Tygart Media

Tag: GCP Infrastructure

  • Split Brain Architecture: How One Person Manages 27 WordPress Sites Without an Agency

    Split Brain Architecture: How One Person Manages 27 WordPress Sites Without an Agency

    The Lab · Tygart Media
    Experiment Nº 684 · Methodology Notes
    METHODS · OBSERVATIONS · RESULTS

    The question I get most often from restoration contractors who’ve seen what we build is some version of: how is this possible with one person?

    Twenty-seven WordPress sites. Hundreds of articles published monthly. Featured images generated and uploaded at scale. Social media content drafted across a dozen brands. SEO, schema, internal linking, taxonomy — all of it maintained, all of it moving.

    The answer is an architecture I’ve come to call Split Brain. It’s not a software product. It’s a division of cognitive labor between two types of intelligence — one optimized for live strategic thinking, one optimized for high-volume execution — and getting that division right is what makes the whole system possible.

    The Two Brains

    The Split Brain architecture has two sides.

    The first side is Claude — Anthropic’s AI — running in a live conversational session. This is where strategy happens. Where a new content angle gets developed, interrogated, and refined. Where a client site gets analyzed and a priority sequence gets built. Where the judgment calls live: what to write, why, for whom, in what order, with what framing. Claude is the thinking partner, the editorial director, the strategist who can hold the full context of a client’s competitive situation and make nuanced recommendations in real time.

    The second side is Google Cloud Platform — specifically Vertex AI running Gemini models, backed by Cloud Run services, Cloud Storage, and BigQuery. This is where execution happens at volume. Bulk article generation. Batch API calls that cut cost in half for non-time-sensitive work. Image generation through Vertex AI’s Imagen. Automated publishing pipelines that can push fifty articles to a WordPress site while I’m working on something else entirely.

    The two sides don’t do the same things. That’s the whole point.

    Why Splitting the Work Matters

    The instinct when you first encounter powerful AI tools is to use one thing for everything. Pick a model, run everything through it, see what happens.

    This produces mediocre results at high cost. The same model that’s excellent for developing a nuanced content strategy is overkill for generating fifty FAQ schema blocks. The same model that’s fast and cheap for taxonomy cleanup is inadequate for long-form strategic analysis. Using a single tool indiscriminately means you’re either overpaying for bulk work or under-resourcing the work that actually requires judgment.

    The Split Brain architecture routes work to the right tool for the job:

    • Haiku (fast, cheap, reliable): taxonomy assignment, meta description generation, schema markup, social media volume, AEO FAQ blocks — anything where the pattern is clear and the output is structured
    • Sonnet (balanced): content briefs, GEO optimization, article expansion, flagship social posts — work that requires more nuance than pure pattern-matching but doesn’t need the full strategic layer
    • Opus / Claude live session: long-form strategy, client analysis, editorial decisions, anything where the output depends on holding complex context and making judgment calls
    • Batch API: any job over twenty articles that isn’t time-sensitive — fifty percent cost reduction, same quality, runs in the background

    The model routing isn’t arbitrary. It was validated empirically across dozens of content sprints before it became the default. The wrong routing is expensive, slow, or both.

    WordPress as the Database Layer

    Most WordPress management tools treat the CMS as a front-end interface — you log in, click around, make changes manually. That mental model caps your throughput at whatever a human can do through a browser in a workday.

    In the Split Brain architecture, WordPress is a database. Every site exposes a REST API. Every content operation — publishing, updating, taxonomy assignment, schema injection, internal link modification — happens programmatically via direct API calls, not through the admin UI.

    This changes the throughput ceiling entirely. Publishing twenty articles through the WordPress admin takes most of a day. Publishing twenty articles via the REST API, with all metadata, categories, tags, schema, and featured images attached, takes minutes. The human time is in the strategy and quality review — not in the clicking.

    Twenty-seven sites across different hosting environments required solving the routing problem: some sites on WP Engine behind Cloudflare, one on SiteGround with strict IP rules, several on GCP Compute Engine. The solution is a Cloud Run proxy that handles authentication and routing for the entire network, with a dedicated publisher service for the one site that blocks all external traffic. The infrastructure complexity is solved once and then invisible.

