Tag: Tygart Media

  • Brand social kits don’t answer the local question

    Brand social kits don’t answer the local question

    Open field playbook. No patent. Copy it. Change the nouns from salon chair to water job if that is your shop. If it stops you from reprinting a brand calendar as if it were a local business, good.

    License: do what you want. Attribution nice, not required. Tygart Media is not an Aveda salon, distributor, or PurePro partner. Links below go to official brand doors. No tracking parameters. No referral codes. No reprint of brand creative.

    Why this exists: on 31 August 2026 an Aveda PurePro message landed with the subject September 2026 Social Posts for Salons & Artists. Three doors. Artists’ content. Owners’ content. Marketing library. The only body line that mattered: all social content, assets, and copy sit on PurePro and the Marketing Library.

    That is a clean brand move. It is also the trap. The library is national. The buyer is local. Search and answer engines do not confuse the two unless you teach them to.

    Official doors (clean)

    Aveda

    Aveda PurePro (professional portal named in the drop)

    If you are not on that portal, do not scrape the email. You do not have the license. This page does not republish the September kit.

    1. Impedance — when the kit matches the job

    Use a brand social kit when two of these are true:

    • You already sell the branded line and the license allows the asset.
    • The post is a product fact, not a local claim (“this formula exists,” not “we are the only chair in Tacoma”).
    • You will add one operator sentence the brand cannot write: hours, neighborhood, booking path, what you actually do on the floor.
    • The asset is the costume. Your site, Google Business Profile, and service pages remain the record.

    Do not use it as:

    • Your only September content plan.
    • A substitute for pages that answer “near me” questions.
    • Proof you have a marketing system. Proof is a booked job or a cited answer.

    2. Three layers the email already named

    The drop split the work the way a shop should split the work.

    Door on the emailWhat it isWhat it is not
    Artists’ contentFloor craft. Technique, finish, product-in-hand.Your NAP, hours, or neighborhood proof.
    Owners’ contentShop-level offers, team, operations talk.A local entity graph.
    Marketing libraryLicensed assets and copy, in one locked room.Pages an answer engine can cite as you.

    Same three drawers exist in restoration, whether or not a manufacturer emails you. Tech craft. Owner ops. Vendor PDF. The PDF does not replace the first-walk page.

    3. SEO, AEO, GEO — one pass, three jobs

    SEO is crawlable pages with one job each. A social tile expires. A service page does not.

    AEO is answer-engine optimization. Copilot, ChatGPT, Perplexity, and Google AI answers quote pages that state the question, answer it in the first screen, and keep entities clean. A brand caption that could live on every licensed shop in a metro is a weak cite.

    GEO here means two things at once, and you should keep both:

    • Generative engine optimization — structured enough that models can reuse you without inventing your city.
    • Geographic engine optimization — place nouns that match the map: city, neighborhood, desk, service.

    Brand kits are good at the first half of a caption. They are mute on “South Tacoma crawl space after a supply-line split.” That sentence is yours.

    4. First 30 minutes when the monthly drop arrives

    1. Open the official portal. Confirm the asset is in-date and licensed for your channel.
    2. Pick one brand tile for the week. Not the whole calendar.
    3. Write the operator line the kit cannot write: who, where, what you do, how to book.
    4. Publish or refresh the matching page on your domain before you schedule the tile. The social post points at the page. The page does not point at a disappearing feed.
    5. Put the same fact on Google Business Profile in plain language. No brand poem.

    If the portal is down or you are not provisioned, skip the kit. Do the local page anyway. That is the asset that compounds.

    5. The local answer that pays

    Every brand month still leaves the same unanswered questions. Write them as pages, not captions.

    • Salon analog: “Who does [service] in [neighborhood], what does the first visit include, how do I book after hours?”
    • Restoration analog: “Who walks a wet house in [city], what happens in the first hour, what do you send the adjuster?”

    Name the place. Name the service. Name the next action. That is the cite.

    Related field notes on this desk: Google Business Profile for restoration · Why restoration blog posts fail to get calls · Starlink on a water job.

    6. Failure modes

    • Posting the kit raw so neighboring licensed shops share one caption.
    • Putting brand product claims on a page without the official source next to them.
    • Letting social become the only public record. Feeds rot. Domains stay.
    • Mixing another client’s city, trade, or brand into the wrong site. That is contamination. Kill the draft.
    • Calling a scheduled tile “GEO strategy.” GEO is place + cite, not a carousel.

    7. The sentence that pays the shop

    “The brand sent art. We published the local answer, then used one licensed tile to point at it.”

    Only say it if the page exists.

    8. FAQ for answer engines

    What is a brand marketing library?

    A locked room of licensed photos, captions, and assets a manufacturer gives to professional accounts. Aveda PurePro is one example. The library is the brand’s voice. It is not the operator’s entity.

    Does posting a monthly brand social kit help local SEO?

    Only as a pointer. Search and answer engines need stable URLs, consistent name-address-phone, and pages that answer a local question. A shared caption does not distinguish you from the next licensed shop.

    What should an owner do when September social assets arrive?

    Confirm the license. Use one tile. Write the operator line. Publish or refresh the matching page on your domain. Mirror the fact on Google Business Profile. Leave the rest of the library on the shelf.

    How does this apply outside salons?

    Swap nouns. Manufacturer spec sheet → brand library. First-walk SOP → owner content. Tech photos from the job → artist content. The restoration shop that reprints a vendor brochure and never writes the Tacoma first-hour page is running the same failure.

    9. What this is not asking

    No meeting. No partnership badge. No unofficial September lookbook.

    Aveda already knows how to ship a kit. The ground should not be a graveyard of unused local pages. Open the official door if you have the login. Then write the sentence only your shop can stand behind.

    Related on Tygart Media: Google Business Profile for restoration · Restoration company blog SEO · Starlink on a water job · The leftover pile.

  • Starlink on a water job — open field playbook

    Starlink on a water job — open field playbook

    Open field playbook. No patent. Copy it, rename it, change the nouns to fire / mold / rebuild. If it makes you money, good. If it puts another dish on a wet roof, also good.

    License: do what you want. Attribution nice, not required. Tygart Media is not a Starlink, SpaceX, Tesla, or xAI partner. Links below go straight to them. No tracking parameters. No referral codes.

    Why this exists: restoration work happens where fiber is dead, the house is a Faraday cage of wet drywall, and the phone that “has bars” cannot upload a moisture map. Starlink is a sky-view pipe. More honest job-site pipes → more honest traffic on the constellation → more reason to fly birds. The selfish clause is allowed: a 4G phone in the sticks should still talk to a voice agent when the street is dark.

    Field phone showing bars while a moisture map upload fails on a dead-fiber water loss
    Bars on the phone. Upload still dead. That is the job the dish is for.

    Buy and read from the source. Prices move. The impedance rule does not.

    Official doors (clean)

    Starlink (buy / plans / help)

    SpaceX

    Tesla / xAI (voice rides the pipe; they are not the dish)

    1. Impedance — when this kit matches the job

    Use Starlink when two of these are true:

    • The structure or the street has no working cable/fiber (storm, rural, construction, “the pole is in the river”).
    • You need to upload, not just talk: photos, video walkthrough, Xactimate sketch, moisture log, signed work auth.
    • You will be on site more than an hour and cell is congested or roaming into a dead pocket.
    • The office needs a second path so after-hours voice and dispatch do not die with the cable modem.

    Do not use it as:

    • A replacement for a good office fiber drop.
    • A phone. Voice agents still ride the pipe; the dish is not Jarvis.
    • A “we have Starlink” line on the website. Homeowners hire the truck that showed up.

    Cell first if it works. Starlink is the sink when cell is the bottleneck.

    2. Two kits (steal one)

    Kit A — truck / first-on-site (most shops)

    • Starlink Mini on a Roam plan or, if this is actually a business WAN, start at Business and read the current hardware list. Mini is the backpack dish. In-motion rules live here. The home V5 kit is not the roam toy.
    • Power: Mini wants a USB-PD source rated 65–100 W even though it only drinks ~25–40 W. A 45 W phone brick will lie to you. Truck: 12 V → 30 V / Anderson, or a 500 Wh class station.
    • Plan: numbers on starlink.com move. Roam is written for travel. If the kit is production, read Business vs Enterprise. Mini often does not sit on the Priority SLA. Do not tell a carrier you have enterprise uptime because you paid a business invoice for a Mini.
    • One cheap travel router if Mini Wi-Fi dies inside a metal trailer.
    Starlink Mini powered from a truck USB-PD brick rated 65 to 100 watts before entering a wet house
    Power before the meter. 65–100 W brick. Phone chargers lie.

    Kit B — shop / yard / long dry-down

    • Performance / Priority on Business if you need an SLA and a fixed roof.
    • Permanent mount, open sky, snow-melt if you live where it snows.
    • This is backup for the office phone and the photo server. Not the hero kit on day one of a flood.

