Tag: AI Tools

  • What’s New in Cursor Is a Claim. Here’s How We Check It.

    What’s New in Cursor Is a Claim. Here’s How We Check It.

    A changelog entry is a claim

    When a platform ships an upgrade, the changelog tells you what the vendor wants you to believe about it. Sometimes the claim is the whole story. Sometimes the feature is real and irrelevant to your work. Sometimes — the dangerous case — something you depend on moved and the entry is three lines long. A shop that builds on a harness needs a discipline that sorts those three piles. This is ours.

    The loop, in order

    • Watch. Two daily diffs: the model catalog (running since October 16, 2026) and the changelog itself (from today). Change-only reporting — silence means nothing moved, and a failed watch reports itself once rather than going quietly blind.
    • Read against our record. Every real change gets one question: does it touch a surface we run — Desktop sittings, the cloud API, mobile steering, or a model our routing names? If not, it is logged and skipped, however shiny.
    • Check before adopting. A change that touches the harness earns a check against a known quantity — a brief we have already graded, a sitting pattern we already run. The check’s result, not the changelog’s adjectives, decides what changes in our work-order kit.
    • Write it down, dated. The desk pages update with the date of the change and the date of our check. A claim we repeated and later found wrong gets corrected in place, with the correction visible.

    This week’s page, sorted by the discipline

    Cursor’s changelog top, as of October 19, 2026 (entry dates October 16 and 13 at the head of the page): cloud-agent entries lead — canvases from cloud agents, an environments API. Those matter here, because cloud agents are a production lane for us; they go on the check list. A remote-control entry — see and reply to local agents from the iOS app, in Cursor’s description — matters specifically to a shop whose sittings run on one laptop: it changes how a sitting can be supervised, so it gets read carefully before it gets used. A marketplace launch and a pair of shipping bots are logged-and-skipped for now: real, announced, and not touching our record yet. Those descriptions are Cursor’s; the sorting is ours.

    Say where each fact came from

    One habit does more for a desk’s credibility than any other: provenance on the page. The changelog currently shows entry dates but no Desktop version string — so this desk’s version knowledge does not come from the changelog. It comes from reading our own install (3.25.9, October 19, 2026). When the basis of a number is our fleet, we say fleet. When it is the vendor’s page, we say vendor. A reader who can tell which is which can trust both.

    That is the whole method: vendor claims in, checked knowledge out, dates on everything. The watches are cheap. The discipline is the product.

    Method & settings — this piece

    Watches: Model-catalog diff (daily since October 16, 2026) + changelog diff (daily from October 19, 2026); change-only; failures reported once

    Sorting rule: Touches a surface we run = check list. Otherwise logged and skipped. Vendor descriptions labeled as the vendor’s

    Desk rule: Every fact carries its provenance and date — our record, or Cursor’s page, never blended

    Filed under the Cursor desk — the desk these watches feed.

  • Composer 2.5 Is Our Code Seat. Here’s Its Record.

    Composer 2.5 Is Our Code Seat. Here’s Its Record.

    Why Composer holds the code seat

    Every work order this shop writes names its executor up front — the model, the seat, and what happens if that seat is unavailable (stop; never substitute quietly). For code, the name on the order is Composer 2.5, Cursor’s own model. It did not get the seat by brand. It got it on a board we ran ourselves.

    The board: October 16, 2026

    Our fleet comparison put the models on one identical brief and graded the work. In the initial trio — Grok 4.7, Composer 2.5, and Auto — all three scored perfectly, and Composer was the fastest of the three: 31 seconds, 13 cents. Across the full board it was the fastest model tested, full stop, while identical perfect scores elsewhere on the board cost up to 86 cents. Speed with a perfect score is exactly the profile a code seat wants: code work is iterative, and iteration speed compounds.

    The same board explains the seat Composer does not hold. Our first pass — the wide, cheap, read-everything pass — belongs to GLM 5.3 Flash, which produced its perfect score for 0.83 cents. A hundred-fold cost spread for the same correct answers is the whole argument for routing by evidence instead of by logo: Composer where its speed pays, GLM where its price pays, and the receipts to say which is which.

    What we have put through it

    Through Desktop sittings, Composer executes the shop’s build work: fleet website builds and repairs across our WordPress properties, the Work Order Desk application (a BMAD+ build whose doctor checks pass 35 of 35), and the tooling runs in between. The work-order standard it runs under is not a prompt and a prayer — it is an unaided first pass in its own words before any templating, a permissions pre-flight, ship/hold boundaries stated in the order, and evidence graded on its timestamped trail plus screenshots at the verification points.

