Tag: copilot

  • One Question Per Page: How Generative AI Actually Ingests, Ranks, and Cites Content (Full Video Walkthrough & Analysis)

    Executive Video Masterclass
    6 Chapters // 29m 02s // Studio Audio Mastered

    One Question, One Page, One Answer: The Architecture of AI Citations

    In this 29-minute masterclass, Will Tygart walks through live screen recordings and telemetry dashboards to show how Microsoft Copilot, Perplexity, and Claude harvest web content. Below, the session has been pruned of opening setup chatter, mastered with studio vocal leveling, and segmented into six standalone video chapters with exact timestamps, native playback, and core takeaways.

    Presenter: Will Tygart
    •
    Production: Tygart Media
    •
    Audio Mastering: -16 LUFS Studio Vocal Polish
    •
    Focus: Generative Engine Optimization (GEO)

    Mastered Video Chapters & Detailed Walkthroughs

    Section 1: How Frontier Answer Engines Ingest Knowledge Nodes

    ⏱ 10:15 – 15:45 (5m 30s)

    Behind-the-scenes mechanics of how Microsoft Copilot and Perplexity bots parse web pages. Answer engines don’t browse like consumers—they harvest functional specifications, entity models, and executable schemas to compile synthesized briefings.

    Key Takeaways:

    • Frontier answer engines ingest structured data blocks to construct immediate, synthesized answers for users.
    • Clean entity modeling and tabular layouts reduce token parsing overhead for models like Claude and GPT-4o.
    • When your page is the sole authoritative source for an operational answer, frontier labs cite you by default.

    Section 2: The Human Practitioner vs. The Ingestion Bot

    ⏱ 15:45 – 21:00 (5m 15s)

    Simulating a healthcare facility manager seeking actionable continuity checklists. Demonstrates why annoying popups kill user trust and how clean, copyable data bridges the gap between human and bot workflows.

    Key Takeaways:

    • Human practitioners want immediate utility: checklists, copyable tables, and direct downloads.
    • Intrusive popups drive dead clicks, high bounce rates, and immediate frustration.
    • Designing frictionless copy-paste controls serves human users and AI grounding engines simultaneously.

    Section 3: Why Video Gets Cited First & $7 Instant Checkout Experiments

    ⏱ 21:00 – 26:15 (5m 15s)

    Multi-modal AI prioritization: why search engines push video walkthroughs to the top. Exploring how micro-transactions ($7 instant Square checkout) and agentic protocols (UCP) enable autonomous software purchases.

    Key Takeaways:

    • Modern answer engines prioritize verified video demonstrations over unverified text claims.
    • Testing $7 low-friction digital products with instant payment rails tests transaction velocity.
    • Agent-to-agent commerce (UCP) allows AI bots to discover and purchase resources on behalf of human users.

    Section 4: The Freshness Penalty: Why Stagnant Pages Lose Citations

    ⏱ 26:15 – 30:45 (4m 30s)

    Forensic breakdown of a live Copilot citation featuring policy limits, deductibles, and an October 6th update date. Why high-value technical and regulatory content must maintain recent timestamps.

    Key Takeaways:

    • Copilot explicitly surfaces the publication and update date in its citation snippet.
    • Regulatory, pricing, and insurance topics have a steep decay curve if left untouched.
    • Establishing continuous content maintenance cycles protects high-yielding citation assets.

    Section 5: Telemetry Cadence: 7-Day vs. 30-Day vs. 6-Month Exports

    ⏱ 30:45 – 35:30 (4m 45s)

    How to extract actionable Bing Webmaster and Clarity telemetry without falling into rabbit holes. Why 7-day data skews B2B analysis due to dead weekends, and why 30-day and 6-month windows provide true signal.

    Key Takeaways:

    • B2B traffic operates on a Monday-to-Friday workweek; a 7-day export captures two dead weekends and skews reality.
    • Use 30-day and 6-month horizons to detect real structural growth and query trends.
    • Avoid getting trapped in beta features like ‘Explore Topics’—focus on raw query and page downloads.

    Section 6: The Human-in-the-Loop Strategic Vantage Point

    ⏱ 35:30 – 39:17 (3m 47s)

    The core operational philosophy: leveraging autonomous AI to execute heavy technical lifting (coding, schemas, deployments) so human leaders can step back to 30,000 feet and steer strategy.

    Key Takeaways:

    • AI handles the repetitive technical mechanics: regex, schema generation, and tag purging.
    • The human brings real-world intuition: understanding buyer psychology, practitioner needs, and market gaps.
    • Collaborative human-AI execution yields order-of-magnitude gains in speed and strategic clarity.

    Architecture Matrix: Traditional SEO vs. Single-Question Knowledge Nodes

    Dimension Legacy Multi-Topic SEO Post Single-Question Knowledge Node AI Ingestion Impact
    Semantic Focus Broad, meandering (15-20 subheadings, keyword stuffing) 1 Laser Question, Direct Answer, Context Matrix 100% Entity Match for Copilot & Perplexity
    Freshness Signals Published once; updated annually with minor date tweaks Monthly SLA / Continuous Schema Verification Eliminates Algorithmic Stagnation Penalty
    Human UX Friction Newsletter popups, dead scripts, intrusive traps Zero dead-click scripts; clean copyable tables Sub-180ms INP; Zero JS ReferenceErrors
    Multi-Modal Power Generic stock photos and un-captioned images Time-stamped Video Walkthrough with Chapter Schema Priority Ranking in Multi-Modal AI Summaries
    Agentic Readiness Text-only; requires human to click through forms UCP Manifests, JSON-RPC MCP Tools, Instant $7 Checkout Autonomous Shopping Agents Can Transact

    Actionable Rules for Your Next Content Sprint

    • Lead with the Direct Answer: Place the conclusive answer in the first 120 words beneath your primary heading before unpacking background context.
    • Audit for Dead-Click Scripts: Eliminate broken newsletter modals or un-declared event listeners (like the popupsend error) that cause rage clicks.
    • Anchor With Segmented Video Walkthroughs: Search bots prioritize multi-modal video nodes when verifying technical claims and real-world practitioner authority.
    • Use 30-Day and 6-Month Data Horizons: Never evaluate B2B strategy off a 7-day export that includes two dead weekends.
  • ChatGPT Is Five Rooms, Not One Channel

    ChatGPT Is Five Rooms, Not One Channel

    There’s a post going around that says: if you can rank in ChatGPT, you’re way ahead of the game, your leads from ChatGPT will increase, invest now.