    Notion as the Human Layer

    A system that runs at this velocity generates a lot of state: what was published where, what’s scheduled, what’s in draft, what tasks are pending, which sites have been audited recently, which content clusters are complete and which have gaps.

    Notion is where all of that state lives in human-readable form. Not as a project management tool in the traditional sense — as an operating system. Six relational databases covering entities, contacts, revenue pipeline, actions, content pipeline, and a knowledge lab. Automated agents that triage new tasks, flag stale work, surface content gaps, and compile weekly briefings without being asked.

    The architecture means I’m never managing the system — the system manages itself, and I review what it surfaces. The weekly synthesizer produces an executive briefing every Sunday. The triage agent routes new items to priority queues automatically. The content guardian flags anything that’s close to a publish deadline and not yet in scheduled state.

    Human attention goes to decisions, not to administration.

    What This Looks Like in Practice

    A typical content sprint for a client site starts with a live Claude session: what does this site need, in what order, targeting which keywords, with what persona in mind. That session produces a structured brief — JSON, not prose — that seeds everything downstream.

    The brief goes to GCP. Gemini generates the articles. Imagen generates the featured images. The batch publisher pushes everything to WordPress with full metadata attached. The social layer picks up the published URLs and drafts platform-specific posts for each piece. The internal link scanner identifies connections to existing content and queues a linking pass.

    My involvement during execution is monitoring, not doing. The doing is automated. The judgment — what to build, why, and whether the output clears the quality bar — stays with the human layer.

    This is what makes the throughput possible. Not working harder or faster. Designing the system so that the parts that require human judgment get human judgment, and the parts that don’t get automated at whatever volume the infrastructure supports.

    The Honest Constraints

    The Split Brain architecture is not a magic box. It has real constraints worth naming.

    Quality gates are essential. High-volume automated content production without rigorous pre-publish review produces high-volume errors. Every content sprint runs through a quality gate that checks for unsourced statistical claims, fabricated numbers, and anything that reads like the model invented a fact. This is non-negotiable — the efficiency gains from automation are worthless if they introduce errors that damage a client’s credibility.

    Architecture decisions made early are expensive to change later. The taxonomy structure, the internal link architecture, the schema conventions — getting these right before publishing at scale is substantially easier than retrofitting them across hundreds of existing posts. The speed advantage of the system only compounds if the foundation is solid.

    And the system requires maintenance. Models improve. APIs change. Hosting environments add new restrictions. What works today for routing traffic to a specific site may need adjustment next quarter. The infrastructure overhead is real, even if it’s substantially lower than managing a human team of equivalent output.

    None of these constraints make the architecture less viable. They make it more important to design it deliberately — to understand what the system is doing, why each component is there, and what would break if any piece of it changed.

    That’s the Split Brain. Two kinds of intelligence, clearly divided, doing the work each is actually suited for.

    Tygart Media is built on this architecture. If you’re a service business thinking about what an AI-native content operation could look like for your vertical, the conversation starts with understanding what requires judgment and what doesn’t.

    {
    “@context”: “https://schema.org”,
    “@type”: “Article”,
    “headline”: “Split Brain Architecture: How One Person Manages 27 WordPress Sites Without an Agency”,
    “description”: “Claude for live strategy. GCP and Gemini for bulk execution. Notion as the operating layer. Here is the exact architecture behind managing 27 WordPress sites as”,
    “datePublished”: “2026-04-02”,
    “dateModified”: “2026-04-03”,
    “author”: {
    “@type”: “Person”,
    “name”: “Will Tygart”,
    “url”: “https://tygartmedia.com/about”
    },
    “publisher”: {
    “@type”: “Organization”,
    “name”: “Tygart Media”,
    “url”: “https://tygartmedia.com”,
    “logo”: {
    “@type”: “ImageObject”,
    “url”: “https://tygartmedia.com/wp-content/uploads/tygart-media-logo.png”
    }
    },
    “mainEntityOfPage”: {
    “@type”: “WebPage”,
    “@id”: “https://tygartmedia.com/split-brain-architecture-ai-content-operations/”
    }
    }

    Further Reading

  • I Let Claude Build a 20-Song Music Catalog in One Session — Here’s What Happened

    I Let Claude Build a 20-Song Music Catalog in One Session — Here’s What Happened

    The Lab · Tygart Media
    Experiment Nº 603 · Methodology Notes
    METHODS · OBSERVATIONS · RESULTS

    I wanted to test a question that’s been nagging me since I started building autonomous AI pipelines: how far can you push a creative workflow before the quality falls off a cliff?