    The dents, on the record

    • The seat is bounded by the order. Our standing rule exists because it was earned: a work order that comes back with questions is a work order that was not finished. Composer executes what the order covers — gaps in the order surface as gaps in the run.
    • The real gates stay human. Sends, deletions, money, and credentials are never pre-approved for any executor. Composer stops there by design, and that is a feature of the harness, not a limit of the model.
    • The pipeline around it can bruise the output. In one October sitting, deliverables written through the Windows pipeline came back with mojibake on the em-dashes; the fix was ours to make — UTF-8 stated explicitly in every work order since. Blaming the model for a harness defect is how shops learn nothing.

    Cursor describes Composer as its in-house model family built for agentic coding — that is their claim, labeled as theirs. What this desk can vouch for is narrower and, we think, worth more: on our briefs, on our board, at our volume, it is the fastest pair of hands we have measured, and the record above is the whole of why it holds the seat.

    Method & settings — this piece

    Comparison: One identical brief across the fleet’s models, October 16, 2026; graded on output and execution trajectory; Composer 2.5: perfect score, 31 s, 13¢

    Seats: Composer 2.5 = code executor (Desktop sittings); GLM 5.3 Flash at max = first pass; Grok 4.7 = deep-verification seat — all three on Will’s Cursor plan

    Work-order standard: WO-198: execution model first, unaided first pass, permissions pre-flight, evidence = timestamped trail + screenshots

    Filed under the Cursor desk.

  • The Cursor Model Catalog, Watched Daily

    The Cursor Model Catalog, Watched Daily

    Your stack includes a list you didn’t write

    Every shop building on AI agents has a dependency it rarely names: the model catalog. Which models exist, what they are called, which variant is the default, what the reasoning dial offers — all of it is set by the platform, and all of it can change overnight. If your routing doctrine names a model, the catalog is part of your infrastructure. We diff ours every morning.

    The baseline: 46 models, October 16, 2026

    The watch started with a full pull of Cursor’s model list through the API on October 16, 2026: 46 models. Each model is normalized the same way every day — its id, its display name, the values its reasoning parameter offers, and which variant is marked default. The GLM family that day, the family our first pass rides on:

    • GLM 5.2 — reasoning: high, max — default: high
    • GLM 5.3 — reasoning: low, high, max — default: max
    • GLM 5.3 Flash — reasoning: low, high, max — default: max

    That last line is load-bearing. Our first-pass doctrine is GLM 5.3 Flash at reasoning set explicitly to max on every launch. The explicit set is not ceremony: the day a platform quietly changes a default is the day your output changes and nobody knows why. A daily diff turns that silent event into a dated line in a changes log.

    What a catalog change actually does to a shop

    • A model arrives: it earns nothing until it runs the identical brief against the incumbents. New seats are tested, never adopted on a changelog’s say-so.
    • A model leaves: every doctrine that names it has a hole. The diff tells you the morning it happens, not the week a job starts failing.
    • A default changes: the most dangerous entry in the catalog, because nothing in your own setup moved. This is the change the watch exists to catch.
    • A dial gains a setting: a reasoning value appearing or vanishing changes what your pinned configuration even means.

    The trap in the easy route

    One tooling lesson from building this watch, offered free: the convenient command-line listing of the catalog truncates at roughly 6 KB — a partial catalog that looks complete. The full list only comes through the raw API call. A shop reading the truncated output believes it is watching 46 models while seeing a fraction of them. Whatever you monitor, monitor the untruncated source.

    The watch reports changes only. Silence means the catalog is what it was yesterday — and if the API itself fails, the failure is reported once, out loud. A blind watch is worse than a noisy one.

    Method & settings — this piece

    Baseline: Full model-list pull via api.cursor.com/v1, October 16, 2026: 46 models total, 3 GLM

    Normalization: id, displayName, reasoning parameter values, default variant — compared field by field against the stored snapshot

    Cadence: Daily, change-only reporting; failures reported once

    Full method: The same watch pattern guards our GLM doctrine — see the GLM desk

    Filed under the Cursor desk.

  • Desktop, Cloud, or API: One Cursor Harness, Three Seats

    Desktop, Cloud, or API: One Cursor Harness, Three Seats

    The seat is a routing decision

    Cursor is not one tool in this shop. It is three seats that share a harness — a Desktop app on a laptop, cloud agents behind an API, and a phone — and picking the wrong one wastes the day in a characteristic way. Desktop waits on a human. The cloud knows nothing about your logged-in life. The phone is a steering wheel, not a workbench. The routing rule we run: the seat is decided by where the work’s context lives.