    Here’s the problem with that sentence. There is no “ChatGPT” the way there’s a phone book. There are rooms. And the person in each room is a different person, sitting in a different chair, at a different time of day, asking a different kind of question.

    A free-plan mobile ChatGPT user on the toilet is not the same human as a Claude user inside their desktop looking up technical documentation at 10 in the morning. Treating them as one audience because the logos are similar is how businesses end up advertising B2B services on a consumer feed — the same mistake, wearing a new jacket.

    The five rooms

    Room one: free ChatGPT on a phone. Consumer questions. Evenings, couches, commutes. What’s a good car stereo, write my cover letter, explain this homework. Enormous volume, almost no B2B buying intent.

    Room two: paid ChatGPT at a desk. Prosumers and knowledge workers who chose it as a tool. Better questions, work hours, some buying intent — when the question is about their own workflow.

    Room three: Claude at a desk. Developers, analysts, technical professionals. This is the room that reads documentation for a living. Weekday-shaped, deep, specific.

    Room four: Copilot inside Edge and Office. The corporate room. These people didn’t choose an AI — it arrived inside the tools their employer already runs. Facility managers, compliance staff, operations people, asking work questions in work language, mid-task.

    Room five: Gemini inside Google search. Everyone, for everything, at search scale. The broadest room and the shallowest intent per question.

    Same species of technology. Five different demographics. “Get cited in AI” means nothing until you say which room.

    What the counting says

    I count AI citations for a living — six months of Bing AI Performance data across my own network, 1.6 million citations and change. The rooms are not a theory. They’re in the numbers.

    On Tygart Media, the single most-cited page is a Claude AI pricing explainer — 1,388,909 citations. The audience for this site is technical professionals, and the citation traffic is weekday-shaped: it rises when people are at work and flattens when they aren’t. Room three, behaving like room three.

    On Healthcare Facility Hub — a site for hospital facilities and infection-control people — Microsoft’s AI surfaces cited 188 pages a total of 43,994 times in six months. The top pages are an ICRA matrix (4,067 citations), hospital evacuation planning (2,766), ASHRAE 170 ventilation requirements (2,435), NFPA 101 life safety (1,802). The questions behind them read like this: what has to be in a facility’s emergency preparedness plan about emerging infections; which fire safety feature keeps smoke in one zone. Nobody asks those questions from a couch. Those are room-four questions — asked at a desk, inside a Microsoft environment, by someone whose job depends on the answer being right.

    Two sites. Two rooms. Neither audience is in the room the hype is selling.

    The test that settles it

    Before you pay anyone to get you cited “in ChatGPT,” ask one question: which room is your buyer sitting in when the buying question forms?

    If you’re selling to hospital facilities staff, your room is Copilot at a desk, and the content that wins there is an ICRA matrix, not a viral post. If you’re selling car stereos, room one is genuinely your room, and God bless. The tactic isn’t wrong or right — the fit is.

    Anyone who can’t tell you which room they’re putting you in is selling you the label. The label is the one part that doesn’t matter.


    Will Tygart runs Tygart Media. The citation counts above are from his own six-month Bing AI Performance board, counted nightly. The $97 AI Citation Quick-Scan exists because “which room cites you” is a measurable question: https://tygartmedia.com

  • How AI Search Visibility Is Actually Tracked (and What the Tools Can’t See)

    How AI Search Visibility Is Actually Tracked (and What the Tools Can’t See)

    Here’s how AI search visibility is honestly tracked: you write down the actual questions your customers ask, you ask those same questions in the actual answer engines on a fixed schedule, and you record three things separately — whether the answer names you, whether it cites you, and whether what it says about you is true.

    That’s it. Everything else — dashboards, scores — is packaging around that habit, or a substitute for it. And there’s a problem worth understanding before you buy a substitute: ranking and being cited are not the same event, and a tool that conflates them will mislead you without making a number up.

    Ranking is not being cited

    Start with the structural fact. Search the old way and you get a ranked list of pages. Ask an answer engine — Copilot, ChatGPT, Perplexity, the AI box atop Google — and you get a paragraph, written on the spot, with a handful of sources cited beside it.

    Those two events are only loosely connected. A page can sit at position two in the organic list and never get quoted, while a competitor at position four gets built into the answer. It isn’t a glitch: the engine doesn’t summarize the top result. It breaks your question into smaller sub-questions, looks for material on each, and assembles an answer from what it finds — and studies of cited URLs find just a small minority come from the organic top ten.

    So rank-based tracking measures the list while your customers read the paragraph. That’s the gap where businesses get surprised: “we rank fine, why is the machine recommending somebody else?” The events that matter are being named, cited, and described correctly. For the basic method as a straight answer, see how do you measure AI search visibility. This piece covers the part usually skipped — the limits.

    The only honest method: fixed questions, three separate records

    The method fits on an index card. Build a list of the questions your customers actually ask — not keywords, questions, in their words: “Who fixes a flooded basement in Tacoma?” “What does water damage cleanup cost?” Twenty or thirty is plenty. Then, on a fixed schedule — weekly is honest, monthly the floor — ask them in the engines your customers use, and record what comes back.

    The recording is where honesty lives or dies, because one answer contains three different facts:

    • Mentions. Does the answer name your business at all? Not link, not cite — name. The customer reading that paragraph sees your name or a competitor’s.
    • Citations. Does the engine cite your pages as sources? You can be named with no citation, and cited without being recommended — quoted as background while somebody else gets the call.
    • Accuracy. What does the answer say about you, and is it right? Engines repeat stale facts and invent new ones with total confidence. An answer describing a service you stopped offering two years ago is not a win — it’s a wrong sign on your door.

    Three columns, kept apart. Any tool worth paying for just runs that without the handwork — and the moment one blends those columns into a single number, it throws away the only details you’d ever act on.