    The answer, it turns out, is further than I expected — but the cliff is real, and knowing where it is matters more than the output itself.

    The Experiment: Zero Human Edits, 20 Songs, 19 Genres

    The setup was straightforward in concept and absurdly complex in execution. I gave Claude one instruction: generate original songs using Producer.ai, analyze each one with Gemini 2.0 Flash, create custom artwork with Imagen 4, build a listening page with a custom audio player, publish it to this site, update the music hub, log everything to Notion, and then loop back and do it again.

    The constraint that made it real: Claude had to honestly assess quality after every batch and stop when diminishing returns hit. No padding the catalog with filler. No claiming mediocre output was good. The stakes had to be real or the whole experiment was theater.

    Over the course of one extended session, the pipeline produced 20 original tracks spanning 19 distinct genres — from heavy metal to bossa nova, punk rock to Celtic folk, ambient electronic to gospel soul.

    How the Pipeline Actually Works

    Each song passes through a 7-stage autonomous pipeline with zero human intervention between stages:

    1. Prompt Engineering — Claude crafts a genre-specific prompt designed to push Producer.ai toward authentic instrumentation and songwriting conventions for that genre, not generic “make a song in X style” requests.
    2. Generation — Producer.ai generates the track. Claude navigates the interface via browser automation, waits for generation to complete, then extracts the audio URL from the page metadata.
    3. Audio Conversion — The raw m4a file is downloaded and converted to MP3 at 192kbps for the full version, plus a trimmed 90-second version at 128kbps for AI analysis.
    4. Gemini 2.0 Flash Analysis — The trimmed audio is sent to Google’s Gemini 2.0 Flash model via Vertex AI. Gemini listens to the actual audio and returns a structured analysis: song description, artwork prompt suggestion, narrative story, and thematic elements.
    5. Imagen 4 Artwork — Gemini’s artwork prompt feeds into Google’s Imagen 4 model, which generates a 1:1 album cover. Each cover is genre-matched — moody neon for synthwave, weathered wood textures for Appalachian folk, stained glass for gospel soul.
    6. WordPress Publishing — The MP3 and artwork upload to WordPress. Claude builds a complete listening page with a custom HTML/CSS/JS audio player, genre-specific accent colors, lyrics or composition notes, and the AI-generated story. The page publishes as a child of the music hub.
    7. Hub Update & Logging — The music hub grid gets a new card with the artwork, title, and genre badge. Everything logs to Notion for the operational record.

    The entire stack runs on Google Cloud — Vertex AI for Gemini and Imagen 4, authenticated via service account JWT tokens. WordPress sits on a GCP Compute Engine instance. The only external dependency is Producer.ai for the actual audio generation.

    The 20-Song Catalog

    You can listen to every track on the Tygart Media Music Hub. Here’s the full catalog with genre and a quick take on each:

    # Title Genre Assessment
    1 Anvil and Ember Blues Rock Strong opener — gritty, authentic tone
    2 Neon Cathedral Synthwave / Darkwave Atmospheric, genre-accurate production
    3 Velvet Frequency Trip-Hop Moody, textured, held together well
    4 Hollow Bones Appalachian Folk Top 3 — haunting, genuine folk storytelling
    5 Glass Lighthouse Dream Pop / Indie Pop Shimmery, the lightest track in the catalog
    6 Meridian Line Orchestral Hip-Hop Surprisingly cohesive genre fusion
    7 Salt and Ceremony Gospel Soul Warm, emotionally grounded
    8 Tide and Timber Roots Reggae Laid-back, authentic reggae rhythm
    9 Paper Lanterns Bossa Nova Gentle, genuine Brazilian feel
    10 Burnt Bridges, Better Views Punk Rock Top 3 — raw energy, real punk attitude
    11 Signal Drift Ambient Electronic Spacious instrumental, no lyrics needed
    12 Gravel and Grace Modern Country Solid modern Nashville sound
    13 Velvet Hours Neo-Soul R&B Vocal instrumental — texture over lyrics
    14 The Keeper’s Lantern Celtic Folk Top 3 — strong closer, unique sonic palette

    Plus 6 earlier experimental tracks (Iron Heart variations, Iron and Salt, The Velvet Pour, Rusted Pocketknife) that preceded the formal pipeline and are also on the hub.