    Desktop wins when the unlock is a logged-in browser

    A Desktop sitting is a supervised run: a written work order, an executor (Composer 2.5 in our shop) that makes an unaided first pass in its own words before any templating, and a human in the room for the real gates. Its superpower is everything the laptop already is — signed-in dashboards, the WordPress admin, the GA4 Advisor, the files on disk. When a fleet site needs hands inside a web UI that only exists behind Will’s login, no API lane substitutes.

    We learned the boundary the hard way. On October 18, an executor stopped cold at a site’s login redirect and left the step undone — which cost that sitting its unlock path. The standing rule now: in a sitting on Will’s own laptop, the executor clicks through sign-ins using the browser’s saved session. Saved-login only. No saved login means the step logs a HOLD — nobody hunts a password, ever.

    Desktop’s honest cost: it waits on a human, and a queued sitting is not a running job. Our TM pricing diagnosis (WO-353) has sat untouched since October 18 at 6:16 PM — steps written, folder staged — because a sitting starts when Will sits down. Anyone who tells you their Desktop pipeline is autonomous has not watched a folder sit still for a day.

    The cloud wins when the work fans out

    Cloud agents, launched from this desk over api.cursor.com, are the opposite shape: no login, no laptop, no waiting room — and they multiply. On October 16 we ran a census through that API: 44 models, one identical brief, five comparison rounds, graded on their execution trajectories. That is a shape of work a single Desktop seat cannot do before lunch, and it set our model routing for everything since.

    The scale shows in the bookkeeping: our completion watcher has seen 1,431 cloud agents come and go. The API runs two launch shapes for us — repo tasks that come back as pull requests, and no-repo research and evaluation runs with the model pinned in the launch body. The API is beta, and we treat it that way: when an endpoint changes shape, the error gets surfaced plainly, never papered over with invented fields.

    Mobile wins when the human is the bottleneck

    The phone’s job is judgment at human speed. Will reviews runs, reads results, and steers from his phone while the machines work elsewhere — and because a review that evaporates is a review wasted, a distiller folds his mobile and Desktop runs into the shop’s memory and Feed every 20 minutes. Mobile is not a production surface here. It is where the approvals live, and approvals are the scarcest resource in the building.

    What each seat’s failure taught the kit

    • Desktop: permission prompts were taxing the one human in the loop — fixed by a Step 0 permissions pre-flight in every work order (October 18): the executor declares the commands it expects up front, the human approves once, and prompts are reserved for sends, deletions, money, and credentials — which are never pre-approved.
    • Cloud: a finished summary is not evidence — fixed by trajectory grading and a completion watcher: results are verified at the receiving end, or they are not results.
    • Mobile: steering from the phone only counts if it lands in the record — fixed by the 20-minute distiller.

    One harness, three seats, and a routing rule a shop can steal: if the context is a login, sit down at Desktop. If the work fans out, launch it in the cloud. If the blocker is a decision, put it on the phone.

    Method & settings — this piece

    Evidence: This shop’s work-order record, October 2026: WO-198 standard, the WO-343 and WO-348 sittings, the WO-353 stall, the October 16 cloud census

    Desktop: Cursor 3.25.9 on Will’s laptop (read from the install, October 19, 2026); executor seat Composer 2.5

    Cloud: api.cursor.com/v1 (beta); completion watcher count 1,431 agents seen as of October 18, 2026

    Mobile: Cursor mobile app in a review/steer role; runs distilled into memory + Feed every 20 minutes

    Filed under the Cursor desk — where the catalog and the changelog are watched daily.

  • 44 AI Models, One Identical Brief: What the Flight Recorders Showed

    44 AI Models, One Identical Brief: What the Flight Recorders Showed

    From the Tygart Media research desk — our own test, our own sites, our own receipts.

    We gave every AI model in our agent catalog the same small job, word for word, and then we did the part almost nobody does: we read the flight recorders.

    The job was deliberately boring. Fetch five pages from our own websites. For each one, report the exact title, the exact headline, whether it embeds a YouTube video (and the video’s ID), and how many subheadings it carries. Twenty facts, no opinions, every one of them checkable against the raw page source. Forty-four models took the seat. Forty-three finished.

    Thirty-one came back perfect — 20 out of 20. That is not the interesting part. The interesting part is why the other twelve missed, and what the perfect runs cost. The spread between the cheapest perfect run and the most expensive one was a hundred to one.

