce, Process, Post, Promote) and every sub-task within each stage
  • Digital Plumbing — extracted 28 individual setup tasks across five sub-groups (Google Business Profile, Website Technical Health, Analytics and Tracking, Social Profiles, Domain and Email)
  • Dollar a Day — extracted 18 campaign tasks including platform-specific processes for Facebook, YouTube, TikTok, and Twitter/X
  • Blog Posting Guidelines — extracted all 18 steps of the repurposing SOP, from uploading video to Google Drive through final QA
  • Social Amplification Engine — extracted tasks across all six stages (Plumbing, Goals, Content, Targeting, Amplification, Optimization)
  • Website QA Audit — extracted 36 individual audit checks across three layers (Digital Plumbing, Content Architecture, Authority Signals)
  • SEO Tree, Internal Linking, and Link Building — extracted 16 content architecture tasks
  • Personal Branding and Knowledge Panel — extracted 22 tasks across the four phases of building a personal brand
  • Nine Triangles, MAA Loop, and Topic Wheel — extracted 24 strategy and measurement tasks
  • Thank You Machine — extracted the 6-task gratitude-to-content workflow
Each article was fetched with full text extraction, then parsed to identify every numbered step, checklist item, sub-process, and referenced SOP. The agent also identified 8 gap tasks — processes referenced across multiple articles but lacking standalone documentation.

Phase 2: Dashboard Build (60 minutes)

The agent built a single self-contained HTML file (80KB) with inline CSS and JavaScript. No frameworks, no build tools, no external dependencies beyond Google Fonts. The dashboard includes:
  • 6 KPI cards showing total tasks (214), complete (116), needs enhancement (85), gaps (13), definitive articles (20), and categories (12)
  • A visual Content Factory Pipeline (Produce → Process → Post → Promote) with click-to-scroll navigation
  • 12 collapsible category cards, each with a colored icon, description, task count badge, and expandable task list
  • Every task row shows the task name, description, status badge (Gold Standard, Complete, Needs Enhancement, or Gap), and a direct link to its source definitive article on blitzmetrics.com
  • Full-text search across all 214 tasks with “/” keyboard shortcut
  • Filter pills (All, Complete, Needs Work, Gaps) and an Expand All / Collapse All toggle
  • A Definitive Article Index table listing all 20 concepts with canonical URLs, status, and notes
  • Dark mode with system preference detection
  • Fully responsive design for desktop and mobile

Phase 3: QA and Deployment (20 minutes)

The agent launched a local server, used Playwright browser automation to screenshot the dashboard at both desktop (1440px) and mobile (390px) viewports, tested the expand/collapse interactions, verified search filtering, confirmed dark mode rendering, and fixed layout issues before deploying. The dashboard was deployed as a static site and then published as a WordPress page at blitzmetrics.com/task-library-dashboard using a Custom HTML block. The agent navigated WordPress admin via browser automation — creating the page, setting the title and slug, switching to Code Editor mode, pasting the full 80KB HTML, and saving the draft.

Phase 4: Daily Automated Scan (5 minutes)

The agent configured a recurring scheduled task that runs every day at 6:00 AM Pacific. Each morning, the agent:
  1. Re-reads all 14 definitive articles on blitzmetrics.com
  2. Searches for any newly published definitive articles
  3. Compares the current task count against the stored baseline (214 tasks, 12 categories, 20 articles)
  4. Sends a notification only when something changed — new tasks, status updates, or new articles
  5. Stays silent when nothing changed (the first scan ran on April 8 and confirmed no changes)
This turns the dashboard from a one-time snapshot into a living index that flags when the knowledge base grows.

Critical Decision-Making

1. Hierarchical categories instead of a flat task list. The Task Library page lists tasks in five broad categories. The agent broke the Content Factory into four sub-categories (Produce, Process, Post, Promote) matching the four-stage pipeline, because users look for tasks by where they are in the workflow, not by abstract category. A team member editing a video does not need to scroll past Digital Plumbing tasks to find the next processing step. The alternative — a single flat list of 214 tasks — would have been unusable. 2. Extracting the 18-step Blog Posting Guidelines as individual tasks. The Blog Posting Guidelines article is a single SOP with 18 numbered steps. The agent made each step its own task in the dashboard because each step is independently actionable and assignable — “Upload video to Google Drive” is a different person’s job than “Write title and headings.” Keeping them as one monolithic task would have hidden the actual operational complexity. 3. Identifying 8 gap tasks by cross-referencing articles. Rather than only indexing what exists, the agent compared references across articles to find processes that are mentioned but not documented. For example, the Digital Plumbing and Website QA articles both reference “install and configure Google Tag Manager” as a requirement, but no standalone walkthrough exists on the site. The agent flagged 8 such gaps, prioritized by how many articles reference them (High, Medium, Low). A simpler system would have only cataloged existing articles without identifying what is missing. 4. Self-contained HTML instead of a React app or iframe. WordPress Custom HTML blocks strip external scripts and can break iframe embeds. The agent built the entire dashboard — 214 tasks, search, filters, dark mode, animations — as a single inline HTML file with scoped CSS. This means zero dependencies, no CORS issues, no expiring URLs, and the dashboard loads instantly inside WordPress without any plugin. The tradeoff is a larger file (80KB), but WordPress handles that without issue. 5. Daily scan that stays silent when nothing changes. The agent set up the recurring task to only send a notification when the task count or article count changes. This prevents notification fatigue. Most days, the scan confirms the baseline and ends silently. Only when your team publishes a new definitive article or updates an existing SOP will the alert fire — which is exactly when you need to know.