    What tracking can genuinely see

    Done this way, tracking earns its keep. Four things it shows straight:

    • Trends on fixed questions. Same questions, same schedule. When your name starts appearing in answers it wasn’t in, that’s real movement — usually tied to work you did.
    • Which pages get cited. Not which pages rank — which ones engines actually pull from. In our own work, a few pages carry a large share of the citations.
    • Share against named competitors. Record who gets named when you don’t, on the same question set.
    • Answer drift. Ask the same question next month and the answer is different: a new source, a dropped name. Drift is normal — and why a one-time check is worth little.

    What no tool can see

    Now the part that doesn’t make it into the sales deck: five things no tracker — ours, theirs, anybody’s — can show you.

    The answer your actual customer got

    Answers vary by who’s asking, where they are, and when they ask — the same question can name different businesses for two people in the same town on the same afternoon. A tracker sees a sample, from its own accounts, and a sample is not the population. Anyone presenting a report as a census of what your customers saw is overselling the instrument.

    The questions nobody thought to ask

    Your prompt list is a map, and the map is not the demand. Customers ask things you’d never predict — oddly specific, half-wrong, mid-emergency questions typed one-handed at 2 a.m., some the most valuable in your market because the person asking is ready to buy. If it isn’t on your list, your tracker never asks it. The fix isn’t a bigger tool — it’s refreshing the list from real life: call recordings, intake notes.

    Why the engine picked a source

    No engine publishes its citation reasons. A tracker can tell you a page got cited, never why that page and not yours — anyone who claims otherwise is guessing and charging for the guess. What you can do is compare: read the cited page next to yours. Does it answer in the first paragraph, state facts plainly enough to quote, is it current? That’s judgment, not telemetry.

    What the answer caused

    Attribution stops at the answer. The engine doesn’t report back that the homeowner who read its paragraph called you, called the other company, or fixed it themselves — those calls are invisible to every visibility tool ever built. The last mile shows up only in your own books, so report and call log get read side by side before anybody claims the visibility did anything.

    Engines that don’t show their answers

    Some surfaces can’t be sampled at all — answers behind logins, in apps, in voice assistants. A tracker reports on the engines it can reach and has nothing on the rest. Ask any vendor which engines their number doesn’t cover.

    The score problem

    Which brings us to the product most buyers are actually being sold: a single visibility score. One number, proprietary formula, up and to the right in the demo. The trouble isn’t that it’s fake — it’s what it has to compress to exist.

    Run a small example. Over a quarter, a business gets mentioned in more answers and cited more often too. By any blended formula the score rises, and the quarterly report is a celebration. But read the accuracy column, the one the score dissolved: the engines now describe the business as offering a service it dropped last year, at a price it no longer charges, because an old page still says so. Customers call with wrong expectations, and staff spend five minutes a call correcting the internet.

    Score up. Facts wrong. Both true at once — and only one shows up in the report the owner paid for. A blended number turns three actionable facts into one feeling. A score that rises while the answer about your business is wrong isn’t measuring your visibility. It’s measuring its own smoothness.

    What to demand instead

    You don’t need to become a measurement expert. Ask for four things, and watch whether the seller can produce them.

    • Your prompt list, built from real customer questions — and shown to you. Generic questions make generic tracking.
    • The raw answers, kept. Not a screenshot of the best week — the actual paragraphs, so anything in the report traces back to a readable answer.
    • The three records, kept separate. Mentions, citations, accuracy — three columns, never one blended score. If a summary number exists, it sits on top of the columns, not instead of them.
    • Figures you can re-pull yourself. Where engines expose their own numbers — Bing Webmaster’s AI Performance reports, Microsoft Clarity — those live in accounts you own, and any figure from them can be checked by you, in your login. Hold every report to that standard: see the best agency for AEO SEO reporting is the one whose numbers you can re-pull, and our page on what an AI visibility report should show lists the sections to expect. An unverifiable report is a story you’re being told.

    Measurement, done honestly, is a flashlight, not a scoreboard. It shows you where to work next — which question you’re absent from, which fact about you has gone stale. The moment the measurement becomes the product being sold, it stops measuring your business and starts measuring itself. Run the fixed questions. Keep the three columns. Read the actual answers.

    Questions buyers ask us

    How do AI visibility tools work?

    At bottom, every one of them does what you’d do by hand: asks a fixed list of questions in the answer engines, on a schedule, and records what comes back — who’s named, who’s cited, what changed. The honest ones keep the records separate and show you the raw answers; the expensive-looking ones blend everything into a proprietary score. Either way, all of them see a sample — never every answer a customer received.

    Why doesn’t my Google ranking match my AI mentions?

    Because they’re different events. Ranking is your position on a list of pages. A mention is whether an answer engine names you in a paragraph assembled from its own sub-questions — whose cited sources overlap the organic top ten only a little. You can rank second and go unnamed while a competitor at fourth gets quoted — and tracking only the list keeps that gap invisible.

    Can I track AI visibility myself?

    Yes — the basic version is genuinely do-it-yourself. Write down twenty or thirty questions your customers actually ask, put them to Copilot and ChatGPT, and record three things: named, cited, accurate. Repeat monthly, same questions, and check the figures the engines give you in Bing Webmaster and Clarity, in your own accounts. An afternoon to start, an hour a month to keep. What you’re paying for, if you pay, is never skipping the month.

  • An AEO Report You Can Re-Pull: A Worked Example

    An AEO Report You Can Re-Pull: A Worked Example

    A report you can trust is a report you can re-pull. Every figure in it traces back to a source you own — your own Bing Webmaster account, your own Microsoft Clarity account — so checking the work takes an afternoon, not an act of faith.

    I have argued before that the best agency for AEO SEO reporting is the one whose numbers you can re-pull. That is the standard. Our page on what an AI visibility report should show lays out the requirements. This piece is the missing third thing: the artifact itself. What follows is one monthly report, walked section by section — what each section shows, where each number lives, and how you would re-pull it yourself to check it.

    One disclosure before the numbers. This is a worked example. The business is a regional restoration company, the kind of outfit that answers the phone at 2 a.m. when a pipe lets go. Identifying details are changed, and the figures are a composite drawn from real reporting periods — not one client’s month dressed up as gospel. The sections, though, are the real sections, in the real order, and every figure in every section has a home in an account the client owns and can open without asking me.