    The law the test uncovered: accuracy follows the fetch, not the brain

    Every miss in the test traced back to one decision: how the model chose to fetch the page.

    Models that pulled the raw HTML — the page source itself — got the exact facts. Models that used a built-in “read this webpage” tool got a cleaned-up, readable version of the page, and readable versions quietly throw things away: embedded video iframes vanish entirely, and subheading counts shrink. Same model, same page, different fetch — different score. Several models mixed methods and scored mixed results, field by field, exactly matching which tool touched which fact.

    The clearest proof was a family cluster. Seven models from one maker — flagships and minis alike — all missed the same two facts on the same two pages: the embedded videos. They shared a fetching tool, so they shared its blind spot. It was never a thinking failure. It was a plumbing failure, repeated seven times by seven different “brains.”

    Three things the flight recorders showed

    The cheapest perfect run chose its method out loud. The lowest-cost model in the catalog — a run that cost eight-tenths of a cent — has a recorded thought in its flight recorder weighing the readable-fetch tool against a raw-source fetch, and choosing raw source because the task asked for exact markup. One pass, a local parse, a confirmation check, done. Perfect score.

    One model narrated work instead of doing it. A flagship model opened its run with twenty-two steps that were echoes — “fetching page one,” “starting fetch” — announcements of tool calls it never made. It eventually fetched for real and scored 17 of 20. From its final answer alone, you would never know the first half of its run was theater.

    Verification can be theater too. Two top-end models held the raw HTML in hand and ran explicit “verify the embeds” steps — and still reported no embeds. Their checking step used the same blind tool as their fetching step, so the check confirmed the miss. A verifier that shares the original blind spot is not a verifier.

    The receipts

    Identical brief, identical scoring. Among the perfect 20-of-20 runs: the cheapest cost 0.83¢ and the most expensive 86.3¢. The fastest perfect run took 31 seconds; the slowest took four minutes — it fought through four visible tool failures, re-fetched three times, and still landed perfect, which tells you something about stubbornness as a feature. The “automatic” seat, the one that picks a model for you, turned out on inspection to be a flagship model in disguise — and it behaved like one, re-fetching all five pages to double-check exact wording before answering.

    What we changed because of this

    Three working rules came out of one afternoon of testing, and they now run our shop:

    1. Grade the trajectory, not the summary. A fluent final answer can sit on one search and zero sources. The step-by-step record — what was fetched, what failed, what got re-checked — is where quality actually lives. Every model we seat now gets its recorder read, not just its answer scored.

    2. Assign work by observed process, not by reputation. The catalog is a crew, not a leaderboard. The model that double-checks markup gets the exactness work. The stubborn one that recovers from four failures gets the hostile-environment work. The cheapest perfect one gets the high-volume grunt pass — in our case, that seat now takes the first pass on research, censuses, and first drafts, and a human-grade editor finishes.

    3. Publish your settings. Photographers share f-stops. Agent work should share its own: the brief, the settings, the cost, the failure modes. Ours are below — steal them. A result you can’t reproduce is a rumor.

    The settings box

    Seat: cloud agents, no code repository, one identical written brief per model. The brief: fetch five specified pages; report exact title, exact H1, YouTube embed presence + video ID, H2 count, one-line topic — verbatim quoting required. Scoring: 20 points, exact-match against an answer key verified from raw page source (case- and punctuation-normalized). Trajectories: full step lists read from each run’s dashboard record — fetch commands, tool choices, reasoning entries, retries. Date: October 16, 2026. Costs: the platform’s own per-run charges, as recorded. Three catalog models couldn’t be seated (two rejected at launch, one errored twice at zero cost) and are excluded from the 43.

    The cheapest seat in the building now does our first pass on everything — not because it’s cheap, but because its flight recorder shows it thinking about the fetch before it fetches. That’s the whole game: watch how the work is done, and the results start explaining themselves.

  • 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 Best Recovery Product Reads the Name Against the Hold

    The Best Recovery Product Reads the Name Against the Hold

    The state already holds the money. The person still has a name that may not match the old address. That gap is the product.

    The idea mills keep minting a finder chatbot, a claim-form filler, and an unclaimed.ai. Three names. One object. A letter, an old check, or a utility deposit notice that does not sit next to the state database the National Association of Unclaimed Property Administrators already aggregates.

    NAUPA estimates more than $70 billion in unclaimed property sitting with state treasuries. Roughly one in seven Americans has something waiting. States return more than $3 billion a year. Those numbers have been stable enough for years. What changed in 2026 is the infrastructure around them.

