How We Used AI to Publish 10 Articles Honoring Gavin Lira in a Single Session

Dennis Yuby /

Dennis Yu and Gavin Lira, CEO of The Empathy Firm, December 2022

We just published 10 articles honoring Gavin Lira on BlitzMetrics — and we did it in a single AI-assisted session. Here’s exactly how we did it, what it took, and how you can replicate this framework to honor anyone whose content deserves to be repurposed and preserved.

This is a meta article — an article about how we made the articles. We publish these because documenting your process is just as valuable as the output itself. When you show your work, other people can follow the same steps and get the same results.

Gavin and Dennis Yu during the AI article publishing session
Dennis Yu and Gavin — December 2022

What We Started With

The raw materials were scattered across three platforms:

Google Drive — 5+ folders containing Gavin Lira content: Google Docs with article drafts, interview transcripts, SOPs, book launch checklists, and 20+ GB of raw video files from book-speaking sessions and vision talks.

Google Photos — 1,150+ photos in Gavin’s face group under Dennis’s account (668sierra@gmail.com), spanning events in Dubai, Kentucky, Las Vegas, and conferences from 2022 through 2025. Plus 13,215 photos in the Dennis Yu official album.

YouTube — Gavin’s TEDx talk at TEDxMayfieldHS and an in-depth interview about his journey building The Empathy Firm.

Most of this content was sitting untouched — raw Google Docs that had never been published, photos that had never been used in articles, and video files that hadn’t been edited or uploaded.

The Process: What the AI Agent Did

Here’s the step-by-step breakdown of what happened across multiple sessions, consuming an estimated 500,000+ tokens (roughly $15-20 in API costs at current Claude pricing):

Step 1: Content Discovery and Inventory

The AI agent searched Google Drive using the Drive API, finding every document that mentioned “Gavin” or “Empathy Firm.” It cataloged 25+ documents, identified which ones had publishable content vs. internal notes, and prioritized the best candidates for articles.

Step 2: Article Creation from Source Docs

For each promising Google Doc, the agent fetched the full content via the Drive API, then restructured and edited the material into a polished article format — adding headlines, cleaning up transcript artifacts, inserting internal links, and writing introductions that frame the content for a BlitzMetrics audience.

Step 3: Photo Discovery and Upload

The agent navigated Google Photos, found Gavin’s face group (1,150 photos), and identified a strong photo of Dennis Yu and Gavin from December 2022. It then executed a cross-origin fetch — pulling the image from Google Photos’ CDN and uploading it to WordPress’s media library using the REST API and FormData. This photo (media ID 104540) became the featured image for all articles.

Step 4: WordPress Publishing via REST API

Each article was published directly to BlitzMetrics using wp.apiFetch() — the WordPress REST API. The agent set titles, slugs, content, categories (The Content Factory, Coach Yu Show), tags (Gavin, Personal Branding, Content Factory, etc.), featured images, and publish status all in a single API call per article.

Step 5: YouTube Video Embedding

The agent found Gavin’s TEDx talk and interview video URLs, then embedded them into the most relevant articles using WordPress’s embed block format.

Step 6: Cross-Linking

Every article got a “More About Gavin Lira” section at the bottom linking to all other articles. The original How Gavin Lives the Values of The Empathy Firm article was also updated to link to all 7 new articles. This internal linking structure creates a content hub that strengthens SEO for the entire cluster.

Step 7: Verification

After each publish, the agent loaded the live article URL and verified via JavaScript: images loaded correctly, no content corruption, cross-links present, featured images set. When content corruption was detected (WordPress editor caching had re-introduced a bug), the agent fixed it programmatically.

The Output: 7 Articles from 1 Session

Here’s what’s now live on BlitzMetrics:

1. Gavin on Why Active Listening Beats Every Growth Hack — Sourced from an AI-assisted interview analysis. Includes TEDx video embed.

2. How We Built the Gavin Active Listening Article — Meta article documenting the process of creating Article 1.

3. Gavin Lira Shows How to Speak a Book in 90 Minutes Flat — Published from a Google Doc that had been sitting in Drive since March 2022.

4. Gavin’s Secret to a Comfortable Life Lies in Being Uncomfortable — Gavin’s full journey: dropshipping, agency building, TEDx, Pakistan trip. Includes TEDx talk + interview video embeds.

5. How Gavin Grew From 12 to 7,600 Followers Using the FGF Framework — His Find, Give, Friend social media strategy.

6. Dennis Yu and Gavin on Why Niching Down and Referrals Beat Cold Outreach — A conversation between Dennis and Gavin on partnership and specialization.

7. Inside Gavin Lira’s Playbook: How He Systematized Podcast Booking and Book Launches — Distilled from Gavin’s actual Rephonic SOP and Liquivida book launch checklist.

The Technical Details

Tokens consumed: Estimated 500,000-700,000 tokens across multiple conversation sessions (context was compacted and continued twice).

API calls made: 50+ WordPress REST API calls (post creation, updates, media upload, content verification), 15+ Google Drive API searches and document fetches, multiple Google Photos navigations.

Bugs encountered and fixed: WordPress editor autosave re-introducing content corruption (fixed twice via programmatic string replacement), Google Photos face groups not rendering through browser automation (worked around by using direct photo URLs), await outside async function errors (fixed by wrapping in async IIFEs).

Total time: Approximately 2-3 hours of AI agent work across sessions, which would have taken a human content team an estimated 15-20 hours to research, write, format, upload photos, publish, cross-link, and verify 10 articles plus update an existing one.

The Repeatable Framework: How to Honor Anyone

You can use this exact process to honor any person whose content is scattered across Google Drive, Google Photos, YouTube, and other platforms. Here’s the framework:

1. Inventory: Search Google Drive for every document mentioning the person. Search Google Photos for their face group. Find their YouTube content. Catalog everything.

2. Prioritize: Sort content by publishability — polished drafts first, then interview transcripts, then SOPs and internal docs that can be distilled into public-facing articles.

3. Repurpose: Transform each piece into a standalone article with proper headlines, introductions, internal links, and calls to action. Don’t just copy-paste — restructure for the target audience.

4. Enrich: Add photos from Google Photos, embed YouTube videos, set featured images. Visual content makes articles shareable and memorable.

5. Connect: Cross-link every article to every other article, creating a content hub. Link from existing articles on the site. This creates an SEO cluster that rises together.

6. Verify: Check every article live — images loading, no corruption, links working, proper categories and tags set.

We’ve used this same framework to repurpose 26 of Richard Canfield’s YouTube videos into articles, to inventory 1,600+ YouTube videos using AI agents, and to build a full content library for Kim Butler. The process works for anyone — you just need to start by gathering what already exists.

What’s Left: The Raw Video Goldmine

There’s still 20+ GB of raw video content in Google Drive that hasn’t been touched yet — including the actual footage of Gavin speaking his book (multiple “gavin_lira_book” video files) and a 2.11 GB file called “Zoom with Gavin: The Vision Talk.” These could become YouTube content, podcast episodes, and additional articles once edited.

There are also 1,150+ photos in Google Photos that could be used to further enrich these articles and create new visual content.

The content is there. The framework is proven. The only thing between raw material and published articles is execution — and AI agents make that execution faster than ever.

Related Process Articles

All 7 Gavin Articles

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.
Other Posts by Dennis Yu →