    Where Quality Held Up — and Where It Didn’t

    The pipeline performed best on genres with strong structural conventions. Blues rock, punk, folk, country, and Celtic music all have well-defined instrumentation and songwriting patterns that Producer.ai could lock into. The AI wasn’t inventing a genre — it was executing within one, and the results were genuinely listenable.

    The weakest output came from genres that rely on subtlety and human nuance. The neo-soul track (Velvet Hours) ended up as a vocal instrumental — beautiful textures, but no real lyrical content. It felt more like a mood than a song. The synthwave track was competent but slightly generic — it hit every synth cliché without adding anything distinctive.

    The biggest surprise was Meridian Line (Orchestral Hip-Hop). Fusing a full orchestral arrangement with hip-hop production is hard for human producers. The AI pulled it off with more coherence than I expected.

    The Honest Assessment: Why I Stopped at 20

    After 14 songs in the formal pipeline (plus the 6 experimental tracks), I evaluated what genres remained untapped. The answer was ska, reggaeton, polka, zydeco — genres that would have been novelty picks, not genuine catalog additions. Each of the 19 genres I covered brought a distinctly different sonic palette, vocal style, and emotional register. Song 20 was the right place to stop because Song 21 would have been padding.

    This is the part that matters for anyone building autonomous creative systems: the quality curve isn’t linear. You don’t get steadily worse output. You get strong results across a wide range, and then you hit a wall where the remaining options are either redundant (too similar to something you already made) or contrived (genres you’re forcing because they’re different, not because they’re good).

    Knowing where that wall is — and having the system honestly report it — is the difference between a useful pipeline and a content mill.

    What This Means for AI-Driven Creative Work

    This experiment wasn’t about proving AI can replace musicians. It can’t. Every track in this catalog is a competent execution of genre conventions — but none of them have the idiosyncratic human choices that make music genuinely memorable. No AI song here will be someone’s favorite song.

    What the experiment does prove is that the full creative pipeline — from ideation through production, analysis, visual design, web publishing, and catalog management — can run autonomously at a quality level that’s functional and honest about its limitations.

    The tech stack that made this possible:

    • Claude — Pipeline orchestration, prompt engineering, quality assessment, web publishing, and the decision to stop
    • Producer.ai — Audio generation from text prompts
    • Gemini 2.0 Flash — Audio analysis (it actually listened to the MP3 and described what it heard)
    • Imagen 4 — Album artwork generation from Gemini’s descriptions
    • Google Cloud Vertex AI — API backbone for both Gemini and Imagen 4
    • WordPress REST API — Direct publishing with custom HTML listening pages
    • Notion API — Operational logging for every song

    Total cost for the entire 20-song catalog: a few dollars in Vertex AI API calls. Zero human edits to the published output.

    Listen for Yourself

    The full catalog is live on the Tygart Media Music Hub. Every track has its own listening page with a custom audio player, AI-generated artwork, the story behind the song, and lyrics (or composition notes for instrumentals). Pick a genre you like and judge for yourself whether the pipeline cleared the bar.

    The honest answer is: it cleared it more often than it didn’t. And knowing exactly where it didn’t is the most valuable part of the whole experiment.



  • From 200+ Episodes to a Searchable AI Brain: How We Built an Intelligence Layer for a Consulting Empire

    From 200+ Episodes to a Searchable AI Brain: How We Built an Intelligence Layer for a Consulting Empire

    The Machine Room · Under the Hood

    The Problem Nobody Talks About: 200+ Episodes of Expertise, Zero Searchability

    Here’s a scenario that plays out across every industry vertical: a consulting firm spends five years recording podcast episodes, livestreams, and training sessions. Hundreds of hours of hard-won expertise from a founder who’s been in the trenches for decades. The content exists. It’s published. People can watch it. But nobody — not the team, not the clients, not even the founder — can actually find the specific insight they need when they need it.