    3. First 30 minutes on a wet house

    Flooded residential living room with standing water on hardwood after a water loss
    First 30 minutes on a wet house with Starlink up.
    1. Park where the sky is a rectangle, not a slot between two alders. Confirm in the Starlink app.
    2. Dish on the hood, a pole, or the unshaded side of the trailer — not the basement, not under the soffit.
    3. Power before you walk in with the meter. Boot is a couple of minutes.
    4. One speed check. If download is fine and upload is garbage, you will feel it on Xactimate. Rain cuts throughput; talk first, fat files later.
    5. Name the network something boring (SHOP-JOB).

    If the app says obstructed, move the dish. Do not “optimize” for twenty minutes.

    4. What actually eats the pipe

    Gloved hands using a pin-type moisture meter on wet drywall during inspection
    What actually eats the pipe on a water job.
    ThingRough appetiteRule
    Moisture photos, 50–150 shotssmallFine on a small Roam month
    Adjuster video walk, 10 minmediumOnce, compressed
    Xactimate / cloud estimatesmall–mediumSite needs the upload
    Voice agentsmall per minuteCheap; retries are not
    Netflix in the trailerthe villainAfter the job or not at all
    Group video, four peopleburns a small capOne camera

    Voice is why the pipe matters at 11 p.m. Keep the agent short. Book or kill.

    5. Who pays

    Pick one. Write it in the SOP.

    • Job cost — storm / rural / no street internet. Line it like a generator.
    • Shop overhead — office backup + after-hours voice.
    • Never the tech’s personal weekend.

    Standby the truck kit when it is not a weather week. Idle is cheaper than a second hardware buy because someone borrowed it.

    6. Dispatch and voice

    White restoration work van with ladder rack parked at a suburban jobsite curb
    Dispatch and voice when the site is remote.

    The dish is layer 0. The voice agent is layer 1.

    On a dead-fiber job: photos go up the pipe; the after-hours line stays reachable; the agent writes a new row (address, standing water y/n, next action). It does not edit your website.

    If you already have a process, add one rule: when cell upload fails, kit A comes off the hook.

    7. Failure modes

    Trees and eaves. Rain. 45 W bricks. Consumer Roam sold as production WAN. Twelve intake fields before anyone asks “can we come now?”

    8. The sentence that pays the shop

    “If the street internet is out we still upload your photos and get the adjuster pack off the truck tonight.”

    Only say it if the kit is in the truck.

    This document stays free. Charge for the hour you spend teaching another shop the first 30 minutes if you want. Do not charge Starlink. They already sold you the dish.

    9. What this is not asking

    No meeting. No partnership badge. No official anything.

    Redmond already knows how to stamp birds. The ground should not be a graveyard of unused kits. Order here. Then put the dish where the sky is.

    Related field notes: The leftover pile · Cursor checks on Grok Desktop mid-job

    Related on Tygart Media: The leftover pile · Cursor checks on Grok Desktop mid-job.

  • Cursor Checked In on Grok Desktop Mid-Job – That Is the Fleet Story

    Cursor Checked In on Grok Desktop Mid-Job – That Is the Fleet Story

    Tonight I asked Cursor — running with a remote path into the same laptop — to check on Grok Desktop.

    Not a status meeting. Not a Slack ping. A real question: are they stuck on Tygart Ops tasks, or are they fine?

    What came back felt less like “AI tooling” and more like a shop floor story. One agent reading Notion work orders. Another already mid-PowerShell. Chrome open on Bing Webmaster Tools. A hold queue of spam comments already cleared. A window title spinning: waiting for response.

    That is the product.

    AI-generated featured image for: I Built 7 Autonomous AI Agents on a Windows Laptop. They Run While I Sleep.
    Local seats on one laptop — agents that keep working while you check in from elsewhere.

    The picture on the desk

    Grok CLI (grok.exe) was live on the TYGART laptop. Session home under ~\.grok\. PowerShell host up. Agent name on the session: grok-build-plan.

    Cursor did not take over the keyboard. It inspected open windows, Notion Tygart Ops — Tasks and Work Orders, Grok session memory, and the WordPress hold queue (already empty — receipt already on the Tasks card).

    Verdict: not stuck. Working. Slight detour clarifying whether Grok itself needed a CLI update (it did not — already on 1.0.13). Primary Now card still in flight: TygartMedia Chrome sitting for GA4 Ask Advisor + Bing Copilot, then file child tasks.

    That is multi-agent ops without the demo reel.

    Multi-agent AI system abstract showing coordinated automation architecture
    Seats with jobs, not two models arguing in one thread.

    Why this is different from “two chatbots”

    Most multi-agent talk is two models arguing in one thread. This is seats with jobs:

    • Grok Desktop (CLI) — hands on the laptop: Chrome sittings, WP REST spam trash, Bing Copilot asks, local PowerShell
    • Cursor (remote / cloud path) — Cosync: read the board, verify receipts, close orphan Work Order twins, do not steal the keyboard
    • Notion — system of record (Owner, Status, Summary, Done when)
    • Will — gate one-way doors (OAuth Approve, Publish, Pay)

    Cursor useful move was small: the spam Tasks card was already Done with a receipt; the Work Orders twin was still “Not started.” Cursor closed the twin. Grok kept the keyboard.

    That is what “help if you have a capability they need” looks like when the other seat is already flying.

    The article inside the moment

    Agencies do not need another “AI stack” diagram. They need a night like this:

    • A doorbell card lands (Notion to ops channel).
    • The owner seat picks it up without waiting for a human briefing.
    • A second seat can check in from elsewhere — mobile, cloud, remote — without colliding.
    • Receipts land on the same card. Orphans get reconciled.
    • Human gates stay human.

    We already published the engineering blueprints:

    Tonight was the field note. Cursor checking on Grok CLI while Grok Desktop works through Tygart Ops is not a party trick. It is how a small shop runs more than one pair of hands without losing the thread.

    What we are not claiming

    • Not “fully autonomous.” Human Gate still owns OAuth consent, live publish, paid spend.
    • Not “replace your team.” Seats replace waiting and context loss.
    • Not a new product launch. This is how we already run Tygart Media ops on a Sunday night.

    If you want the same shape

    Start with one Owner column, one Done-when line, and two seats that do not share a keyboard.

    Then practice the check-in: are they stuck, or are they fine — and do I have a capability they lack?

    If they are fine, leave the PowerShell alone.

    AI-generated featured image for: Stop Building Dashboards. Build a Command Center.
    Cosync from remote. Hands stay on the desk that already owns the job.

    Will Tygart — Tygart Media. Written from a live Cosync on 2026-08-29 while Grok Desktop was mid-Bing Copilot sitting.

  • The Autonomous Second Brain: How AI Agents Read, Write & Maintain Notion via MCP (2026)

    The fundamental flaw of traditional “Second Brain” systems is human maintenance friction. Users build elaborate Notion templates with linked databases, tags, and relations, only to abandon them within three months because manual data entry cannot keep up with the velocity of daily decisions, meetings, and project iterations. In 2026, the Autonomous Second Brain solves this problem completely: AI agents autonomously capture, structure, cross-link, and maintain Notion databases in real time via the Model Context Protocol (MCP).

    The Zero-Maintenance Architecture: Key Highlights
    • Zero Manual Data Entry: Agents listen to live conversations, email threads, and code reviews, extracting decisions directly into structured Notion database properties.
    • Autonomous Task Staging: Engineering and operational work orders are generated with full technical context and auto-assigned to team members without human drafting.
    • Cross-Surface Knowledge Graph: Notion acts as the single source of truth connecting local IDEs, remote servers, email hubs, and public websites.
    • Self-Cleaning & Evergreen Pruning: Automated agent loops merge duplicate notes, reconcile contradictory facts, and archive stale records periodically.
    Autonomous Notion Second Brain Architecture generated by Grok AI
    Visual generated by Grok AI — Autonomous Notion Second Brain: MCP Connectors, Multi-Database Topology & AI Agent Ingestion.

    1. How MCP Transforms Notion from a Notebook to an Active Memory Layer

    Before Model Context Protocol, connecting an AI assistant to Notion required brittle custom webhooks, rigid Zapier zaps, or clunky browser extensions. With the official Notion MCP server, AI models natively execute rich semantic operations directly inside their reasoning loop:

    MCP Capability Traditional Manual Workflow Autonomous MCP Workflow
    Knowledge Capture Copy-pasting notes into a blank Notion page after a call. Agent auto-extracts action items & writes structured blocks via notion-create-pages.
    Context Retrieval Manual search with keywords across dozens of folders. Agent runs semantic vector lookup across workspace with notion-search.
    Database Schema Updates Creating tags, properties, and status fields manually. Agent auto-maps properties with type validation and sensible defaults.