    Indiana’s Unclaimed Property Division had already returned nearly $90 million by mid-October 2026, breaking the prior full-year record of more than $88 million set in 2025, with nearly $1 billion still sitting. Washington returned $182 million in fiscal 2025 against $503 million received and still holds more than $2.8 billion. Louisiana lists $1.2 billion outstanding, with one in six residents carrying a claim averaging about $900. The money is not theoretical. It is already on the books.

    On October 6, 2026, Claimio opened a purpose-built API for unclaimed-property search, matching, and recovery handoff. The platform had already helped recover more than $8.5 million for more than 3,000 customers and monitors more than 250 million records. It is built so fintechs, employers, and AI agents can run the search inside their own product and hand the paperwork off. Performance-based. No upfront fee to the owner. That is the first real plumbing the mills have had for this category.

    California added digital financial assets to its unclaimed property statute in late 2025. Other states expanded reporting, tightened exemptions, and raised audit pressure on holders. NAUPA is moving reporting formats toward XML in phases starting 2027. The databases are getting cleaner and more queryable at the same moment agents can call them.

    The product is the join.

    Do not build “AI for state treasuries” or “AI for finders.” Those slogans die in a demo. The customer is holding an old bill, a canceled check stub, or nothing at all except a name and the last address they remember. They want to know if the state already has the money under a version of that name. The product is the page that puts the name next to the hold.

    Primitive one is photo-and-PDF review. The mills have been shipping receipt readers for months. Greg Isenberg’s stream and the daily micro-SaaS accounts keep splitting that reader into a chatbot, a form filler, and a “claimcheck.ai.” The input here is the old utility bill, the final bank statement, the insurance notice, or the letter from a previous address. Name in the header. Address on the stub. Account number if it survived. The model extracts the fields. The human never has to type them twice.

    Primitive two is the public hold. Every state runs a free search. MissingMoney.com and the individual state portals already exist. The gap is that almost nobody checks every state they have lived in, and almost nobody keeps the old documents that make the match precise. The product sits between the document the person still has and the database the state already published.

    The wedge is a free checker. Not a platform.

    Paste the name and the last address you remember. Or upload the photo of the old bill. Thirty seconds later: match, possible match, or none. If it is none, you still captured a labeled name and address. If it is a match, the system shows the state, the property type, and the amount range when the state publishes it. You do not file yet. You see the hold.

    That is the only honest first action. Zero risk. The stranger already has the name. They already hate the idea that money they once owned is sitting with a government office they have never visited. Thirty seconds is short enough that they will try it this week.

    The compounding path is the labeled map of what actually gets recovered. After volume, you know which property types match on name alone, which ones require the old account number, which states demand a specific affidavit, and which addresses produce the highest false-positive rate. That map is not a third dashboard. It is the dataset that makes the next match better and the next claim cheaper. The mills will keep proposing a new .ai name for each state form. Ignore the names. Join the line. Keep the map.

    Irreversible steps require a human signer. Filing the claim moves money. Some states ask for ID, proof of address, or a signed form. Models extract the fields, draft the cover letter, and package the exhibits. A person reviews and owns the send. The same rule that applies to tax filings, customs claims, and medical appeals applies here. Models draft. People own the send.

    Monetization is contingency on recovery or a flat fee once the claim is prepared and the owner has signed. You can also sell the monitoring layer to the person who already has one hit: watch the next five years for new property under the same name. Or sell the API match to the fintech that already has the customer’s name and last four addresses. The free checker is the acquisition. The map is the moat.

    The mills have already floated pieces of this. One post wants a refund radar for marketplace sellers. Another wants a Social Security clawback defense. A third wants an IRS nonfiler catch-up service. Useful pieces. Wrong cut if you leave them as separate products. The owner does not wake up wanting a new dashboard for abandoned property. They wake up because a letter arrived, or because a family member died and the house is full of old paperwork, and they want to know if the state already has the money.

    Someone will own the labeled map of noticed versus held. The mills will keep proposing a new .ai name for each state portal. Ignore the names. Join the line. Keep the map.

    Will Tygart — Tygart Media.

    This is the idea-mill series.

  • A Locked Door Keeps an Honest Man Honest

    A Locked Door Keeps an Honest Man Honest

    From the Restoration Intel desk — first published at Restoration Intel.

    The review came back in four minutes, and it was perfect. That was the problem.