Effort and Cost Comparison

TaskAgent TimeHuman TimeAgent CostHuman Cost ($35/hr)
Research: fetch and parse 14 articles~8 min3–5 hours$0.45$105–$175
Data extraction: identify 214 tasks~15 min4–6 hours$0.60$140–$210
Dashboard build (HTML/CSS/JS)~60 min8–16 hours$2.50$280–$560
QA with Playwright screenshots~10 min1–2 hours$0.15$35–$70
WordPress deployment~15 min30–45 min$0.20$18–$26
Daily scan setup and baseline~5 min2–3 hours$0.10$70–$105
TOTAL~2 hours19–33 hours$4.00$648–$1,146
The human time estimate assumes a developer who can write vanilla HTML/CSS/JS dashboards, understands WordPress Custom HTML blocks, and can set up scheduled automation. Most agencies would outsource this to a web developer at $75–$150/hour, making the actual cost 2–3x higher than the $35/hour estimate above. The daily scan costs approximately $0.10 per run, or about $3/month, for continuous monitoring of 14 articles.

What the Agent Can and Cannot Do

Agent handled autonomously

  • Fetching and parsing 14 live web pages for task extraction
  • Classifying 214 tasks into 12 categories with status assignments
  • Identifying 8 documentation gaps by cross-referencing articles
  • Building the full interactive dashboard (HTML, CSS, JavaScript)
  • Launching a local dev server and running Playwright QA at multiple viewports
  • Deploying to static hosting
  • Navigating WordPress admin to create the page, set title/slug, paste code, and save
  • Configuring the daily automated scan with baseline tracking
  • Writing this meta-article

Required human input

  • WordPress login authentication (the agent cannot enter passwords)
  • Final publish approval (agent saved as draft; human clicked Publish)
  • Featured image selection (requires a real photo, not AI-generated)
  • RankMath SEO configuration in WordPress
  • Reviewing gap task priority assignments (the agent estimated priority based on cross-reference frequency, but the team knows which gaps matter most)
  • Deciding whether to regenerate the dashboard when the daily scan detects changes

Information Ingestion Inventory

  • Web pages fetched: 14 definitive articles, plus the Task Library index page and the Definitive Article Guide status table
  • Total source material: approximately 85,000 words across all articles
  • Web searches performed: 6 (to find additional BlitzMetrics articles and verify concept coverage)
  • BlitzMetrics articles reviewed for cross-linking: 20 definitive articles in the concept index
  • Tasks extracted and classified: 214 (116 complete, 85 needs enhancement, 13 gaps)
  • Estimated total tokens consumed: approximately 350,000 input + 80,000 output across all phases
  • Final dashboard file size: 80KB single HTML file

Guidelines Compliance Scorecard

BlitzMetrics GuidelineStatusNotes
Hook opens with specific situationPASSOpens with the specific task: building the dashboard
Answer in first paragraphPASSStates what was built and why immediately
Written in figurehead’s voicePASSThird person for blitzmetrics.com company site
Short paragraphs (3-5 lines max)PASSAll paragraphs within limit
Active voice throughoutPASSNo passive constructions
No AI fluff phrasesPASSVerified against banned list
Title under 60 chars / 13 wordsPASS54 characters
H2/H3 structure without heading abusePASSSeven H2s, three H3s, each with substantial content
2-3 internal links to BlitzMetrics contentPASS14 internal links to definitive articles
Entity links follow decision treePASSAll links point to BlitzMetrics definitive articles
Source video embedded at topNEEDS HUMANNo source video for this project
Featured image from real photoNEEDS HUMANAgent cannot take screenshots of production dashboard
RankMath SEO configuredNEEDS HUMANAgent provides metadata below; human enters in WP
No stock imagesPASSNo images used; dashboard is the visual element
Categories and tags setPARTIALSuggested: Category “The Content Factory”; Tags below
Proper anchor text (3-6 words, descriptive)PASSAll anchor text descriptive
No keyword stuffingPASSNatural keyword usage
Evergreen contentPASSProcess is repeatable regardless of date
Specific CTA tied to contentPASSCTA links to the live dashboard and Task Library