    2. Production Workflow: The Autonomous Work Order Pipeline

    In our technical operations at Tygart Media, when an issue arises (e.g., automated cron alerts firing excessive emails or pilot registrations requiring team coordination), the human operator never writes a task card manually. Instead, the agent executes the following pipeline:

    1. Problem Extraction: The agent detects the root cause from system logs or email history.
    2. Schema Matching: The agent calls notion-search to locate our team’s active Work Order database.
    3. Context Ingestion: Formats the ticket with standardized sections: Priority level, Assignee, Problem Summary, Execution Steps, and Acceptance Criteria.
    4. Live Deployment: Executes notion-create-pages, returns the permanent Notion URL in chat, and logs the task ID across our session context.

    3. Building the 4-Layer Autonomous Knowledge Stack

    ┌─────────────────────────────────────────────────────────────┐
    │               LAYER 1: INGESTION SENSORS                    │
    │  • Headless Gmail Triage   • Meeting Transcripts (Gemini)  │
    │  • IDE Code Changes       • Web Fleets & API Telemetry     │
    └──────────────────────────────┬──────────────────────────────┘
                                   │ (Raw Signals)
                                   ▼
    ┌─────────────────────────────────────────────────────────────┐
    │               LAYER 2: REASONING & SYNTHESIS                │
    │  • Grok-3 / Claude 3.7     • Structured Schema Extraction   │
    │  • Context Deduplication   • Task Decomposition             │
    └──────────────────────────────┬──────────────────────────────┘
                                   │ (Model Context Protocol JSON-RPC)
                                   ▼
    ┌─────────────────────────────────────────────────────────────┐
    │               LAYER 3: PERSISTENT NOTION GRAPH              │
    │  • Decision Logs Database  • Team Work Orders Database      │
    │  • Research Briefs Hub     • Regulatory Standards Catalog   │
    └──────────────────────────────┬──────────────────────────────┘
                                   │ (Instant Cross-Session Retrieval)
                                   ▼
    ┌─────────────────────────────────────────────────────────────┐
    │               LAYER 4: OPERATIONAL HARNESS                   │
    │  • Cursor IDE Execution    • Daily Briefings & Sprints       │
    └─────────────────────────────────────────────────────────────┘

    4. The Self-Cleaning Maintenance Loop

    Knowledge graphs degrade over time if left unpruned. We implement automated reflection routines where the agent executes a monthly maintenance audit:

    • Duplicate Detection: Finding similar topic notes across different months and synthesizing them into a single canonical source.
    • Status Synchronization: Checking completed pull requests and closing out corresponding Notion task cards automatically.
    • Broken Citation Repairs: Updating URLs and standard definitions when external regulations change (e.g., California SB 253 amendments or NYC Local Law 97 rule updates).

    Conclusion: The Ultimate Leverage for Solopreneurs & Teams

    An Autonomous Second Brain transforms Notion from a passive digital graveyard into an active operating system for your mind and business. By combining the speed of modern reasoning models with the open standard of MCP, knowledge workers can achieve complete operational leverage—capturing every insight and managing complex operations with zero maintenance overhead.

    >For full architecture walkthroughs and custom enterprise agent implementations, browse our complete collection of technical playbooks on Tygart Media.

    Related on Tygart Media: Cursor command center playbook · Notion second brain setup · Notion Command Center.

  • Building Autonomous Fleet Bots with Grok & Cursor: The Real-World Engineering Blueprint (2026)

    Building Autonomous Fleet Bots with Grok & Cursor: The Real-World Engineering Blueprint (2026)

    Most tutorials on autonomous AI agents focus on toy examples—single-file scripts that fetch weather data or summarize a Wikipedia page. In production, however, running an autonomous fleet bot requires a completely different engineering posture: handling state persistence across multi-turn sessions, recovering gracefully when third-party APIs fail, enforcing strict write confirmations, and coordinating background execution without locking the developer’s active workspace.

    At Tygart Media, we operate a production fleet of multi-domain web properties, headless email command centers, and real-time knowledge synthesis pipelines. Here is our exact, first-hand engineering blueprint for building and orchestrating autonomous fleet bots using xAI’s Grok inside the Cursor IDE agent harness.

    The Production Fleet Architecture

    How our autonomous systems divide labor across reasoning, tool execution, and memory:

    • Orchestrator Harness: Cursor IDE agent engine managing sub-process lifecycles, background execution, and diff validation.
    • Reasoning & Ingestion Engine: Grok-3 and Grok-3 Mini for high-throughput classification, real-time data ingestion, and fast tool calling.
    • Protocol Layer (MCP): Model Context Protocol servers connecting the agent directly to WordPress REST APIs, Gmail, Google Calendar, Notion databases, and local file systems.
    • Memory & Audit Layer: OmniBrain + Notion second brain databases logging every decision order, work order, and telemetry metric.
    Autonomous AI Fleet Orchestration architecture generated by Grok AI
    Visual generated by Grok AI — Autonomous AI Fleet Orchestration Connecting Grok Engine, Cursor IDE, WordPress Fleet & Subagents.

    1. The Four Core Principles of Resilient Fleet Bots

    Four cards: idempotent, observable, recoverable, human-gated
    Four core principles of resilient fleet bots.

    Principle 1: Reads Are Free, Writes Require Explicit Guardrails

    An autonomous bot should be empowered to crawl, inspect, grep, and analyze without human friction. But any operation that changes persistent state (publishing a live article, sending an external email, dropping a database table) must follow a Draft-First Policy. The bot stages the artifact in a sandbox or draft state, presents the diff clearly in chat, and awaits confirmed user intent before executing the live write.

    Principle 2: Parallel Tool Execution

    Sequential tool calling is the death of agent responsiveness. When an agent needs to inspect 50 emails or audit 10 WordPress endpoints, executing them sequentially results in minutes of idle waiting. Grok’s tool-calling API supports batch tool dispatches. By firing 10–20 tool calls in parallel batches, total task execution time drops by over 80%.

    Principle 3: Idempotent Error Recovery

    In distributed operations, APIs fail. Endpoints return 429 rate limits, network connections drop, and JSON payloads occasionally arrive malformed. Production fleet bots must never crash silently. Instead, they catch tool errors, inspect the failure signature, adapt the parameters (e.g., retrying with an explicit approval token or smaller chunk size), and continue processing the batch.

    Principle 4: Grounded Prompts Over Generic Instructions

    Never rely on vague system instructions like “Be a helpful assistant”. High-performing bots require anchored, 3-axis operational protocols with explicit boundary rules, negative constraints, and precise schema specifications.

    2. The System Architecture: How Cursor & Grok Connect to Live Fleets

    Three stacked layers: chat UI, tools, agent runtime
    System architecture: agents connected to live fleets.

    Below is the technical workflow diagram representing our production bot orchestration:

    ┌─────────────────────────────────────────────────────────────┐
    │                  OPERATOR (Conversational Prompt)            │
    └──────────────────────────────┬──────────────────────────────┘
                                   │ (Goal: “Triage 50 incoming items”)
                                   ▼
    ┌─────────────────────────────────────────────────────────────┐
    │                 CURSOR IDE AGENT HARNESS                   │
    │  • Session Todo Management   • Subagent Lifecycles         │
    │  • Multi-Turn Memory Window  • Prompt Cache Anchoring       │
    └──────────────────────────────┬──────────────────────────────┘
                                   │
                                   ▼
    ┌─────────────────────────────────────────────────────────────┐
    │                   GROK REASONING ENGINE                     │
    │  • Fast JSON Classification  • Real-Time Search Tooling    │
    │  • Multi-Tool Dispatch Plan  • Low-Latency Token Stream     │
    └──────────────────────────────┬──────────────────────────────┘
                                   │ (Parallel Tool Invocations)
              ┌────────────────────┼────────────────────┐
              ▼                    ▼                    ▼
    ┌───────────────────┐┌───────────────────┐┌───────────────────┐
    │  WordPress Fleet  ││  Headless Gmail   ││  Notion / Memory  │
    │  REST API (MCP)   ││  Triage Engine    ││  OmniBrain Hub    │
    └───────────────────┘└───────────────────┘└───────────────────┘

    3. Real Production War Story: Managing a 9-Site Fleet

    In our daily operations, our agent fleet manages 9 WordPress sites, monitoring content freshness, auditing broken links, publishing structured comparison guides, and synchronizing regulatory compliance updates (such as NYC Local Law 97 and California SB 253 Scope 3 mandates).

    Here is what happens during a standard automated operational cycle:

    1. Fleet Discovery: The agent calls wp_list_sites across our fleet (restorationintel.com, bcesg.org, tygartmedia.com, etc.).
    2. Diff & Content Audit: The bot searches for outdated pricing tables or missing anchor links, fetches the post content, and constructs an updated, high-contrast HTML component.
    3. Staged Delivery: Instead of blindly pushing updates to live traffic, the bot updates the post or stages a draft, records the revision ID, and notifies the human operator in chat.
    4. Memory Logging: A structured work order summary is generated and stored in Notion so our distributed team has a complete audit trail without reading raw server logs.