    1. The ledger summary

    The first page is the whole story in one table: how many times the answer engines cited this business in the period, set against the period before. Nothing else. No score, no grade, no wall of arrows.

    Measure This period Last period Change
    Total citations 1,184 1,021 +16%
    Queries where the business was cited 214 187 +27
    Pages cited at least once 38 34 +4

    Where the numbers live: the overview export in the AI Performance section of Bing Webmaster Tools. The client logs into their own account, picks the same date range printed at the top of the report, downloads the CSV, and the headline citation count is sitting right there. Re-pulling this section takes about four minutes. If the number in the report and the number in the export disagree, the report is wrong, full stop — and the client found that out from their own account, not from a call with me.

    2. Share on the queries that pay

    A citation total by itself is a vanity number wearing a suit. What matters is which questions the citations hang on. This section lists the money questions — the ones a buyer asks an answer engine right before picking up the phone. For a restoration company, that is things like “water damage cleanup near me,” “how much does mold remediation cost,” and “who do I call for a burst pipe.” Next to each question: whether this business got cited for it, and who else did.

    Where the numbers live: the Search Queries export, same Bing Webmaster AI Performance section, same date range. Re-pull it, look up the questions that matter to the business, and the cited sources are listed per query. This is the section owners actually read, because it reads like the market itself. You can watch a competitor take a question you used to own, in plain text, with nobody’s opinion layered over the top of it.

    3. Page movers

    Citations land on pages, not on businesses. This section lists the pages that gained citations in the period and the pages that lost them, biggest moves first. A service page that doubled its citations after a rewrite. A location page that went quiet. A post from two years ago that an engine suddenly started quoting.

    Where the numbers live: the Page Stats export, same account, same date range, compared against last period’s export — which is why we keep every month’s files. Re-pulling means downloading the current export and setting it against the file from the prior period. The “why” written next to each mover is our read, and it is labeled as a read. The movement itself is not an opinion. It is in the client’s own files.

    4. New questions

    Every month, the query export contains questions that were not in it before. Somebody asked an engine something new — a new phrasing, a new service name, a question nobody in the market has written a page for yet. This section lists those questions, flags the ones this business was already cited on, and marks the rest as gaps.

    They come straight out of the same Search Queries export. There is no separate tool and no secret feed behind this section. New questions are the demand moving, in public, in the askers’ own words. Half of next month’s content list is usually sitting right here — and the client can check that claim too, because the questions are in their export, not in my notes.

    5. The work, priced against the movement

    This is the section most reports skip, and it is the one that keeps everybody honest. On one side, what was actually done in the period, named plainly: three pages published, two pages rewritten, one round of technical fixes. On the other side, what moved. It is the measurement loop from the workstreams behind AI SEO services, printed instead of described — the work and the numbers on facing pages, where the client can judge whether one earned the other.

    Two rules govern this section. First, the work list is complete. The page that was published and went nowhere sits on it, right next to the one that took off. Second, no credit is claimed where the movement cannot be tied to the work. If citations rose on a question nobody touched, the report says so and calls it what it is: the market moved, or the engine changed its mind, and we do not know which. An agency that only shows you the wins is editing. Editing is the first step toward inventing.

    6. What the report refuses to show

    The last section is a list of absences, and it is there on purpose. There is no proprietary visibility score, because a score only the agency can compute is a number you can never check. There is no best-week screenshot, because a business runs on months, not on its best seven days. And the engines are never blended into one soup of a number. The Bing and Copilot figures come out of the client’s own Microsoft accounts; anything that cannot be pulled from a source the client controls is reported separately, with its method stated, or left out — with the report saying it was left out.

    Blending is a hiding place. A blended number can rise while the engine that actually sends you buyers is falling, and you would never see it. Separate numbers can be wrong, but they can be caught. That is the whole trade, and we will take catchable over impressive every time.

    The test

    Here is the one test you can run on any report from any agency, including this one. Pick a figure — any figure, the bigger the better. Ask one question: “Show me where this lives in my own accounts.” Then watch what happens. If you get walked to the export, the account, and the date range, and the number matches when you pull it yourself, you are looking at reporting. If you get an explanation of why the methodology is proprietary, you are looking at a story about reporting. The figure was never the product. The trail behind the figure is the product.

    Questions buyers ask

    What should an AEO report include?

    Five things: a citation total you can re-pull, your share on the specific questions your buyers ask, which pages gained and lost citations, the new questions showing up in the data, and the work done in the period set next to what moved. A report carrying a score you cannot recompute from your own accounts is missing the point, even if it has everything else.

    How do I check my agency’s numbers?

    Log into your own Bing Webmaster Tools account, open the AI Performance exports for the same date range printed on the report, and compare. The overview export checks the headline, the queries export checks the questions, the page stats check the pages. Microsoft Clarity is yours the same way. An agency should be able to tell you which export backs which figure, gladly. That conversation is the check.

    What is a red flag in an SEO report?

    A number with no trail behind it. Proprietary scores, blended engine totals, best-week screenshots, and rankings reported without the source account are all the same flag in different colors: a figure you are being asked to take on trust. Trust is fine in a relationship. It has no place in a spreadsheet.

  • The Shortlist Is Written by a Machine Now

    The Shortlist Is Written by a Machine Now

    Somewhere tonight, a business owner is going to ask an AI assistant a question like “top ai seo agencies” or “top ai seo services for small businesses” — and the assistant is going to hand back a shortlist. Nobody at those agencies will be in the room. Nobody will make a pitch. The machine will build the list out of what it can find, cite, and trust, and most of the owners reading it will never ask how the list got made.

    We know these questions are being asked, because the search engines publish the opportunity data. In Bing’s own topic reporting for our site, that cluster of buyer questions — “top ai seo agencies ai-driven services,” “top rated ai seo services for small businesses,” “affordable aeo services strong seo results” — shows up as live demand, month after month. People are hiring this way now. So the only question that matters for a buyer is: what is the machine actually reading when it decides who makes the list?

    The shortlist is built from citations, not claims

    An AI assistant recommends what it can ground. When it answers “who should I hire,” it leans on pages it has cited before — pages whose facts it has already used in other answers. An agency’s beautiful website copy about itself barely registers. What registers is the agency’s citation footprint: how often its pages are used as sources, on which questions, and whether that number is climbing or flat.