    That’s the situation we walked into six months ago with a client in a $250B service industry. A podcast-and-consulting operation with real authority — the kind of company where a single episode contains more actionable intelligence than most competitors’ entire content libraries. The problem wasn’t content quality. The problem was that the knowledge was trapped inside linear media formats, unsearchable, undiscoverable, and functionally invisible to the AI systems that are increasingly how people find answers.

    What We Actually Built: A Searchable AI Brain From Raw Content

    We didn’t build a chatbot. We didn’t slap a search bar on a podcast page. We built a full retrieval-augmented generation (RAG) system — an AI brain that ingests every piece of content the company produces, breaks it into semantically meaningful chunks, embeds each chunk as a high-dimensional vector, and makes the entire knowledge base queryable in natural language.

    The architecture runs entirely on Google Cloud Platform. Every transcript, every training module, every livestream recording gets processed through a pipeline that extracts metadata using Gemini, splits the content into overlapping chunks at sentence boundaries, generates 768-dimensional vector embeddings, and stores everything in a purpose-built database optimized for cosine similarity search.

    When someone asks a question — “What’s the best approach to commercial large loss sales?” or “How should adjusters handle supplement disputes?” — the system doesn’t just keyword-match. It understands the semantic meaning of the query, finds the most relevant chunks across the entire knowledge base, and synthesizes an answer grounded in the company’s own expertise. Every response cites its sources. Every answer traces back to a specific episode, timestamp, or training session.

    The Numbers: From 171 Sources to 699 in Six Months

    When we first deployed the knowledge base, it contained 171 indexed sources — primarily podcast episodes that had been transcribed and processed. That alone was transformative. The founder could suddenly search across years of conversations and pull up exactly the right insight for a client call or a new piece of content.

    But the real inflection point came when we expanded the pipeline. We added course material — structured training content from programs the company sells. Then we ingested 79 StreamYard livestream transcripts in a single batch operation, processing all of them in under two hours. The knowledge base jumped to 699 sources with over 17,400 individually searchable chunks spanning 2,800+ topics.

    Here’s the growth trajectory:

    Phase Sources Topics Content Types
    Initial Deploy 171 ~600 Podcast episodes
    Course Integration 620 2,054 + Training modules
    StreamYard Batch 699 2,863 + Livestream recordings

    Each new content type made the brain smarter — not just bigger, but more contextually rich. A query about sales objection handling might now pull from a podcast conversation, a training module, and a livestream Q&A, synthesizing perspectives that even the founder hadn’t connected.

    The Signal App: Making the Brain Usable

    A knowledge base without an interface is just a database. So we built Signal — a web application that sits on top of the RAG system and gives the team (and eventually clients) a way to interact with the intelligence layer.

    Signal isn’t ChatGPT with a custom prompt. It’s a purpose-built tool that understands the company’s domain, speaks the industry’s language, and returns answers grounded exclusively in the company’s own content. There are no hallucinations about things the company never said. There are no generic responses pulled from the open internet. Every answer comes from the proprietary knowledge base, and every answer shows you exactly where it came from.

    The interface shows source counts, topic coverage, system status, and lets users run natural language queries against the full corpus. It’s the difference between “I think Chris mentioned something about that in an episode last year” and “Here’s exactly what was said, in three different contexts, with links to the source material.”

    What’s Coming Next: The API Layer and Client Access

    Here’s where it gets interesting. The current system is internal — it serves the company’s own content creation and consulting workflows. But the next phase opens the intelligence layer to clients via API.

    Imagine you’re a restoration company paying for consulting services. Instead of waiting for your next call with the consultant, you can query the knowledge base directly. You get instant access to years of accumulated expertise — answers to your specific questions, drawn from hundreds of real-world conversations, case studies, and training materials. The consultant’s brain, available 24/7, grounded in everything they’ve ever taught.

    This isn’t theoretical. The RAG API already exists and returns structured JSON responses with relevance-scored results. The Signal app already consumes it. Extending access to clients is an infrastructure decision, not a technical one. The plumbing is built.