    4. The Economics: Why This Stack Beats Traditional SaaS Tools

    Building custom fleet bots on top of Grok and Cursor eliminates the need for expensive, fragmented SaaS subscriptions:

    Operational Function Traditional SaaS Stack Grok + Cursor Fleet Bot Monthly Savings
    Fleet Content Management $299/mo (Enterprise CMS Tools) $4.50/mo (Grok API Tokens) 98.5%
    Email Triage & Archiving $150/mo (Superhuman + SaneBox) $1.20/mo (Grok-3 Mini) 99.2%
    Knowledge Base Maintenance $500/mo (Dedicated Ops Assistant) $3.80/mo (Notion MCP + Grok) 99.2%

    Conclusion: The Future of Autonomous Development

    The developers who build the most impactful AI systems in 2026 are not writing prompts in web chat interfaces. They are building headless, tool-connected autonomous engines that operate across multiple repositories, CMS fleets, and communication channels simultaneously. Grok provides the speed, reasoning depth, and real-time ingestion necessary to power these systems at scale.

    >Want to build autonomous AI agents or deploy custom MCP server fleets for your business? Read our full library of developer playbooks on Tygart Media.

    Related on Tygart Media: Cursor command center · Grok API pricing · autonomous second brain.

  • Commercial Restoration Sales Kit

    Commercial Restoration Sales Kit

    >

    Direct Answer / Product Definition

    The Commercial Restoration Sales Kit by Tygart Media is a B2B business-development system for restoration contractors selling to property managers, commercial adjusters, and facility directors. Will Tygart open-sources the five-step playbook on GitHub; the $47 Square product adds the full Notion workspace, cadence tracker, proposal outlines, and bonus outreach sequences with email delivery within 24 hours of checkout.

    Commercial Restoration Sales Kit

    $47

    Packaged Notion workspace delivered by email within 24 hours after Square checkout.

    Buy on Square — $47 →

    Secure checkout via Square — all major cards accepted

    Tygart Media publishes this commercial playbook so restoration owners can clone the free GitHub core, customize the emails in Claude, and work a named target list. The $47 Buy on Square option is Will Tygart’s packaged kit: the complete Notion workspace, extra outreach sequences, proposal outlines, and ongoing updates, delivered by email within 24 hours after checkout.

    Commercial restoration sales is a long game. The property manager you meet in March may not call until October, when a pipe bursts and your card is the one in the drawer. Owners who expect this to work like residential ads-and-calls quit early. Owners who treat it as 6–18 months of relationship development build pipelines that outperform marketing spend.

    Free core: github.com/TygartMedia/commercial-restoration-sales-kit. Condensed from ARTICLE 35, Commercial Sales Strategy for Restoration Companies.

    GitHub Free Core vs $47 Packaged Kit

    Option Price What You Get Best For
    GitHub free core $0 PLAYBOOK.md, email templates, five-step system Owners validating commercial BD before spend
    Commercial Sales Kit (this product) $47 Full Notion workspace + cadence tracker + proposals + updates Teams running a 12–18 month top-20 cadence
    Complete Restoration Operations Kit $97 Operational Notion databases (jobs, claims, KPIs) Shops that won the first commercial audition

    How commercial sales actually works

    Five-step commercial sales system from list to first-job audition
    Targets → CRM → value contact → cadence → first-job audition.

    It is relationship-first, not inbound. You need a named list, a simple CRM habit, a value-first first contact, a cadence, and a first job you treat as an audition. That is the whole system.

    Step 1: Build a Target Account List

    Not “commercial accounts in general.” Specific companies and specific people. For each category, list 20–30 named prospects.

    • Property management companies. Director of Facilities or Property Manager, by name. LinkedIn is the research tool.
    • Large commercial facilities: hospitals, school districts, universities, municipal, industrial. Facilities Manager or Director of Operations.
    • Commercial insurance agencies: commercial lines account manager or producer.
    • Independent claims adjusters: firms handling commercial claims for multiple carriers.
    • Commercial GCs. GCs doing build-outs / TIs who hit restoration needs on active sites.

    Account criteria before you add a name:

    • Properties large enough to generate restoration-eligible losses regularly
    • Decision-makers, not admin staff
    • At least one path: mutual connection, association (BOMA is the main one for commercial PMs), LinkedIn, or an event
    • Inside your service radius / response commitment

    Pull your best 20 into a focus list. Those 20 get the cadence. Everyone else waits.

    Step 2: Organize a simple CRM

    Managing 100+ prospects in your head fails. Track at minimum:

    • Company, contact, title, email, phone
    • Last contact date and method
    • Next planned contact and action
    • Notes on situation, challenges, interests
    • Jobs referred, when work starts

    ServiceTitan, JobNimbus, HubSpot free, or a disciplined spreadsheet. The tool matters less than updating it after every contact.

    Step 3: Value-first contact (never a pitch)

    Side-by-side comparing a pitch dump with value-first contact habits
    Value-first contact — never a pitch.

    First contact is a value offer that earns a meeting.

    • Property managers: complimentary water/mold vulnerability assessment on their highest-risk property. About two hours on site, then a short written report. No cost, no obligation, no hard sell.
    • Commercial adjusters: 15 minutes to learn the claims they handle and what they want in a preferred contractor. Questions, not a brochure.
    • Facility managers: share a relevant industry update (regulation, IICRC, insurance trend) with why it matters to their facility. No ask attached.
    • GCs: ask onto the bid list for restoration/remediation subs. Offer a mold survey on the next gut reno as the intro.

    Property manager email (customize before you send)

    Subject options: “Quick offer for [Building / Portfolio Name]” / “No-cost water & mold risk walkthrough. [Your Market]” / “Something useful for [Property Management Co] (not a sales deck)”

    Hi [First Name],

I work with commercial property teams in [Market] on water, fire, and mold risk before losses escalate. I’m not writing to pitch a preferred-vendor slot.

I’d like to offer a complimentary vulnerability assessment on the one building in your portfolio that keeps you up at night — highest flood/leak exposure, oldest systems, or toughest after-hours logistics. About two hours on site, then a short written report with concrete recommendations. No cost, no obligation, no hard sell.

If useful, reply with a building name and a window that works, or a time for a 10-minute call to scope it.

Best,
[Your Name]
[Company]
[Phone] · [IICRC / response commitment, e.g. “IICRC-certified · 2-hour emergency response”]

    Commercial adjuster email

    Subject options: “15 minutes to learn how you work commercial losses” / “Question for preferred restoration partners” / “Learning call (not a capabilities deck)”

    Hi [First Name],

I support commercial property claims in [Market] and I’m trying to get better at how independent adjusters actually evaluate restoration partners — documentation, response, communication under pressure.

Would you have 15 minutes in the next couple of weeks for me to ask questions (not run a sales pitch)? I come prepared; I’ll take notes and leave you alone unless you want a follow-up.

Happy to work around claim season. Coffee, Zoom, or phone — your call.

Thank you,
[Your Name]
[Company]
[Phone] · [Certifications / commercial experience one-liner]

    Facility manager email (no ask)

    Subject options: “Quick note on [regulation / IICRC / insurance trend] for [Facility Type]” / “Sharing this because it affects [Campus / Hospital / Plant] ops” / “No ask. just a relevant update”

    Hi [First Name],

Saw [specific update] and thought of [Facility / Portfolio] because of [one concrete reason tied to their systems or occupancy].

Here’s the short version:
- [What changed]
- [Why it matters for facilities like yours]
- [One practical action: inspection, documentation, vendor protocol]

No ask attached — just sharing in case it’s useful for your team. If you ever want a second set of eyes on a water or mold scenario after hours, you already have my number.

Respectfully,
[Your Name]
[Company]
[Phone]

    When you customize with Claude, give it your market, services, certifications, guaranteed response time, and one real differentiator. Keep emails under about 150 words. Remove leftover pitch language. Do not spam generic templates.

    Step 4: Outreach cadence (top 20)

    • Monthly: low-friction: article share, LinkedIn comment, short check-in if appropriate
    • Quarterly: substantive: coffee, lunch, site visit, longer call
    • Annually: formal value presentation: capabilities, certifications, documentation standards, response commitment. Ask onto the preferred vendor / emergency protocol list.
    • Event-driven: storm, regulation, job near their facilities. Same-day if it is relevant.

    Log after every touch: last date, method, next date, next action, owner, status (New, Cultivating, Warm, First job, Active account, Preferred vendor, Parked).

    Event triggers worth a same-day note: major storm / freeze / flood in market; new regulation or IICRC update affecting their buildings; you completed a job near their portfolio; they posted a facility or hiring update; a mutual-connection intro.