    That flips the buyer’s job. You are no longer comparing pitch decks. You are reading report cards — and the agency selling AI visibility has one whether it shows you or not. So ask for it. Any agency doing this work seriously can pull its own numbers from Bing Webmaster’s AI Performance reports in about five minutes. If they have never looked at them, you have learned the most important thing on the call.

    The receipts test: four things to ask for

    One: total AI citations, and the trend. A single big number means little; a number that climbs month over month means the engine keeps choosing their pages. Ask for this month against last month, from the report, not from a slide.

    Two: the grounding queries they win. The report lists the actual questions their pages get cited on, with their share of each. An agency cited on the questions its buyers ask is proving something. An agency cited on a mountain of questions nobody in its market asks is farming trivia.

    Three: one page that climbed, and why. A single page’s citation history is a story with a mechanism — consolidation, structure, freshness, a topic the engine needed. If they can tell you that story with numbers, they understand the machine. If they can’t, their results, if any, are weather.

    Four: what they measure every month. Citation visibility is a trailing measure — a rate over the last thirty days, not a switch that flips. An agency that reports it that way, and can show you the rate moving, is measuring the real thing. An agency that promises rankings by Friday is selling the old world at new prices.

    Our own report card, printed in full

    We will go first, because that’s the test. From our own Bing Webmaster AI Performance exports — the same reports any agency can pull — tygartmedia.com was cited 1,459,726 times across 922 pages in the most recent full export on file (October 15, 2026). On the question “claude pricing,” our pages hold a 24.5% citation share; on “anthropic console,” 54.5%. That is the top of our footprint, and it is mostly content about AI tools and pricing — the audience that reads this site.

    The number we watch hardest is smaller and closer to our trade. Our page on IICRC certification for restoration contractors — the credential page for the industry we serve — has climbed four straight exports: 1,635 citations, then 1,913, then 2,454, then 2,790 (September 27 through October 24). A near-duplicate twin of that page collapsed over the same stretch, from 304 citations to 6, because the engine consolidated onto the stronger page. We didn’t game that. We watched it in the data, understood it, and fed the winner.

    What our numbers don’t show, said plainly: these are Bing and Copilot figures. Google’s map is different, every engine’s is, and anyone who quotes you one engine’s numbers as “AI visibility” full stop is rounding in their own favor. Citation share also trails the work by weeks — it is evidence about the recent past, not a promise about your future. And a footprint proves an agency can get itself cited; whether it can do it in your vertical is a separate question, which is why item two of the test — the grounding queries — matters more than the total.

    The buyer’s move

    The machine is going to keep writing the shortlists. That part is settled. What isn’t settled is who is on them, and the way onto the list is not a better sales page — it is a body of work the engines already trust enough to cite.

    So if you are hiring: skip the deck, ask for the report. Total citations and the trend. The grounding queries and the shares. One page that climbed and the story behind it. The monthly measurement, in the trailing-rate language of people who actually watch it. An agency that can hand you those four things is showing you its own exhaust — the work, on tape. An agency that can’t is asking you to take its word for the one thing it claims to sell.

    Take nobody’s word. Ours included. The reports are free, they take five minutes to pull, and they do not care whose logo is on the website. That is exactly why they are worth reading.

  • Wonder Full Stays in the Seat. The API Key Is a Different Promise.

    Wonder Full Stays in the Seat. The API Key Is a Different Promise.

    On October 12, 2026, Meta launched two models that share a name and almost nothing else. Muse Wonder is a product you can call: it sits on the Meta Model API at $4.00 input, $0.20 cached input, and $20.00 output per million tokens, and inside Muse Code. Muse Wonder Full is a model you can only sit in front of: it exists exclusively inside a Muse Code subscription, on the Power Usage and Maximum Usage plans. The decision an operator makes before pointing either one at a real repository is not which model is smarter. It is which promise they are buying — and the seat’s default promise is not the one most buyers think they made.

    The frontier model is a seat, not a SKU

    Meta’s own availability table is the whole story in four cells. Muse Wonder (muse-wonder-1.0): available on the Model API, standard mode only, and in Muse Code on pay-as-you-go and every plan. Muse Wonder Full: not available on the API at all — Power Usage and Maximum Usage subscriptions only.

    There is no back door. Setting reasoning effort to “max” on muse-wonder-1.0 does not select Wonder Full; Meta’s models page says so in plain words. Meta publishes no API model ID for Full. A team that wants Full behind its own product has, in the words of one launch-week review, no path at any price — businesses can test it inside Meta’s coding environment and cannot deploy it through the standard API.

    The seat prices are printed on the Muse Code product page: Everyday Usage $5 a month, High Usage $15 at 5× the Everyday allowance, Power Usage $50 at 20×, Maximum Usage $200 at 80×. Power is the cheapest chair that includes Wonder Full. The allowances run on five-hour and weekly resets, and per the Terms, a subscription’s per-period allowance expires at the end of each period and does not roll over. On Maximum, when the allowance is gone, Meta’s documented way forward is to wait for the refresh.

    The credential is a leash

    The subscription applies to the API key Meta automatically connects during Muse Code CLI onboarding, and the subscriptions doc is explicit about the boundary: “This credential is for use with Muse Code only.” The Terms give the arrangement its legal name — a Coding Harness Subscription — and the same restriction: the connected key “may not be used to access the Services outside the coding harness or to circumvent your subscription’s usage limits or billing.”

    Any additional API keys you create under the same account are billed pay-as-you-go, per token. So one Meta account holds two different commercial relationships at once: a flat seat that works only inside one CLI, and metered keys that work anywhere except that they can never call the frontier model. Budget them as two products, because Meta does.

    The default is the decision

    Here is the trap, and it is set by a default. “Muse Code subscriptions default to Contributor mode. In Contributor mode, you get more usage from your plan in exchange for letting Meta use your content — the prompts, code, files, and context you send, plus the model responses you get back — to train future Meta models.”