    And because every query and every source is tracked, the system creates a feedback loop. The company can see what clients are asking about most, identify gaps in the knowledge base, and create new content that directly addresses the highest-demand topics. The brain gets smarter because people use it.

    The Content Machine: From Knowledge Base to Publishing Pipeline

    The other unlock — and this is the part most people miss — is what happens when you combine a searchable AI brain with an automated content pipeline.

    When you can query your own knowledge base programmatically, content creation stops being a blank-page exercise. Need a blog post about commercial water damage sales techniques? Query the brain, pull the most relevant chunks from across the corpus, and use them as the foundation for a new article that’s grounded in real expertise — not generic AI filler.

    We built the publishing pipeline to go from topic to live, optimized WordPress post in a single automated workflow. The article gets written, then passes through nine optimization stages: SEO refinement, answer engine optimization for featured snippets and voice search, generative engine optimization so AI systems cite the content, structured data injection, taxonomy assignment, and internal link mapping. Every article published this way is born optimized — not retrofitted.

    The knowledge base isn’t just a reference tool. It’s the engine that feeds a content machine capable of producing authoritative, expert-sourced content at a pace that would be impossible with traditional workflows.

    The Bigger Picture: Why Every Expert Business Needs This

    This isn’t a story about one company. It’s a blueprint that applies to any business sitting on a library of expert content — law firms with years of case analysis podcasts, financial advisors with hundreds of market commentary videos, healthcare consultants with training libraries, agencies with decade-long client education archives.

    The pattern is always the same: the expertise exists, it’s been recorded, and it’s functionally invisible. The people who created it can’t search it. The people who need it can’t find it. And the AI systems that increasingly mediate discovery don’t know it exists.

    Building an AI brain changes all three dynamics simultaneously. The creator gets a searchable second brain. The audience gets instant, cited access to deep expertise. And the AI layer — the Perplexitys, the ChatGPTs, the Google AI Overviews — gets structured, authoritative content to cite and recommend.

    We’re building these systems for clients across multiple verticals now. The technology stack is proven, the pipeline is automated, and the results compound over time. If you’re sitting on a content library and wondering how to make it actually work for your business, that’s exactly the problem we solve.

    Frequently Asked Questions

    What is a RAG system and how does it differ from a regular chatbot?

    A retrieval-augmented generation (RAG) system is an AI architecture that answers questions by first searching a proprietary knowledge base for relevant information, then generating a response grounded in that specific content. Unlike a general chatbot that draws from broad training data, a RAG system only uses your content as its source of truth — eliminating hallucinations and ensuring every answer traces back to something your organization actually said or published.

    How long does it take to build an AI knowledge base from existing content?

    The initial deployment — ingesting, chunking, embedding, and indexing existing content — typically takes one to two weeks depending on volume. We processed 79 livestream transcripts in under two hours and 500+ podcast episodes in a similar timeframe. The ongoing pipeline runs automatically as new content is created, so the knowledge base grows without manual intervention.

    What types of content can be ingested into the AI brain?

    Any text-based or transcribable content works: podcast episodes, video transcripts, livestream recordings, training courses, webinar recordings, blog posts, whitepapers, case studies, email newsletters, and internal documents. Audio and video files are transcribed automatically before processing. The system handles multiple content types simultaneously and cross-references between them during queries.

    Can clients access the knowledge base directly?

    Yes — the system is built with an API layer that can be extended to external users. Clients can query the knowledge base through a web interface or via API integration into their own tools. Access controls ensure clients see only what they’re authorized to access, and every query is logged for analytics and content gap identification.

    How does this improve SEO and AI visibility?

    The knowledge base feeds an automated content pipeline that produces articles optimized for traditional search, answer engines (featured snippets, voice search), and generative AI systems (Google AI Overviews, ChatGPT, Perplexity). Because the content is grounded in real expertise rather than generic AI output, it carries the authority signals that both search engines and AI systems prioritize when selecting sources to cite.

    What does Tygart Media’s role look like in this process?

    We serve as the AI Sherpa — handling the full stack from infrastructure architecture on Google Cloud Platform through content pipeline automation and ongoing optimization. Our clients bring the expertise; we build the system that makes that expertise searchable, discoverable, and commercially productive. The technology, pipeline design, and optimization strategy are all managed by our team.