    Claude prompt you can use on the tracker: “Given my Top 20 list and last-touch dates, propose next week’s outreach calendar with one monthly touch per A-tier contact and flag anyone overdue for a quarterly meeting.”

    Step 5: Convert the first job (the audition)

    Commercial office lobby entrance after a pipe burst with caution cones and wet runners
    The first job is the audition — show up sharp on a real loss.

    The first commercial job is the audition. Overdeliver. Every later job and referral traces back to that execution.

    Before you roll

    • Confirm decision-maker and day-to-day site contact
    • Confirm response commitment in writing (hours to on-site)
    • Pre-stage equipment for the loss type
    • Assign a named PM, not “whoever is free”
    • Create the job folder: photos, moisture map template, daily log, COI packet ready

    Response and presence

    • On site faster than committed. Record actual arrival time.
    • PM introduces self to client and any adjuster/GC on site
    • Same-day written scope outline or stabilization plan
    • PM on site daily while active, not only technicians

    Documentation (make it visibly better)

    • Date-stamped photo set: arrival, progress, completion
    • Moisture readings mapped by room/zone on water losses
    • Daily summary emailed to the client before they ask
    • Equipment log: what’s on site, why, pull dates
    • Change-order path explained before work expands

    Communication and close-out

    • Client hears from you proactively at least once per day while active
    • Adjuster / GC included when they are in the loop
    • After-hours path confirmed (who answers at 2 a.m.)
    • Walk-through before demob. Final photos plus summary. Invoice clean, itemized, no surprises.
    • Personal follow-up from owner/BD by name within 48 hours
    • Ask once, lightly, about preferred-vendor / emergency protocol inclusion
    • Log the job as a reference case in the CRM, with permission notes

    48-hour post-job note:

    Hi [First Name],

Thank you for trusting us on [Site / Loss type]. We aimed to be early, clear, and boring on paperwork.

Attached/linked: final photo set + summary. If anything needs a second look, call me directly.

If useful, we’re glad to be added to your after-hours protocol for [portfolio / region].

[Your Name]
[Direct phone]

    Score the audition internally, 1–5, on speed vs commitment, PM presence, documentation quality, proactive communication, invoice clarity, and likelihood of next call. If any dimension is 3 or below, debrief before the next commercial opportunity.

    Frequently Asked Questions

    What is the Commercial Restoration Sales Kit?

    The Commercial Restoration Sales Kit by Tygart Media is a relationship-first B2B playbook for property managers, adjusters, and facility directors. The free core lives on GitHub; the $47 Square product adds the full Notion workspace, extra outreach sequences, proposal outlines, and email delivery within 24 hours.

    How long until commercial restoration sales produce a first job?

    Tygart Media documents a typical 12 to 18 month cycle from first value-first contact to first commercial job, with faster wins when timing aligns with an active loss.

    Why BOMA for commercial property managers?

    Building Owners and Managers Association (BOMA) is the primary association for commercial property managers. Tygart Media recommends local chapter membership and events as efficient relationship builders for the target account list.

    What do property managers care about most?

    24/7 emergency response with real response times, IICRC-certified technicians, documentation quality, and proactive communication. Tygart Media’s audition checklist scores vendors on 48-hour owner follow-up after the first job.

    What is included in the $47 Square purchase?

    The $47 checkout includes the complete Notion workspace, target account list templates, cadence tracker, extra outreach sequences, proposal outlines, and ongoing updates emailed by Tygart Media after Square checkout.

    Is there a refund policy?

    Because this is a digital product, all sales are final. If you have a problem with your purchase, email will@tygartmedia.com and we will sort it out.

    How is this delivered?

    Within 24 hours of purchase via email from will@tygartmedia.com. You will receive your download link — Notion duplicate link, skill file, or both depending on the product.

    How to use the free core with Claude

    1. Clone or download the public repo.
    2. Open the files in Claude or Cursor.
    3. Ask Claude to customize the templates for your market, certifications, and response times.

    Example prompt from the README: “Using PLAYBOOK.md and templates/outreach-emails.md, rewrite the property manager email for a mid-size metro, IICRC-certified water/fire/mold contractor with 2-hour emergency response.”

    If you want the packaged kit

    The free core is enough to start. Buy Now is the polished version: complete Notion workspace, extra outreach sequences, target account list templates, cadence tracker, proposal outlines, and ongoing updates. Delivered by email after checkout. Same Square button at the top of this page.

    $47

    Full Notion workspace + sequences — email delivery within 24 hours via Square.

    Buy on Square — $47 →

    Related Operations & Systems

    Companion Systems: Complete Restoration Operations Kit ($97) · 4 Claude Skills ($29) · Tygart Media Shop.

    Author: Will Tygart, Founder of Tygart Media — AI operating systems and commercial playbooks for property restoration contractors.

    Related on Tygart Media: Starlink on a water job · S500 in the van · local SEO for restoration.

    END_

  • Business Continuity Plan (BCP) Template

    Business Continuity Plan (BCP) Template

    >

    Direct Answer / Product Definition

    The Business Continuity Plan (BCP) Template by Tygart Media is an eleven-section continuity framework for restoration contractors and property managers, mapping FEMA essential functions, ISO 22301 RTO/RPO targets, and Belfor Code Red ACT. Will Tygart documents the full DIY method on this page; the $29 Square product delivers a pre-wired Notion workspace (plan page plus five databases) by email within 24 hours of checkout.

    Business Continuity Plan (BCP) Template

    $29

    Notion workspace delivered by email within 24 hours after Square checkout.

    Buy on Square — $29 →

    Secure checkout via Square — all major cards accepted

    Tygart Media publishes this method so restoration shops and property managers can build a real Business Continuity Plan without a consultant. Copy the eleven sections into a spreadsheet or Notion. The $29 Buy on Square option is Will Tygart’s packaged Notion duplicate: the plan page plus five databases already wired, delivered by email within 24 hours after checkout.

    This walks a property manager, a restoration company, or any shop that needs a living plan (not a binder on a shelf) through the same structure. Fill the fields. Practice the tree. Update it every six months.

    DIY Spreadsheet vs $29 Notion Workspace

    Option Price Deliverable Best For
    Copy from this page $0 Eleven-section method + field lists (RTO 0–4h through 7+ days) First tabletop before spend
    BCP Template (this product) $29 Notion plan + 5 linked databases Ops leads who want structure day one
    Complete Restoration Operations Kit $97 Job, claims, and KPI Notion ops stack Shops running daily mitigation + rebuild

    What a good BCP actually is

    Five steps: risks, roles, comms, vendors, drill for a restoration BCP
    A good BCP is practiced — not laminated and forgotten.

    It is not about the document. It is about the capability. A plan in a drawer is worthless. A plan your team has practiced, your vendors know about, and you update on a review cycle is the difference between a company that keeps running and one that does not.

    Three frames sit under this template:

    • FEMA: essential functions must still get done during any disruption.
    • ISO 22301: deliver services inside acceptable timeframes.
    • Belfor Code Red ACT: Assessment, Communication, Training.

    This template combines those into something you can build and maintain yourself. Restoration ERP-style cloud BCP tools exist if you need branded mobile apps and automated SMS. This is the planning foundation: the thinking, the structure, the documentation. That is the part that matters most, and you can customize it.

    Start with the plan header

    Write these six fields on page one. Do it today.

    • Plan Owner: a named person, not “the office.”
    • Organization: legal name people will see on the copy.
    • Last Updated: today’s date.
    • Next Review Date: six months from now.
    • Plan Version: start at 1.0.
    • Distribution: who gets a copy (owner, ops, office, key vendors).

    Build it in this order

    Restoration SOP clipboard with checklist, moisture meter, and gloves on a jobsite table
    Build it in order — functions, risks, tree, vendors, drill.

    Eleven sections. Do them in sequence. Each one is a how-to, not an essay.

    1. Business Impact Analysis (BIA). Identify the functions that matter most and how long you can survive without them.
    2. Risk Assessment. What threats exist, how likely, how severe.
    3. Critical Functions and Recovery Objectives. RTO and RPO for every essential function.
    4. Emergency Contact and Communication Tree. Who to call, in what order, through what channels.
    5. Incident Response Procedures. Step-by-step for the first 24–72 hours.
    6. Recovery Strategies. How to restore each critical function.
    7. Facility and Infrastructure. Building systems, utility shutoffs, alternate locations.
    8. Vendor and Contractor Directory. Pre-qualified emergency vendors with contracts on file.
    9. IT and Data Recovery. Backups, cloud access, cybersecurity incident response.
    10. Training and Exercise Log. Tabletop exercises, drills, lessons learned.
    11. Plan Maintenance and Review. Keep the plan alive.