    A careful buyer can still walk into it. Meta’s Model Designation Policy lists Muse Wonder and Muse Wonder Full as Standard Models — the tier whose use constitutes Standard Services, where content is not used for training. The same policy then overrides the list: “If you access the Services through a Coding Harness Subscription, you are considered to be using the Contributor Services by default regardless of which Meta Model you select.” Terms section 3.3 says the same. In Muse Code, Contributor mode is not a model name. It is a subscription setting, and it is on.

    Turning it off is one toggle: open /settings in Muse Code. The help page states what the toggle does and does not do: “Turning Contributor mode off changes how much usage you get from your plan. It doesn’t change which plan you’re on.” How much usage changes, Meta does not publish — no ratio, no prompt count, no price difference appears in the documents. The honest line for a budget is that the size of the privacy discount is undocumented.

    Meta’s own warning belongs in every seat-setup checklist, quoted exactly: “You must not submit sensitive, confidential, or personal information to the Discounted Services. If your use case involves processing personal information, please use Standard Services.” Accounts with Zero Data Retention cannot use Contributor mode at all — and ZDR itself is an organization-level enablement Meta’s sales team turns on for Model API accounts, not a toggle in the CLI, and it does not cover requests made with a personal account.

    The switch does not reach backward

    The off-switch is prospective. Terms section 3.3: a change to Standard applies “prospectively only; it would not apply to Content previously submitted to the Contributor Services, and Meta’s rights with respect to that Content under Section 6 will survive the change.” Everything a seat sent while the default was on stays under the training grant after you flip the setting.

    Section 6.1 adds the subtler pull: “Content previously submitted to the Standard Services becomes Content submitted to the Contributor Services if it is included in any request to the Contributor Services, whether directly or as context or background for your prompts or instructions.” One later Contributor-mode session that pulls an earlier, clean conversation in as context reclassifies that content.

    The commitments page softens the arrangement with a safeguard and then qualifies it: before using Discounted Services content to train models, Meta “takes steps designed to disassociate that Content from your Accounts” — but Meta may use the same content for “evaluation, safety, abuse, quality, and policy review” without first applying those steps. And section 6.1 acknowledges the output side: models trained on your content may produce outputs “similar or identical to your Content,” including for third parties.

    The API shelf is labeled honestly

    On the API, the same choice exists — as a separate model name, printed on the pricing page where a buyer can see it. Contributor mode “isn’t available for Muse Wonder on Model API.” For Spark it is a different SKU: muse-spark-1.3-contributor and muse-spark-1.2-contributor at $0.10 input, $0.002 cached, $0.20 output per million tokens, against standard Spark at $1.25 / $0.15 / $4.25 — capped at 150 requests per minute against 3,000 for the standard IDs. The Muse Code product page labels the two rows without euphemism: the Contributor row is “Used to improve our products”; the standard row is “Not used to improve our products.”

    That is the contrast the seat hides. On the API, training is a priced, named, rate-limited variant a buyer selects on purpose. In the subscription, it is the factory setting of the harness — and the model table’s “Standard Model” label will tell a skimming buyer exactly the wrong story about which arrangement they are in.

    The operator’s checklist

    Decide the data arrangement before the repository, not after the first session. A public demo and a confidential codebase can run through the same agent on the same afternoon; they require different settings, and the setting is per-subscription, not per-conversation.

    Turn Contributor mode off in /settings before any client code, customer data, or contract-confidential material enters the seat — remembering that the flip protects only what is sent afterward, and that earlier standard content follows it if it is ever pulled back in as context.

    Buy the seat for the seat’s work. Wonder Full is a genuinely frontier tool for a person at a keyboard, and it is not a component. Anything your own product must call belongs on the API, in Standard mode, on keys you budget per token.

    This desk tracks Meta’s platform as it changes; the full rate card and the contributor tier’s arithmetic are in Meta Model API Pricing & Limits, and every Meta piece hangs off the Meta AI desk hub. The short version to tape above the desk: the model in the seat is not the model on the shelf, and the seat’s most consequential setting is the one nobody remembers choosing.

  • How do you measure AI search visibility?

    Updated November 2, 2026 — added direct answers on visibility metrics and AI search share of voice, from our own published measurement.

    You measure AI search visibility with two kinds of tools: the reports the platforms publish about their own answers, and trackers that ask the assistants your customers’ questions on a schedule and record who gets named. The platform reports show who the platform cited. The trackers show what an assistant answered when asked. A buyer who knows which tool shows which thing can read either one honestly.

    What does “visible” mean in an AI answer?

    An AI answer can mention your business, cite your business, or recommend your business, and those are three different measurements. A mention means your name appears in the answer text. A citation means the answer credits your page as a source. A recommendation means the assistant names you as the choice. Every tool below reports some mix of the three, under its own labels.

    The distinction decides what a number is worth. A mention can be one name in a list of eight. A citation means the platform read your material closely enough to credit it — that is the receipt that survives. A recommendation is the strongest outcome and the least common. When a tool shows you one big “visibility” number, the first question is which of the three it counted.

    What metrics matter for AI search visibility?

    Traditional search metrics like keyword rank and search volume do not apply to AI assistants. A complete measurement framework tracks five distinct metrics, as established in our guide to measuring LLM visibility and our three-layer visibility measurement framework:

    • Citation frequency: The total number of times your domain or brand is cited as a source in AI-generated answers over a measured window.
    • Prompt coverage: The percentage of your sampled buyer queries where your brand or content appears anywhere in the output.
    • Share of voice: The proportion of citations your domain earns on a specific prompt set compared to named competitors.
    • AI referral traffic: The volume of qualified sessions arriving on your site from AI platforms, tracked via custom GA4 channel groups.
    • Citation-assisted conversions: Inquiries, form submissions, and booked jobs that originate from or touch an AI search session.

    What is share of voice in AI search?

    Share of voice in AI search—also termed share of authority—is the percentage of total citations awarded to a specific domain across a fixed set of prompt tests. Unlike a simple citation count, share of voice measures your presence relative to every other source cited for the same queries.

    Consider a live worked example from Tygart Media’s own tracking on November 2, 2026. Across a Clarity measurement run evaluating the topic “AI citation rate measurement” (101 total citations distributed across approximately 50 competing domains), the single leading domain captured 8.91% of citations (9 citations). Tygart Media earned a 0.99% share of authority (1 citation). In an emerging, fragmented AI search topic where no single authority owns the category, tracking share of voice across recurring runs reveals whether your content is steadily accumulating citations or losing share to competing domains.