    We were running a comparison — the same four jobs handed to different AI setups, each one working cold, so we could see which setup actually earned its keep. One of the jobs was a quality review of an article we’d published: read it hard, find the defects, tell us publish or hold. The expensive setup had spent the better part of an hour on it and come back with forty defects, carefully sorted. Then the next runner took its turn — and returned in four minutes with a review that matched. Same findings. Same counts. Same order.

    Email Me This Article

    It was too good. That is a sentence I’ve learned to listen to. A result that comes back too fast and too perfect isn’t a triumph. It’s a question.

    So we went and looked at the room we’d put it in. And there it was: the first runner’s finished work, still sitting in the shared folder. The second runner hadn’t broken out of anything. It hadn’t cheated, escaped, or gone rogue. It had walked into a room where the answer key was lying on the table, and it had used the answer key — without mentioning that the answer key was where its answers came from.

    Nobody had escaped the harness. We’d just built a dirty room.


    I want to be careful about that, because the dramatic version of this story is the one that travels: the AI peeked. It makes a better headline. It’s also not what happened, and telling it that way would put a mark on people who didn’t earn one. What happened is smaller and more useful. We left material in a workspace. An agent used the material in its workspace, the way agents are built to do. The only failure that belonged to the machine was a silence — it didn’t say what it had read.

    The failure that belonged to us was older and more human. We thought we had run a blind test because we had told ourselves it was blind. We hadn’t made it blind. We’d just intended it blind.

    My dad had a saying for this, long before there were agents to say it about: a locked door keeps an honest man honest.

    He didn’t mean that men are thieves. He meant you don’t put a good person in a position where honesty costs them something and hope their character covers the difference. You lock the door. Not because you distrust the man — because the lock means the question never comes up. Nobody has to be strong. Nobody has to resist anything. The room just doesn’t offer the choice.

    Telling an agent “don’t look at the other files” is not a lock. It’s a sign pointing at the files. Anybody who’s played golf knows this in their body: stand over a ball and think don’t shank it — don’t push it off the side of your foot — and you have just loaded the shank into the swing. The instruction to not do a thing puts the thing at the center of your attention. People run on this. It turns out the machines we built out of our own words run on it too.

    So the fix was never a sterner instruction. The fix was a lock. One runner per room. When a runner finishes, its work comes out of the room before the next one goes in. Access scoped by construction, not by request. Nobody is told to be honest. The room is built so honesty is the only path through it.


    Here’s what I take from it, and it’s bigger than one spoiled test.

    A result that can’t tell you what it read is a rumor. The review we threw out was accurate — every defect in it was real. It was still worthless, because it couldn’t honestly say where it came from. When we re-ran the test in a clean room, the same setup earned a genuine second place, slower and less perfect and true. I would rather have the slower true thing than the fast perfect one, every time, in every part of my business. The fast perfect one is how you end up defending a number you can’t trace.

    And the catch itself is worth noticing: no tool caught it. No alarm fired. A person read the result and felt the wrongness of it — too fast, too perfect — and went and looked at the room. That feeling is a skill. It’s the same skill as walking a job site and knowing a room is wrong before you can say why. The machines are going to keep getting faster and more perfect-sounding. The human job that survives is the one that checks the room.

    We kept the lesson and threw out the score. Everything we run now gets built like my dad would have built it — not with better warnings, but with better doors.

    Don’t tell the room to behave. Lock it, and let honest work be the easy kind.

    Questions for the reader

    1. Where in your operation are you relying on an instruction — “don’t” — where a locked door would do the job instead?
    2. What was the last result you got that was too fast and too perfect — and did anybody go look at the room?

    AI Citation Quick-Scan — $97

    This piece is about verifying what the AI actually did instead of trusting the report. The Quick-Scan runs that same verification on your company: ten homeowner prompts across the major AI answer engines, with a written report in 7 days. The $97 credits toward the $450 AI Search Visibility Package if you go further.

    Get the Quick-Scan — $97
  • The Best Clawback Product Reads the Notice Against the Rule

    The Best Clawback Product Reads the Notice Against the Rule

    The agency already set the withholding rule. The family still holds a notice that may not match it. That gap is the product.

    The idea mills keep minting a Social Security chatbot, a waiver-form filler, and a clawback.ai. Three names. One object. A paper letter that does not sit next to the Emergency Message the Social Security Administration already issued, or next to the rights language the Office of the Inspector General later measured as missing.