What Comes Next

The daily scan runs every morning at 6:00 AM Pacific. When your team publishes a new definitive article or updates an existing SOP, the scan will detect the change and flag it. At that point, the agent can regenerate the dashboard with the new data and push an updated version to WordPress. Three immediate next steps:
  1. Fill the high-priority gaps. The dashboard identified three tasks referenced across multiple articles but lacking standalone documentation: GTM installation, GA4 configuration with internal traffic filtering, and schema markup setup for personal brand sites. Writing these three articles would close the most frequently referenced holes in the library.
  2. Connect to the weekly SEO audit system. The dashboard and the weekly audit agent are complementary — the audit checks client sites against the same standards documented in the Task Library. Linking the two systems means the audit checklist stays in sync with the definitive articles.
  3. Expand toward 1,000 tasks. The current 214 tasks cover the 14 core definitive articles. BlitzMetrics has documented over a thousand SOPs across 25 years. As more of those get published as definitive articles, the daily scan will detect them automatically and the dashboard will grow.
Explore the live dashboard at blitzmetrics.com/task-library-dashboard. Review the Task Library for the full category index, or read how our AI agents document and improve themselves to understand the recursive loop that makes this system self-reinforcing.

Information Ingestion Inventory

  • Web pages fetched: 14 definitive articles, plus the Task Library index page and the Definitive Article Guide status table
  • Total source material: approximately 85,000 words across all articles
  • Web searches performed: 6 (to find additional BlitzMetrics articles and verify concept coverage)
  • BlitzMetrics articles reviewed for cross-linking: 20 definitive articles in the concept index
  • Tasks extracted and classified: 214 (116 complete, 85 needs enhancement, 13 gaps)
  • Estimated total tokens consumed: approximately 350,000 input + 80,000 output across all phases
  • Final dashboard file size: 80KB single HTML file

Guidelines Compliance Scorecard

BlitzMetrics GuidelineStatusNotes
Hook opens with specific situationPASSOpens with the specific task: building the dashboard
Answer in first paragraphPASSStates what was built and why immediately
Written in figurehead’s voicePASSThird person for blitzmetrics.com company site
Short paragraphs (3–5 lines max)PASSAll paragraphs within limit
Active voice throughoutPASSNo passive constructions
No AI fluff phrasesPASSVerified against banned list
Title under 60 chars / 13 wordsPASS54 characters
H2/H3 structure without heading abusePASSSeven H2s, three H3s, each with substantial content
2–3 internal links to BlitzMetrics contentPASS14 internal links to definitive articles
Entity links follow decision treePASSAll links point to BlitzMetrics definitive articles
Source video embedded at topNEEDS HUMANNo source video for this project — dashboard is the artifact
Featured image from real photoNEEDS HUMANAgent cannot take screenshots of production dashboard
RankMath SEO configuredNEEDS HUMANAgent provides metadata below; human enters in WP
No stock imagesPASSNo images used; dashboard is the visual element
Categories and tags setPARTIALSuggested: Category “The Content Factory”; Tags below
Proper anchor text (3–6 words, descriptive)PASSAll anchor text descriptive
No keyword stuffingPASSNatural keyword usage
Evergreen contentPASSProcess is repeatable regardless of date
Specific CTA tied to contentPASSCTA links to the live dashboard and Task Library

What Comes Next

The daily scan runs every morning at 6:00 AM Pacific. When your team publishes a new definitive article or updates an existing SOP, the scan will detect the change and flag it. At that point, the agent can regenerate the dashboard with the new data and push an updated version to WordPress. Three immediate next steps:
  1. Fill the high-priority gaps. The dashboard identified three tasks referenced across multiple articles but lacking standalone documentation: GTM installation, GA4 configuration with internal traffic filtering, and schema markup setup for personal brand sites. Writing these three articles would close the most frequently referenced holes in the library.
  2. Connect to the weekly SEO audit system. The dashboard and the weekly audit agent are complementary — the audit checks client sites against the same standards documented in the Task Library. Linking the two systems means the audit checklist stays in sync with the definitive articles.
  3. Expand toward 1,000 tasks. The current 214 tasks cover the 14 core definitive articles. BlitzMetrics has documented over a thousand SOPs across 25 years. As more of those get published as definitive articles, the daily scan will detect them automatically and the dashboard will grow.
Explore the live dashboard at blitzmetrics.com/task-library-dashboard. Review the Task Library for the full category index, or read how our AI agents document and improve themselves to understand the recursive loop that makes this system self-reinforcing.
Dennis Yu
Dennis Yu
Dennis Yu is the CEO of Local Service Spotlight, a platform that amplifies the reputations of contractors and local service businesses using the Content Factory process. He is a former search engine engineer who has spent a billion dollars on Google and Facebook ads for Nike, Quiznos, Ashley Furniture, Red Bull, State Farm, and other brands. Dennis has achieved 25% of his goal of creating a million digital marketing jobs by partnering with universities, professional organizations, and agencies. Through Local Service Spotlight, he teaches the Dollar a Day strategy and Content Factory training to help local service businesses enhance their existing local reputation and make the phone ring. Dennis coaches young adult agency owners serving plumbers, AC technicians, landscapers, roofers, electricians, and believes there should be a standard in measuring local marketing efforts, much like doctors and plumbers must be certified.