    What does Bing AI Performance show?

    Bing AI Performance is Microsoft’s free first-party report, and it shows what the assistants built on Bing actually cited. The report organizes citations four ways: Intents, Topics, Citation Share, and Compare. It is the platform grading its own homework — the most direct evidence a buyer can get, and a view of exactly one surface.

    The four views answer four plain questions. Intents shows the kinds of things people were trying to do when your pages got cited. Topics groups those citations by subject, so you can see which of your subjects the machines trust. Citation Share shows your slice of the citations on a topic against everyone else cited there. Compare puts two date ranges side by side, so a change shows up as a change and not a feeling.

    Our own report is the example we read every month. For tygartmedia.com, our Bing AI Performance report covering six months of Microsoft Copilots and partners shows 1.5M total citations across an average of 164 cited pages. We read that as our footprint on one measured surface — proof the surface can be measured, and a baseline to compare the next run against. It says nothing about any other platform, and it is not a promise about any other business.

    What do third-party visibility trackers show?

    Third-party trackers are subscriptions that ask a fixed set of questions to the major assistants on a schedule and record the answers. A tracker shows mention rates, citation rates, and competitor shares across several surfaces at once. What it sells is a trend line across platforms, built from sampled asks — not a record of what any real customer saw.

    The honest advantages are real. A tracker sees surfaces the first-party reports cannot, because each platform only reports on itself. A fixed question set, asked the same way each run, produces runs a buyer can actually compare. Competitor context comes built in, and in a contested market that context is the point.

    The limits are just as real. The tracker asks its questions, on its schedule, from its accounts — your customers ask differently, locally, and once. Small question sets get reported as precise percentages, and a two-question swing can dress itself up as a trend. And the subscription runs whether you read it or not. A tracker earns its money in a competitive market with several assistants in play, read monthly by someone who acts on it. Everywhere else it is an expensive screensaver.

    What can no tool tell you?

    No tool can tell you what a specific customer saw, whether a mention became a phone call, or why an assistant chose a competitor. AI answers vary by person, place, and moment, and the platforms do not publish their reasoning. A tool shows outputs. The cause behind an output is still the buyer’s work to figure out.

    Sit with that limit before you buy anything, because it is where the honest tools end and the salesmanship starts. No report closes the gap between “the assistant named us” and “the phone rang” — that gap closes with call tracking and asking customers how they found you, unglamorous as that is. A provider who sells you certainty across that gap is selling you the gap.

    Which tool should a buyer start with?

    A buyer should start with the free first-party report for the surface their customers actually use, and add a tracker only when they need a cross-platform trend and will read it monthly. The tool matters less than the discipline behind it: a fixed set of your customers’ questions, asked before the work and after, with the raw answers kept. Any tool run that way beats a better tool run casually.

    Most small businesses find the first-party report is enough to start, because it answers the only question that changes what they do next: on the questions my customers ask, who does the machine name — and is it me? If you want that first measurement done by hand instead, our AI Citation Quick-Scan asks 10 prompts about your service line and returns a scored report within 7 days — $97, one time.

    Which lines the platforms lift is their call. We build the material they lift from — and then we measure what they did.

  • The Desktop Sidecar

    The Desktop Sidecar

    Last verified: 9 September 2026. Practitioner essay from the workbench — not a Google or SpaceXAI press release. We use these tools because they make the company better. No affiliate links. Just the receipt.

    Interesting fact, because the seats keep getting mashed together: this piece was reported from a Grok CLI sitting on the physical laptop — the sidecar, not a cloud bot and not a phone app — while that same session logged into Gemini, attached a 293-source notebook, and asked Gemini to grade the notebook against 2026. Two harnesses. One desk. It was a live interoperability test. It worked.

    On 27 December 2025 I built a Gemini notebook called Cortex-One: Architectural Mandate for the Native Audio Second Brain. Two hundred ninety-three sources. Audio, slides, video, reports, a mind map. A week later I opened a sister notebook: The Desktop Sidecar Evolution Brief.

    Then the sources stopped. The Studio still shows the last Gemini note as 232 days ago — about 20 January 2026. The brain froze. The world did not.

    Today I sat next to the laptop and asked the frozen brain what it got right.

    What Cortex-One was betting on

    Gemini, reading its own notebook, put the bets in three lines:

    1. Native audio over text chatbots. Speech-to-speech. Barge-in. The death of the typed box as the main door.
    2. A router called “The Cortex.” One brain. Specialist sub-agents for research, code, memory. Not one giant prompt.
    3. Remote MCP on Cloud Run. And — this is the plot — it explicitly rejected a local desktop sidecar.

    That third bet is the one I want to hold up to the light.

    232 days later

    Bet Call What actually happened
    Voice agents Early, mostly right Native audio shipped. Cascaded pipelines (Pipecat, LiveKit, WebRTC) did not die. The “one model does all the speech” purity was too rigid.
    Gemini ↔ Notebook Right Two-way notebook sync shipped in April 2026. Today I attached Cortex-One to a Gemini chat in three clicks.
    Named personal agents Right direction Meta launched Muse on 8 September 2026. You name the agent. Mine, on the personal box, is Glint. That is not the work seat.
    Desktop sidecar Wrong call Cortex-One killed it. Seven days later I wrote the Sidecar brief anyway. Today this CLI is the sidecar: a Grok seat on the physical machine, using Gemini’s own notebook and the copilots already inside Gmail, Analytics, and Notebook.
    Cloud bots Real, different seat Grok Bot shipped in August. Android and iPad this week. Persistent cloud computer. Fantastic. Not this laptop. Mixing “Grok Desk,” Grok Mobile, Grok Bot, and this CLI is how you get a 17-message thread that cannot tell the seats apart.

    Gemini scored the frozen brain itself: vision 8/10, infrastructure pragmatism 5/10, longevity 6/10. The 5 is because it locked to Cloud Run Remote MCP and dismissed local sidecars. I agree with the 5. I wrote it.

    Gemini also called Grok Bot “late / niche.” That is Gemini being Google. Bot is a real product with a real cloud computer. It is just not the thing sitting next to me.

