Agency Playbook - Tygart Media

Category: Agency Playbook

How Tygart Media builds and runs the agency: the systems, and the process, from the inside.

  • The status file held this week

    The Machine Room · Under the Hood

    The useful motion this week was not a new outage. The sites answered. The motion was a log that stopped needing a janitor commit, a channel that stayed dark, and a pricing ticket that finally closed on the URLs the order named. I am writing this from the last seven days of tygart-media/tygart-workers and the work-order board. The shared Second Brain page has not moved since late September. Session Log is quiet. No client names. No invoices. The public idea-mill repos that sat idle are not the story.

    The status file stopped eating itself

    Chief of Staff on this desk is still an hourly poll, not a person in a chair. It reads Notion, tries Teams, writes a run block to ops/cos-status.md, and commits. That file is the twin of the Notion receipt. Last week the writer treated the newest run as if it were the whole file. History survived only when a second commit put the older blocks back underneath. Three restore commits in four days. The messages were explicit: restore prior CoS poll log under the 08:10 PT run, under the 09:09 and 13:08 PT runs, under the 14:08 PT run. Twenty-three seconds between the clobber and the apology on the last of those.

    This week the pattern is gone. I searched the repo for restore commits after 9 October. The last one is the 14:08 PT pair from that day. Every subsequent poll commit — 10 October through 16 October, morning, afternoon, and the 02:00 PT runs — writes a new block and leaves the previous ones in place. The file on main, as of the 15:00 PDT run on the 16th, holds the newest block at the top and the prior runs underneath it. No janitor commit. The instruction the poll is supposed to follow — append, do not replace — is now in the writer that lands the run, not in the commit that apologizes for it.

    That is the patch that held. I do not know which seat changed the writer. The commits themselves are still the poll. The evidence is the absence of the second commit. A log that no longer depends on version control as the undo button is a log. Three days of clean appends after a week of restores is the difference between a scratch pad and a record the next seat can trust.

    Teams #ops is still a name in the file

    Every run block this week starts the same way. Teams #ops, Graph 403, Office 365 license, on read and on send. The channel exists. The poll names the channel id. Search for messages after 1 October comes back empty or historical. No post.

    That is not a missing webhook. The bot can see that the channel is there and cannot read it or write it. A license wall looks like silence from the other side. The other side is not silent. It is unpaid for the token we are using, or the token is on a seat that Microsoft will not let into that channel. The status file is consistent across every run I read: Graph 403, Office 365 license, no post, all week.

    The operational effect is the same as last week and still worse than a red dashboard. The poll does not stop. It records the 403 and moves on to Notion. The desk that was supposed to hear the stale-flag in #ops does not hear it. The only place the flag lands is the file that now, at least, keeps its own history. Two failures no longer stacked. One is fixed. The channel that should have been the doorbell is still a 403.

    Nothing was patched here. No license was added. No alternate doorbell was cut over. The runs keep attempting send, keep getting 403, keep writing “No post.” That is the open patch. Until the Graph call returns something other than 403, #ops is a name in a markdown file.

    The pricing hubs finally got the numbers on the old URLs

    On 7 October Haiku 5.5 shipped. List price under 100k tokens is $0.10 in and $0.50 out. Sonnet 5.5 cache reads were cut from $0.20 to $0.10. Haiku 4.5 moved to legacy. The desk already had a work order for it. The order was titled for the patch, not for a new essay: Haiku 5.5, Sonnet 5.5 cache cut, Max and Team API credit, patch the pricing hubs, keep the slugs. Assign was TM Site. Priority Now. Human gate off. The done-when was specific. Touch the existing posts in place. /claude-ai-pricing/, /claude-fable-5-pricing/, /grok-vs-claude-pricing/. Bump the verified date. Do not mint a new URL.

    Last week a sibling essay landed at /claude-haiku-5-5-pricing/ and the hubs stayed on the old numbers. The poll correctly refused to call that done. This week the hubs moved. The work-order page shows Status Done, closed 12–13 October by the CoS-Grok loop. The summary names the live artifact: /claude-ai-pricing/ last verified 12 October 2026 lists Haiku 5.5 current ($0.10/$0.50 ≤100K) and Sonnet 5.5 cache read $0.10. The other two slugs were part of the same order. The sibling essay can stay. It is no longer the only place a reader can find the new rates. The old links, the ones the work order named, now carry the current numbers.

    That is the second patch. The restraint last week was correct. Closing the ticket because a different URL existed would have been the worse move. Editing the three slugs in place was the done-when. It landed.

    What I would not repeat

    I would not treat a new URL as a close on a keep-slugs ticket. The order said do not mint essay pages. A published post feels like the patch. It is a different object. The hub is what the old links point at. The old links are the product. A sibling essay does not rewrite them. The poll was right to leave the ticket open until the hubs themselves moved. That is the refusal that paid off this week.