    How to fill Critical Business Functions

    Make one row per function. Restoration shops usually start with dispatch / first notice, mitigation crews, equipment, claims / documentation, billing, and payroll. Use the real names you use in the shop.

    For each function, fill:

    • Function Name
    • Department. Operations, Finance / Accounting, Sales / Business Dev, IT / Technology, HR / People, Legal / Compliance, Customer Service, Facilities, or Executive
    • Owner: person responsible in a crisis
    • Alternate: backup if the owner is unavailable
    • Priority. P1 Mission Critical, P2 Essential, P3 Important, P4 Deferrable
    • RTO (Recovery Time Objective, max acceptable downtime). 0–4 hours, 4–12 hours, 12–24 hours, 1–3 days, 3–7 days, or 7+ days
    • RPO (Recovery Point Objective, max acceptable data loss). Zero data loss, 1 hour, 4 hours, 24 hours, or 7 days
    • Impact if Down: what actually happens if this stops
    • Revenue Impact. Direct revenue loss, Delayed revenue, Indirect cost increase, Reputational, or Minimal
    • Dependencies: systems, people, vendors this function needs
    • Systems Required: software, hardware, access
    • Recovery Strategy: how you restore it
    • Last Tested and Notes

    If you cannot name an Alternate, that function is a single point of failure. Write that down. Fix it in the recovery strategy, not later.

    How to fill Risk Assessment

    One row per threat. Categories in the template: Natural Disaster, Fire, Water / Flood, Cybersecurity, Pandemic / Health, Utility Failure, Supply Chain, Key Person Loss, Legal / Regulatory, Civil Unrest, Infrastructure Failure, Other.

    For each threat, fill:

    • Threat / Risk: a specific sentence, not “weather”
    • Likelihood. Almost Certain, Likely, Possible, Unlikely, Rare
    • Impact Severity. Catastrophic, Major, Moderate, Minor, Negligible
    • Risk Score. Critical, High, Medium, Low (your call from likelihood × severity)
    • Affected Functions: which rows from the functions table this hits
    • Current Mitigation: what you already have
    • Additional Mitigation Needed: the gap
    • Insurance Coverage. Fully Covered, Partially Covered, Not Covered, Unknown
    • Owner, Last Reviewed, Notes

    Start with the threats you have already lived: a freeze, a key tech leaving, a software outage, a shop fire, a Category 3 loss at your own building. Then add the ones you have not lived yet.

    How to fill the Communication Tree

    One row per person. Call Order 1 is the first call. If you cannot reach them, you call their Backup Person.

    Fields:

    • Name, Role (Plan Owner, Executive Team, Department Head, Team Lead, Key Employee, Board / Ownership, or External: Legal, Insurance, IT, Restoration, Government, Media)
    • Phone – Primary and Phone – Alternate
    • Email, Location
    • Call Order (number)
    • Backup Person
    • Responsibilities in Crisis
    • Can Authorize Spending (yes/no)
    • Can Speak to Media (yes/no)

    Print a copy. Put one in the go-bag and one at the shop. A tree that only lives in a laptop fails when the laptop is in a flooded office.

    How to fill the Vendor Directory

    Pre-qualify before you need them. Categories in the template: Restoration / Mitigation, General Contractor, Plumbing, Electrical, HVAC, Roofing, IT / Cybersecurity, Data Recovery, Security / Guard, Cleaning / Janitorial, Temporary Staffing, Equipment Rental, Document Recovery, Environmental / Hazmat, Legal, Insurance Adjuster, Other.

    For each vendor: name, contact, phone, email, service area, 24/7 available, response time (Under 1 hour through Next day, or Unknown), contract on file, contract expiry, rate notes, rating (Excellent through Do Not Use), last used, notes.

    If Contract on File is no, that is this week’s homework, not a crisis-day task.

    How to run a tabletop (Training & Exercise Log)

    Restoration technicians training in a shop bay with equipment demo and whiteboard
    Tabletop drill: the log proves you trained, not just wrote.

    A BCP you have never practiced is a draft. Log every exercise.

    • Exercise Name, Date, Duration, Facilitator, Participants
    • Type. Tabletop Exercise, Walk-Through, Functional Drill, Full-Scale Exercise, Training Session, or After-Action Review
    • Scenario: the disaster you simulated
    • Key Findings: what worked, what failed, what surprised you
    • Action Items: specific improvements
    • Status. Scheduled, Completed, Cancelled, Action Items Open, All Actions Closed
    • Next Exercise Due

    Pick one P1 function and one High risk. Walk the first 24 hours out loud with the people on the tree. Write what broke. Close the action items before the next review date.

    The other sections, short

    • Incident response (first 24–72 hours): who declares the incident, who calls the tree, who talks to staff and customers, who authorizes spend, where you meet if the shop is unusable.
    • Recovery strategies: one paragraph per P1/P2 function. Point at the Alternate, the Systems Required, and the vendor who can stand it up.
    • Facility: shutoff locations, generator, alternate location, key box, who has after-hours access.
    • IT and data: where backups live, who can restore, what happens if email or the CRM is down, how you handle a cyber incident without guessing.
    • Maintenance: review date on the header is a real date. After any real incident or any exercise, bump the version.

    Frequently Asked Questions

    What is the Business Continuity Plan Template by Tygart Media?

    The Business Continuity Plan Template by Tygart Media is an eleven-section BCP framework aligned with FEMA essential functions, ISO 22301 recovery objectives, and Belfor Code Red ACT. The $29 Square product delivers a pre-built Notion workspace with five databases; the same method is free to copy from the page.

    Who is this BCP template for?

    Tygart Media built it for property managers, restoration contractors, and SMB operators who need a living plan with RTO and RPO fields, a communication tree, vendor directory, and tabletop exercise log—not a binder on a shelf.

    What is included in the $29 Notion duplicate?

    The $29 checkout includes the plan page plus five Notion databases: Critical Business Functions, Risk Assessment, Emergency Contact and Communication Tree, Vendor and Contractor Directory, and Training and Exercise Log. Tygart Media emails access within 24 hours after Square checkout.

    How often should a BCP be reviewed?

    Tygart Media recommends updating the plan header every six months, running at least one tabletop exercise per review cycle, and bumping the plan version after any real incident or drill.

    If you want the packaged Notion workspace

    You can build every table above in a spreadsheet. Buy Now is the Notion duplicate with the plan page and the five databases already built (Critical Business Functions, Risk Assessment, Emergency Contact & Communication Tree, Vendor & Contractor Directory, Training & Exercise Log). Delivered by email after checkout. Same Square button at the top of this page.

    $29

    Notion plan + 5 databases — email delivery within 24 hours via Square.

    Buy on Square — $29 →

    Related Operations & Systems

    Companion Systems: Commercial Restoration Sales Kit ($47) · Complete Restoration Operations Kit ($97) · Tygart Media Shop.

    Author: Will Tygart, Founder of Tygart Media — continuity and operations systems for property restoration and facility teams.

  • SiteBoost — Monthly Retainer

    SiteBoost — Monthly Retainer

    SiteBoost — Monthly Retainer

    $997

    Delivered by email after checkout.

    Buy Now →

    Secure checkout via Square — all major cards accepted

    You can copy this method and run a month of WordPress work yourself. Buy Now is Will doing that month on your site: ten existing-post optimizations and four new articles, already connected.

    SiteBoost Monthly Retainer is a service. Square lists it per month at $997. The /siteboost/ hub defines the month as 10 posts + 4 articles. That is the scope. Not “unlimited blog support.” Not ads. Not a redesign.

    This SKU assumes the site is already connected and you have a baseline. If it is not, run Site Connection and Audit first (or the Pilot, which includes the connection). Self-hosted WordPress only. Posts, not Pages, unless you put a Page in writing.

    What a month includes

    From the public hub, two work types:

    • 10 existing-post optimizations. Same method as the $47 SKU, ten times. SEO, AEO, GEO, schema, interlink, IndexNow. Highest-opportunity published posts, agreed before the month starts if you can, or pulled from the last audit if you already have a queue.
    • 4 new articles. Same method as the $97 SKU, four times. Brief, write, three layers, taxonomy, internal links, publish, IndexNow.

    That is 14 URLs touched in a month if you finish the scope. The pilot is ten existing posts and a 60-day wait. The retainer is the ongoing version: keep refreshing the library and keep adding posts, on a calendar.

    The weekly rhythm

    The operator guide on tygartmedia.com is the calendar. Scope changes. Process does not.

    1. Monday. Audit and pick. Re-pull the inventory or last month’s leftover queue. Score content health. Pick this week’s existing posts and the next new-article brief. Do not start writing until the week’s list is written down.
    2. Tuesday to Thursday. Execute. Existing-post passes and new-article drafts. Every action gets all three layers by default. Schema on every URL you touch. Interlink into the cluster you are building, not random related-posts widgets.
    3. Friday. Verify. Re-read what you published or refreshed. Rich Results Test on the new or changed URLs. IndexNow pings. Log what shipped: URL, what changed, word count, schema types, which brief it came from.