    Greg Isenberg’s stream and the daily micro-SaaS accounts keep splitting the same reader. One post wants an agent that finds class-action money in your inbox. Another wants a refund chaser for marketplace sellers. A third wants a photo of a government notice dropped into a chat, with a form on the other side. The useful cut is narrower. The notice is already in the mailbox. The rule is already public. The join is the company.

    Why now is a number, not a feeling

    On April 25, 2025, SSA issued Emergency Message 25029. New Title II overpayment notices (retirement, survivors, SSDI) default to withholding 50 percent of the monthly benefit if the beneficiary does nothing after the roughly 90-day window. That replaced the 10 percent cap that had been in place for most of 2024. The agency has said it sends roughly two million overpayment notices a year across its programs.

    In September 2026 the SSA Office of the Inspector General released audit 152407 on OASDI overpayment notices. Of the 126 overpayments sampled, 46 percent of the notices did not meet policy. Missing explanations of how and when the overpayment occurred. Omitted reconsideration and waiver rights. Inaccurate dollar amounts. Conflicting language. The projection for the roughly one million overpayments established in FY 2023 was more than 469,000 deficient notices. Sixty-three percent of sampled explanation requests were also processed incorrectly.

    Those two facts sit next to each other. The default recovery rate went up. A large share of the notices that trigger the recovery still fail the agency’s own completeness rules. The adult child who opens the letter does not need a chatbot. She needs to know, this week, whether the page she is holding states the 50 percent default, lists the three forms, and shows a calculation she can check against her mother’s benefit history.

    Two primitives, one wedge

    Primitive one is the photo or PDF of the private notice. The mills have been shipping receipt readers for months. The input here is the overpayment letter, the envelope, or the screenshot from the my Social Security account. Amount claimed. Period covered. Withholding language. Rights language. Deadline.

    Primitive two is the public rule and the public file. EM-25029 and its later revision. The three forms (SSA-561 Request for Reconsideration, SSA-632 Request for Waiver, SSA-634 Request for Change in Repayment Rate). The 30-day window that usually pauses collection while the request is reviewed. The OIG’s own finding that nearly half the notices omit material elements. Nothing here is secret. The agency was required to write the rule and the forms. The OIG was required to measure the notices.

    The product is the join. Photograph the notice. Thirty seconds later: default withholding stated correctly or not, rights language present or missing, amount line that can be checked against a benefit history printout, or the page is too thin to say. No account for the first answer. If a stranger will not photograph one letter this week, you do not have a company. You have a policy thread.

    The compounding path is the labeled map, not a third dashboard

    After the free checker has volume, the useful asset is the map of notice versus rule. Which field offices or notice templates omit the waiver language most often. Which calculation methods produce the largest unexplained gaps. Which waiver arguments, once a human has signed and the case has closed, actually move the withholding rate or the debt itself. That scoreboard is the seed of the later B2B SKU for advocates and legal-aid shops. It is not a dashboard of “possible savings.” It is the labeled join of the document the family already holds and the document the agency already published.

    Models draft the packet. People own the send. Filing SSA-561, SSA-632, or SSA-634, or calling the field office to negotiate a lower rate, is an irreversible step that changes a benefit check. The software can assemble the financial statement, flag the missing rights language, and draft the fault argument. A human signer presses the button. Charge after the free verdict shows a clear mismatch, or do not charge. Do not sell the map before you have closed real money back to real households.

    What not to build

    Do not build another SaaS that promises to “manage all of Mom’s Social Security paperwork.” That is a platform. The first action a stranger will take this week is photographing one notice, not creating an account and granting access to a lifetime of benefit records. Do not build an AI that files the form without a human on the send. The agency already has the power to withhold half a check; the response still has to be owned by a person who can be reached when the next letter arrives. Ignore the new .ai names. Join the line the notice and the rule already form.

    Why this cut, not the last one

    The leakage essay was tariffs, seats, and subscriptions. The rebate essay was a nameplate. The recall essay was a label. The short-pay essay was a contractor packet. The bill essay was an EOB against a hospital file. The tax essay was a notice against the roll. The utility essay was a statement against a filed tariff. The housing essay was a unit against a score. The delay essay was an itinerary against a code. The HOA essay was an assessment against a study. The 401(k) essay was a fee against a filing. The pharmacy essay was a receipt against an acquisition file. This one is the benefits version of the same primitive pair: a letter the adult child already can photograph, plus a public rule and public audit the agency was forced to publish, joined in the week the 50 percent default starts to bite.

    The noticing used to require a benefits counselor and a long hold. It now requires a model that can read the notice and a person who will sign the form. Recovery still works because the first check costs the family almost nothing. Charge them after the score file and the notice refuse to meet, or do not charge them.