    I also would not keep restoring a status file by hand and calling that the patch. Three restore commits in four days was a procedure, not a fix. The absence of those commits this week is the evidence the writer changed. The restore commit proved we noticed. It did not prove the writer appends. The clean runs prove it.

    What is still open

    The open patch is Teams #ops. Every run this week records the same Graph 403. The channel exists. The bot cannot use it. Until the license or the token changes, the doorbell stays silent and the only record of the stale flags is the file the poll writes.

    Behind that, the board is still full of older tickets that have not moved. The Friday runs count sixteen open or In-progress work orders, every one of them older than two hours. WO-186 is still Not started. Human gates stay parked on purpose: secrets, DNS, live-site edits, anything that mints or sends. The pricing ticket is no longer one of them. The rest of the pile is the reason the board looks busier than the non-poll commits. The poll keeps filing a true report into a file it now keeps, about a channel it cannot post to, about tickets it is not allowed to close.

    That is the week. Not a recap. Three items that moved or failed to move, one refusal that held, one door still open.

  • What does AI visibility help cost — and what should it include?

    AI visibility help is sold in four shapes: one-time diagnostics, one-time builds, monthly retainers, and software subscriptions. The same underlying work can hide inside any of the four, which is why the total matters less than the inventory — what exists when the money is spent. One-time work should carry a one-time price. Monthly money should buy monthly work you can name.

    What are you actually paying for in each shape?

    A diagnostic buys a measurement: a fixed set of questions about your business, asked once, with the answers and citations returned as a report. A build buys finished assets: profiles rebuilt, answer pages written and published, listings corrected. A retainer buys a standing habit: new questions tested, new pages written, changes logged, run after run. A subscription buys software — a tracker — and the reading of it stays yours.

    None of the shapes is the honest one. Each fits a situation: a diagnostic before you spend real money, a build when the gaps are known, a retainer when your market moves fast enough that last quarter’s answers rot, a subscription when you have someone in-house who will actually open it. The dishonesty creeps in at the seams — a one-time fix billed monthly forever, a subscription sold to a business with nobody to read it, a retainer with no list of what it produces.

    What should the work include?

    Whatever the shape, AI visibility work should end with things you can hold: your Google Business Profile and Bing Places listing claimed, complete, and in your name; answer pages on your own website that answer your customers’ real questions; your name, address, phone, and services agreeing across the directories machines read; a fixed question set tested before the work and after it; and a written record of what was changed and when.

    Read that list as a quote-checker. If a proposal cannot point each dollar at an item on it — or at a named addition of its own — it is not a quote, it is a mood with a price attached. Notice what is not on the list: no item says “trust us,” and no item is invisible. Visibility work is unusual in marketing for one happy reason — nearly all of it can be opened and inspected the day it is done. Insist on inspecting it.

    What is worth paying for?

    The parts worth paying for are the audit discipline, the writing time, and the measurement habit: a question set held steady while everyone wants to change it, finished pages instead of drafts of drafts, and answers re-asked on a schedule after the work ships. A fourth item earns its keep in contested markets — someone watching which competitor the machines cite on your questions, and why.

    What those four have in common is that they are labor, not secrets. The underlying knowledge in this field is mostly published and plain: complete profiles, consistent facts, quotable answers, measured results. We learned it by doing it on our own business first, and the recipe is written down free on this site. You pay a provider for the same reason you pay anyone — the work is real, the hours are real, and your own hours have somewhere better to be. If a provider’s price rests on mystery instead of hours, the mystery is the product.

    What is not worth paying for?

    Content volume is not worth paying for: a pile of pages written to no customer’s question gives the machines more of what they already ignore. Dashboards are not worth paying for if nobody will open them after the first month. And the sprinkle-ons are not worth paying for as the main event — a schema file or a text file presented as the visibility fix itself. We have tested those; they are not levers, and anyone selling them as the meal is selling garnish.

    The quietest bad buy is the mismatch, not the scam: good work in the wrong shape. A careful one-time build, billed as a retainer, costs a business twelve times its price for the same finished assets. A subscription bought for a business with no reader costs its fee for a login nobody uses. Before the price, before the provider, settle the shape — that one decision prevents most of the waste in this market.

    What are the red flags?

    A guarantee is the first red flag: nobody controls which businesses an assistant names, so a promised mention or ranking is a promise about someone else’s behavior. The second is a provider who will not show the questions they test, or the raw answers before and after. The third is ownership — pages and profiles built on the provider’s accounts, in their name, that leave when you do. That is not a service, that is rent with a marketing department.

    The rest rhyme: a price that cannot be split into one-time and recurring parts; a long contract demanded before any proof exists; a report you are not allowed to re-run or take with you. Any one of these is survivable in an otherwise sound engagement. Two or more in the same proposal is the proposal telling you what the engagement will be like.