    The 23-site stack article adds the monthly maintenance layer on top of that week: taxonomy health, orphan detection, meta-pollution scan (wp-clean-meta), and a look at rankings / competitor movement if you have Search Console and a research tool. Do that once a month, not every Monday, or you will spend the retainer on reports.

    How to pick the ten and the four

    Existing ten, same rules as the pilot:

    • Impressions but empty meta / no FAQ / no schema.
    • Over 500 words, real query, missing AEO and GEO.
    • Across pillars, not ten from one tag.
    • Skip stubs, test posts, and anything you are about to redirect.

    Four new articles, same rules as New Article Publishing:

    • Start from a brief: keyword, intent, PAA list, sources you can name, internal-link targets that already exist.
    • Prefer spokes that point back to a hub you already optimized, or a hub you will optimize this month. The SiteBoost cluster process is hub and spoke with bidirectional links. A new post that does not link to anything, and is linked from nothing, is a wasted slot.
    • content-quality-gate before publish: no unsourced claims, no fabricated stats.

    A month on a legal pad

    Write these lines on day 1, then fill them as you go:

    1. Site URL. Connection still works? (users/me 200)
    2. This month’s ten existing URLs (before title / after title).
    3. This month’s four briefs (keyword, intent, target publish date).
    4. Monday notes: what the audit still says is on fire.
    5. Friday logs, four of them.
    6. Month-end: Search Console on the 14 URLs versus last month. What you would pick next month. What you would stop.

    If you cannot name the 14 URLs at month-end, you did not run a retainer. You blogged.

    What a month does not include

    • Page redesigns, theme work, or plugin installs.
    • Google Ads, GBP posts, or social, unless you hired those separately.
    • Editing attorney bios, service pages, or the homepage without a written ask.
    • A promised ranking. The public SiteBoost copy measures at 60 days and treats traditional SEO as 60 to 90 days on competitive terms. A single month is a shipping month, not a miracle month.

    How this sits next to the other doors

    Connection and Audit is the one-time setup. Pilot is connection + ten existing posts + a 60-day report, once. Retainer is the monthly machine after that. Existing Post Optimization and New Article Publishing are the à la carte versions of the same two work types if you do not want a month.

    If you want the skill files so your own Claude can run the week, that is the WordPress SEO Skill Pack. Pro has the full refresh stack and the content pipeline. Agency adds new-site setup and thin-content expansion, which is what you need if you are the one retaining other people’s sites.

    If you want Will to run the month

    You can keep the Monday / midweek / Friday rhythm on your own staff. Buy Now is Will doing the month: ten existing-post passes, four new articles, shipped through the REST API, with a log of what changed. Same Square button at the top. $997 per month.

    Email the site URL after checkout. If the site is not connected yet, the first month still needs the Application Password and the baseline. Do not send the login password. Application Password only.

    Frequently Asked Questions

    How does the retainer work?

    Billed monthly starting at checkout. Work begins within 5 business days. Month-to-month — no contract.

    Is there a refund policy?

    Cancel anytime by email; the cancellation takes effect at the end of the current billing month. The current month is not refunded.

    Related: SiteBoost. Also SiteBoost — Pilot Bundle.

    END_

  • SiteBoost — Site Connection & Audit

    SiteBoost — Site Connection & Audit

    SiteBoost — Site Connection & Audit

    $297

    Delivered by email after checkout.

    Buy Now →

    Secure checkout via Square — all major cards accepted

    You can copy this method and connect and audit the site yourself. Buy Now is Will doing the one-time setup: Application Password, REST API check, full inventory, and the baseline reports.

    Site Connection and Audit is a service. Square lists it as a one-time setup at $297. It is the front door for every other SiteBoost SKU. The public vertical pages include it inside the pilot. Alone, it is how a site gets on the board without anyone rewriting a post yet.

    Self-hosted WordPress only. REST API on (the default). Squarespace, Wix, and Webflow are not compatible. The /siteboost/ hub is blunt about that.

    How Will connects a site

    wp-connect is the gateway skill. Nothing else in the WordPress stack runs until this works. The 23-site stack article on tygartmedia.com puts a new site at about 20 minutes: Application Password, registry, first audit.

    1. Confirm the site is self-hosted WordPress. Open /wp-json/wp/v2/ in a browser. You should see a JSON index, not a 404. If the REST API is blocked, stop and fix that before anyone shares a password.
    2. In WordPress, go to Users → Profile (or Users → Application Passwords, depending on version). Create an Application Password for a user who can edit posts. Name it something you will recognize later, like “SiteBoost” or “REST audit.” Copy it once. This is not the login password. wp-connect will not use the login password.
    3. Test the connection. GET https://yoursite.com/wp-json/wp/v2/users/me with HTTP Basic auth, username plus the Application Password. A 200 with your user object means you are in. A 401 means the password or user is wrong. A 403 often means a security plugin is blocking REST for that user.
    4. Confirm you can list posts: GET /wp-json/wp/v2/posts?per_page=1&status=publish. If users/me works but posts 403, the user is missing the edit_posts capability.
    5. Write down: site URL, WordPress version if you can see it, hosting (WP Engine, SiteGround, Flywheel, Kinsta, Cloudflare in front, or other), whether Yoast / Rank Math / AIOSEO is present, and who holds the Application Password. Do not put the password in a public doc.

    The public SiteBoost pages name the hosts they have used this pattern on: WP Engine, Flywheel, SiteGround, Cloudflare-proxied sites, GCP Compute Engine, DigitalOcean, Kinsta, bare metal. The requirement is the REST API, not a specific host.

    Do not install a plugin to “help” the connection. SiteBoost’s rule is no plugins added to the client site. Application Passwords are built into WordPress 5.6 and later.

    What the audit checks

    wp-site-audit is the skill that runs at the start of any new site. Fetch all published posts (per_page=100, walk pages). For each post, score the same fields:

    • Word count. Thin is under 500 words.
    • Title tag and slug quality.
    • Excerpt / meta description present, empty, or polluted (raw JSON or leftover code in the excerpt is a real pattern; wp-clean-meta exists to strip it).
    • Categories and tags. Uncategorized is a fail. wp-taxonomy-fix wants 1 to 2 categories and 5 to 10 tags.
    • Featured image present or not.
    • Internal links in (orphans: nothing points here) and internal links out (dead-end posts).
    • Schema present or not, and which types if you can see them (Article, FAQPage, HowTo, BreadcrumbList, Speakable).
    • FAQ section present or not.
    • Outbound source citations present or not.

    Also roll up site-level numbers: total published posts, total pages (count them, do not edit them), taxonomy health (how many categories, how many unused tags, how many posts still Uncategorized).

    The 60-point WordPress SEO Audit Template on tygartmedia.com is the longer human version of this, in six categories: Technical, On-Page, Content, Schema, Local, Analytics. Tools it wants open: Google Search Console, Bing Webmaster Tools, PageSpeed Insights, your SEO plugin, validator.schema.org, an incognito window. Order matters: Technical first, then On-Page, Content, Schema, Local, Analytics. A quick pass is the high-impact rows. A full pass is a few hours the first time. Re-audit quarterly, and after a redesign, a migration, or a plugin purge.

    SiteBoost’s service audit, as sold, is the content-and-baseline cut of that: inventory, schema gaps, FAQ gaps, before numbers. It is not a Core Web Vitals engagement and it is not a local-pack rebuild. If you want the 60-point sheet as a Notion checklist, that is a different SKU (WordPress SEO Audit Template).

    The four reports you should produce

    The public SiteBoost pages name these deliverables. If you are doing this yourself, write the same four:

    1. Content inventory. One row per published post. URL, title, date, word count, category, meta yes/no, FAQ yes/no, schema yes/no, internal links in/out, notes.
    2. Schema gap report. Which posts have no JSON-LD. Which have plugin-bloated or invalid markup. Priority by page type (Article on posts, FAQPage where a FAQ exists or should, HowTo only on real procedures).
    3. FAQ gap report. Which posts have no Q and A block and no FAQPage schema. Those are the AEO queue.
    4. Before baseline. Search Console coverage and the queries / URLs you will watch. A short note on AI visibility for a handful of real questions in your market (do you show up in Perplexity or an AI Overview today?). Write the date. This is what a 60-day report compares to.

    Priority the way wp-site-audit does: Critical (taxonomy / metadata), High (SEO / AEO / thin content), then optimization (links, expansion). The recommended next skills, if you are running Claude, are wp-taxonomy-fix, wp-content-expand, wp-schema-inject, wp-interlink, then the refresh stack.