    The seats are not interchangeable

    This is the hygiene. If you smash these together you will write emails that are wrong, and then you will believe them.

    Seat Where it lives Job
    Grok CLI on this laptop Physical machine, next to the human Hands. Opens Gmail, Notebook, Analytics. Uses the AI already inside those products. Leaves a receipt.
    Grok Bot Shared cloud computer; desktop app and phone Teammates that keep working when the lid is shut. Chief of Staff, Ops Scout. Draft-to-self. Human Gate on send, post, pay.
    Grok Mobile Phone, same Bot cloud Approve, review, nudge. Not the laptop CLI. Not “Grok Desktop” as a third Will@ mailbox.
    Gemini (work) will@tygartmedia.com Gmail Ask Gemini. Gemini Notebook. GA4 Ask Advisor. Workspace identity.
    Muse / Glint Personal — wtygart@gmail.com Meta’s personal agent. Named. Not the Tygart Media desk. Do not let it operate Slack or Notion for work.

    Personal vs business is a hard wall. Physical vs cloud is a second wall. In-app copilots vs agents that drive the OS is a third. You can use all of them. You cannot pretend they are one brain.

    I already published the ladder as I actually run it — Cursor as lead seat, Grok Bot as Chief of Staff, Notion as the board, Slack as the doorbell — in The On-Ramp Is Real. The Commons Is Unfinished. This piece is the missing rail on that ladder: the laptop that sits next to you.

    The cheapest intelligence is already in the product

    Today’s test was not “build a new agent.” It was: log into the tools we already pay for and talk to the copilot they shipped.

    • Gmail Ask Gemini summarized a 17-message seat-mix thread without opening every message.
    • Gemini Notebook still held Cortex-One and the Sidecar brief.
    • GA4 Ask Advisor answered from live 247 Restoration Specialists data, signed in as work.
    • Gemini chat took Cortex-One as an attachment and graded it against 2026.

    Cloud bots that work while the lid is shut are real. So is a CLI that is you, sitting here, smart enough to use Gemini-in-Gmail instead of forty screenshots. Those are different harnesses. Forcing one AI to fake another is how the Glint / CoS / “Desk Grok” mail mix-up happens.

    Were we early?

    On voice: yes. On a named cortex that routes work: yes. On killing the laptop sidecar so everything could live on Cloud Run: no. I already suspected that on 3 January, which is why the Sidecar brief exists. I just stopped putting sources in the brain.

    The freeze is the other finding. A 293-source notebook with slides and video is not a second brain if nobody feeds it. 232 days is long enough for Gemini 3, Grok Bot, Muse, and notebook sync to ship around a document that still thinks Gemini 2.5 Flash is the architecture.

    The move is not “rebuild Cortex-One.” The move is: keep the notebook as a dated artifact, keep the sidecar on the desk, and stop letting cloud seats write as if they are the laptop.

    What to do this week

    1. Name the seats out loud. CLI, Bot, Mobile, Gemini-work, Muse-personal. If a thread uses one address for two of those, that is a bug.
    2. Use the copilot already inside the product before you spawn a new agent. Gmail, Notebook, Analytics, Search Console — they all talk now.
    3. If you have a frozen notebook, attach it to Gemini and ask what shipped after the last source. Do not pretend the freeze is current doctrine.
    4. Human Gate still holds. Draft is not send. A sidecar with hands is still not allowed to mail a client because it can click Gmail.

    Close

    Cloud agents are teammates in another room. The CLI is a person next to you with hands. Personal and business identities are a wall. The cheapest intelligence is the copilot already inside the product.

    We were early on voice. We were wrong to kill the sidecar. The proof is this session: Grok on the physical desk, Gemini on the notebook, one human watching, a receipt on the site.

    The on-ramp is still real. The sidecar was the point.


    Will Tygart — Tygart Media. Written 9 September 2026 from the Command Center. Grok CLI on the laptop used Gemini (Gmail, Notebook, Analytics Advisor, and a Cortex-One-attached chat) as a live test of two harnesses on one desk. This essay does not speak for Google, Meta, SpaceXAI, Cursor, or xAI. We want those companies to succeed because we are building on the tools they ship. Human Gate on send / post / pay still stands.

  • Tacoma alerts and which utility desk

    Two common mix-ups: which alert list, and which power company. Last checked November 3, 2026.

    Alerts

    Tacoma Alert only covers the City of Tacoma. Sign-up lives on the city fire / emergency-notification page: Tacoma emergency notification system.

    Pierce County Alert (PC Alert) covers most of the county outside Tacoma. It does not replace Tacoma Alert. County page: Alert and warning. Emergency Management office: 2501 S. 35th St., Suite D, (253) 798-6595.

    Work in University Place, Lakewood, or Puyallup? Those cities have their own lists. Sign each one. Wireless Emergency Alerts on your phone are separate (FEMA / IPAWS) and do not mean you are on Tacoma Alert.

    Which utility

    Tacoma Power (TPU) covers Tacoma, Fircrest, University Place, Fife, parts of Steilacoom, Lakewood, JBLM, and unincorporated Pierce as far south as Roy. Outage and start-stop: TPU desk.

    Puget Sound Energy is the other large electric utility in the county. Outage / downed line: 1-888-225-5773 · pse.com/outage. Do not call TPU about a PSE pole.

    Look at the bill. If it says Tacoma Public Utilities, use the TPU desk. Fire / 911 still first if a line is down on a person: Fire desk.

  • Tacoma Community College desk

    TCC is the west-end campus at 6501 S. 19th Street, Tacoma, WA 98466 — 150 acres, not downtown. Last checked November 3, 2026.

    Main: (253) 566-5000 · tacomacc.edu
    Gig Harbor: 3993 Hunt Street NW, (253) 460-2424
    Maps: Maps and directions

    Visitors park in stalls marked “VISITOR” — if those are full, get a temporary permit from the Campus Safety front counter in Building 14. (Gig Harbor needs no parking permit at all.) Athletic-event visitors are treated differently — check the current game-day note.

    West End context: Narrows desk. Transfer to UW Tacoma: UW Tacoma desk. Bus: Transit desk. Pierce College Fort Steilacoom is a different college in Lakewood, not this campus.