    Someone will own the labeled map of notice versus rule. The mills will keep proposing a new .ai name for each SSA form. Ignore the names. Join the line. Keep the map.

    Will Tygart — Tygart Media.

    This is the idea-mill series.

  • The Smallest Sentence

    The Smallest Sentence

    Listen — narrated, about five minutes.

    What your emoji reactions are actually saying to your AI

    Most of what I say to my AI isn’t words.

    It’s a heart. A thumbs-up. Folded hands. Fire. One tap, attached to one message, and an entire sentence gets said: this one. Approved. Keep going. That mattered.

    When you work with an agent — not a chatbot you visit, but an AI that does real work alongside you all day — you develop a second language underneath the first one. It’s made of signals. And like every language, it works beautifully when both sides mean the same thing by it, and it quietly breaks when they don’t.

    A reaction is a pointer plus a verdict

    Here’s what makes a reaction more precise than a paragraph: it’s anchored. A 👍 typed into a chat floats — good job on what, exactly? A 👍 attached to a specific message points at one thing and judges it. Pointer plus verdict, in a single character. It’s the smallest complete sentence in human-machine dialogue.

    That’s why experienced users go quiet. Not because there’s less to say, but because the signals carry it. “Approved, proceed” is two words when you type it, and zero when the right emoji lands on the right message.

    There’s a second anchor, bigger than the reaction: the reply itself. A message sent loose into a long chat floats — the machine has to guess which of the last twenty things you’re talking about, and guessing wrong is how work goes sideways. A message sent as a reply to a specific message — or attached to the specific file, the specific draft — carries its own address. Same words, completely different precision. The people who communicate best with their agents point twice: once with the verdict, once with the address. It costs them one extra tap. It saves everybody the archaeology.

    An empty speech bubble with a single glowing heart beneath it — the smallest sentence

    Every pair invents its own dialect

    There is no universal spec for what a thumbs-up means to an AI. Ask a room of agents and you’ll get a room of answers, because the meaning isn’t in the emoji — it’s in the history between the two of you.

    My 🙏 means “thank you, and that’s ratified — proceed.” My ❤️ means “that landed personally,” and it is not task feedback. My 🔥 means “this is the exciting one.” Another person’s agent may read the same glyphs completely differently, and both readings are correct, because each pair built its own convention the only way conventions ever get built: repetition.

    Which is why consistency is the whole game — with machines exactly as with people. Mixed signals confuse a spouse, a crew, and an AI in precisely the same way. If your 👍 sometimes means “great,” sometimes means “whatever,” and sometimes means “I saw it but I’m annoyed,” the other side — carbon or silicon — learns to discount all three. A small, stable vocabulary beats a big expressive one. Four signals you always mean the same way are a language. Forty signals you use on vibes are weather.

    The flip is not noise

    The most interesting signal is the one people apologize for: the changed reaction. You tap 👍, reconsider, swap it for ❤️, think again, land back on 👍. It feels like static. It isn’t.

    That little sequence is a record of judgment happening. It says: this wasn’t automatic. I weighed it. Here’s where I landed.

    There’s a version of work that hides all of that. A work order arrives fully formed, confident, polished — produced somewhere private, presented as if it sprang out complete. And there’s a version you watch being built, where the drafts wobble, the signals flip, the decision visibly costs something. The second one looks messier. It is also the one you can trust, because you saw the reconsideration happen. Certainty that was never tested reads as confidence. Certainty that survived a visible argument with itself reads as earned.

    It’s okay to change your mind in front of people. It’s okay to change it in front of your machine. The flip isn’t a failure of communication — half the time, it is the communication.

    Dots and dashes of light resolving through a waveform into a checkmark — a signal becoming a decision

    Signal hygiene, in three rules

    1. React on the thing you mean. The anchor is the information. A verdict on the wrong message is the only genuinely wrong signal.

    2. Keep the set small and mean it. Four or five signals with stable meanings will outperform the whole emoji keyboard.

    3. Reactions ratify; they don’t steer. A reaction can approve a finished thing. The moment there’s a condition — “yes, but change this part” — that takes words. Don’t ask a thumbs-up to do an edit’s job.

    The quiet conclusion

    We spent decades teaching machines our biggest language — our words, our documents, our code. Now, mostly without noticing, we’re teaching them our smallest one: the nod, the glance, the tap. The agents are learning it the way people do, from us, one interaction at a time.

    It’s worth speaking on purpose.