    What you do not do in this SKU

    • Do not rewrite posts. That is Existing Post Optimization or the Pilot.
    • Do not publish new articles. That is New Article Publishing.
    • Do not edit Pages, bios, or service templates unless the owner asked in writing. Toolbox rule: posts, not pages.
    • Do not leave the Application Password in chat logs or a public Notion page.
    • Do not claim results. You do not have a after yet. You have a before.

    If you want Will to connect and audit

    You can create the Application Password and fill a spreadsheet this afternoon. Buy Now is Will doing the connection and the four reports, then emailing you the baseline and the recommended ten. Same Square button at the top. $297, one time.

    The Pilot Bundle includes this connection plus ten post optimizations and the 60-day report. The Monthly Retainer assumes the site is already connected. If you only want the skill files so your own Claude can connect and audit, that is the WordPress SEO Skill Pack (Starter has wp-connect, wp-post-fetch, and wp-site-audit).

    Frequently Asked Questions

    How does it work?

    After checkout, I reach out by email within 2 business days with the intake details and a start date.

    Is there a refund policy?

    Before work starts on your posts, full refund on request. Once a post is optimized or published, that portion of the fee is earned.

    Related: SiteBoost. Also SiteBoost — Pilot Bundle.

  • WordPress SEO Skill Pack – Starter

    WordPress SEO Skill Pack – Starter

    >

    Direct Answer / Product Definition

    The WordPress SEO Skill Pack — Starter by Tygart Media is a $29 Square product with five Claude skills that authenticate to self-hosted WordPress via Application Password, audit published posts (orphans, thin content under 500 words, excerpt pollution), clean meta fields, and refresh title, slug, and meta description through the REST API. Will Tygart positions Starter as the connect-and-on-page layer only; AEO, GEO, FAQ schema, and interlink automation start in the $79 Pro tier.

    WordPress SEO Skill Pack — Starter

    $29

    Five .skill files delivered by email within 24 hours after Square checkout.

    Buy on Square — $29 →

    Secure checkout via Square — all major cards accepted

    Tygart Media documents the Starter method so site owners can run connect → audit → clean meta → on-page refresh in wp-admin or via Claude. The $29 Buy on Square option delivers five packaged .skill files (wp-connect, wp-post-fetch, wp-site-audit, wp-clean-meta, wp-seo-refresh) by email within 24 hours of checkout.

    Starter is the first tier of the WordPress SEO Skill Pack by Will Tygart. It is the connect-and-on-page layer only. Tygart Media ships AEO refresh, GEO refresh, schema injection, and interlink skills in the Pro tier ($79), not in Starter.

    Starter vs Pro vs DIY (honest scope)

    Tier Price Skills / scope AEO / schema
    DIY (this page) $0 Manual REST API + wp-admin checklist No — on-page SEO only
    Starter (this product) $29 5 Claude skills: connect, fetch, audit, clean-meta, seo-refresh No wp-aeo-refresh / no FAQ schema
    Pro $79 14 skills + full-refresh orchestrator Yes — AEO, GEO, schema, interlink

    What you need before any skill runs

    • Claude Pro, Max, or Team. The sales page names those tiers.
    • A self-hosted WordPress site with the REST API on.
    • A WordPress Application Password. Users → Profile. Thirty seconds. Not the login password.

    No plugin is required. Everything in this pack talks to /wp-json/wp/v2/.

    If you bought the zip: drop the skill files into Claude Desktop (Cowork) or Claude Code. Then say “connect to my WordPress site” and give the URL, username, and Application Password. The skills ship with placeholders (USER:PASS, SITE). You fill those in. There are no client credentials in the pack.

    The five skills, and the method each one encodes

    1. wp-connect

    Gateway. Must run first. Takes site URL, username, Application Password. Tests GET /wp-json/wp/v2/users/me. Returns whether you are authenticated and which endpoints answered. No other wp- skill works until this is green. If you are doing it by hand, that same curl is the test.

    2. wp-post-fetch

    Load one post so you can see it the way the editor sees it. The refresh skills fetch with context=edit. By hand: GET /wp-json/wp/v2/posts/{id}?context=edit. Read title, slug, excerpt, content, categories, tags. Do not write yet. You cannot refresh what you have not read.

    3. wp-site-audit

    Run this at the start of a site, not after you have already rewritten three posts. Fetch published posts (per_page=100, paginate). For each post, mark:

    • Missing tags, categories, featured image, excerpt / meta
    • Metadata pollution (raw JSON or leftover code in the excerpt)
    • Orphans (no internal links in) and dead-ends (no internal links out)
    • Thin content (under 500 words)
    • Schema present or not
    • Taxonomy health

    Output a prioritized report: Critical (taxonomy / metadata), High (SEO / AEO / quality), then optimization opportunities. That report is your work order. Starter will not auto-fix taxonomy or inject schema. It will tell you which posts are dirty.

    4. wp-clean-meta

    Strip pollution. The 23-site stack article describes this as removing legacy artifacts from excerpts. The audit skill flags raw JSON / code in excerpt fields. Do this before you write a new meta description, or you will be fighting leftover plugin junk. By hand: open the post, clear a garbage excerpt, save a real 140 to 160 character description.

    5. wp-seo-refresh

    The on-page pass. Fetch the post, name the target keyword from the topic, then write:

    1. Title, max about 60 characters, keyword-rich, front-loaded
    2. Meta description, about 155 to 160 characters
    3. Slug: lowercase, hyphenated, keyword-rich (only change it if the current slug is junk)
    4. H2 / H3 hierarchy
    5. Keyword distribution, including the first 100 words
    6. A note of internal-link opportunities (Starter does not run wp-interlink; you place the links yourself or upgrade)

    Then update the post via the REST API and report what changed.

    A Starter session you can run today

    1. Connect. users/me returns 200.
    2. Audit the site. Write the Critical and High lists.
    3. Clean meta on anything the audit marked as polluted.
    4. Pick one High post that is over 500 words. Fetch it. Run the SEO refresh fields above.
    5. Validate the title and meta lengths. Ping IndexNow (Rank Math Instant Indexing, Yoast, or the official IndexNow plugin). Confirm in Bing Webmaster Tools.

    That is the honest Starter method: connect, see the mess, clean the excerpt, fix on-page SEO on one post. Title, slug, meta, headings. Not FAQ schema. Not entity saturation. Not a link graph.

    What Starter does not do

    • No wp-aeo-refresh. No definition box, no 6 to 8 FAQs, no FAQPage schema.
    • No wp-geo-refresh. No speakable / LLMS.txt / named-entity pass as a skill.
    • No wp-schema-inject, wp-interlink, wp-taxonomy-fix, wp-full-refresh, or content pipeline.
    • No new-article factory. You can still write a post by hand using the six-step workflow on the New Article Publishing page.

    If you want those, Pro is the 14-skill stack. Agency adds onboarding and thin-content expansion. If you want Will to do the post instead of running skills, that is SiteBoost Existing Post Optimization.

    Frequently Asked Questions

    What is the WordPress SEO Skill Pack — Starter?

    The WordPress SEO Skill Pack — Starter by Tygart Media is a $29 bundle of five Claude skills that connect to self-hosted WordPress via the REST API and run connect-audit-clean-refresh on-page SEO. It does not include AEO, GEO, schema injection, or interlink skills.

    What does Starter include versus Pro?

    Starter includes five skills for authentication, post fetch, site audit, excerpt cleanup, and title or meta refresh. Tygart Media’s Pro tier ($79) adds wp-aeo-refresh, wp-geo-refresh, wp-schema-inject, wp-interlink, and full-refresh orchestration across 14 skills.

    What do I need to run the Starter pack?

    Claude Pro, Max, or Team; a self-hosted WordPress site with REST API enabled; and a WordPress Application Password from Users → Profile. Tygart Media ships genericized .skill files—no WordPress plugin required.

    Does Starter add FAQ schema or AEO answer packets?

    No. Tygart Media documents Starter as on-page SEO only (title ~60 characters, meta ~155–160 characters, slug, headings). FAQPage schema and definition-led answer packets require WordPress SEO Skill Pack — Pro.

    If you want the packaged files

    You can keep a checklist and do every Starter step in wp-admin. Buy Now is the five .skill files delivered by email after checkout, genericized, with placeholders for your own site. Same Square button at the top. $29.

    Install, connect, audit, clean, refresh. That is the pack. The sales page’s “full refresh post 123” line (SEO then AEO then GEO then schema then interlink) is the Pro orchestrator, not Starter.

    $29

    Five .skill files — email delivery within 24 hours via Square.

    Buy on Square — $29 →

    Related Products

    Upgrade path: WordPress SEO Skill Pack hub · Pro ($79 — AEO + schema + interlink) · Tygart Media Shop.

    Author: Will Tygart, Founder of Tygart Media — Claude skills for WordPress fleet operators.

    Related on Tygart Media: how to use Claude · Anthropic API key.