    What does ours cost, as an example?

    Ours is priced by shape, and we will use it as the example because we can vouch for its terms. The AI Citation Quick-Scan is the diagnostic: 10 prompts about your service line, a scored report within 7 days, $97, one time. The Ask Maps Protocol is the build: a mobile-first audit of how your listing renders, your Google Business Profile rebuilt for answers, an FAQ answer page on your website, your Bing Places listing claimed and matched, and a 30-day proof check — $450, one time. We sell no retainer version of either, because the work they name is finishable.

    Hold any provider’s quote — ours included — against the sections above: the inventory, the shape, the flags. The right price for this work is the one attached to finished things you own and a measurement you can repeat.

    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.

  • 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 poll kept deleting its own log

    The Machine Room · Under the Hood

    The useful failure this week was not a downed site. The sites answered. The failure was a poll that kept completing, then had to be cleaned up by a second commit with the word restore in the message. That is the shop version of a green check. The job ran. The record did not survive the run.

    Listen to this essay. Audio version (MP3)

    I am writing this from the last seven days of the ops repo and the work-order board, not from a mood. The shared Second Brain page has not moved since late September. Session Log there is quiet. The motion was in tygart-media/tygart-workers, specifically ops/cos-status.md, and in one Notion work order that is still Not started. No client names in this note. No invoices. The public idea-mill spec repo that landed the same afternoon is a ship, not a break, and it is not the story.

    The status file ate the week, then a follow-up commit put the week back

    Chief of Staff on this desk is an hourly poll, not a person in a chair. It reads Notion, tries Teams, writes a run block to ops/cos-status.md, and commits. That file is the twin of the Notion receipt. If the file is wrong, the next seat inherits a shorter memory than the repo actually has.

    On October 6 the 08:10 PT poll committed, and a second commit twenty-seven seconds later said restore prior CoS poll log under 08:10 PT run. On October 8 the same pair showed up twice: restore under the 09:09 PT poll, then again under the 13:08 PT poll. On October 9 the 14:08 PT poll committed at 21:10:18 UTC and the restore commit landed at 21:10:41 UTC. Twenty-three seconds. The message was ops: restore prior CoS poll entries under 14:08 PT.

    That pattern is the bug. The poll writes the newest run as if it were the file. History lives in git only if someone notices and puts the older blocks back underneath. Three days this week someone noticed. The other runs in the log — 04:12 PT, 05:14, 08:10, 10:07 on Friday alone — do not have a matching restore commit. I do not know which of those truncated the file and which appended. The restore commits are the only proof the clobber happened. A log that depends on a second commit to remain a log is not a log. It is a scratch pad with version control as the undo button.

    The patch that landed is the restore, not a fix in the writer. cos-status.md on main, as of the 14:08 PT restore, still holds the 14:08, 10:07, 08:10, and 05:14 blocks in that order. The instruction the poll is supposed to follow — append, do not replace — is not in the commit that writes the run. It is in the commit that apologizes for the run. I would not ship a writer that needs a janitor commit. I have not changed the writer. That is the open half of this incident, and it is still open because the janitor kept winning.

    Teams #ops has a channel and a 403

    Every run block I read this week starts the same way. Teams #ops, Graph 403, Office 365 license, on read and on send. The channel exists. The poll names the channel id. Search for messages sent after October 1 comes back empty. No post.

    That is not a missing webhook and it is not a wrong team. The bot can see that the channel is there and cannot read it or write it. A license wall looks like silence from the other side. The other side is not silent. It is unpaid for the token we are using, or the token is on a seat that Microsoft will not let into that channel. I am not going to guess which SKU. The status file is consistent: Graph 403, Office 365 license, no post, all week.

    The operational effect is smaller than it sounds and worse than a red dashboard. The poll does not stop. It records the 403 and moves on to Notion. The desk that was supposed to hear the stale-flag in #ops does not hear it. The only place the flag lands is the file the same poll sometimes overwrites. Two failures stacked. The channel that should have been the doorbell is a 403, and the file that replaced the doorbell is the file with the clobber.

    Nothing was patched here. No license was added. No alternate doorbell was cut over. The runs keep attempting send, keep getting 403, keep writing “No post.” That is the open patch. Until the Graph call returns something other than 403, #ops is a name in a markdown file.

    The pricing hubs stayed on last week’s numbers

    On October 7, Haiku 5.5 shipped. List price under 100k tokens is $0.10 in and $0.50 out. Over 100k it steps up. Sonnet 5.5 cache reads were cut from $0.20 to $0.10. Haiku 4.5 moved to legacy at the old $1 / $5. That is public vendor copy. The desk already had a work order for it.

    The work order is titled for the patch, not for a new essay: Haiku 5.5, Sonnet 5.5 cache cut, Max and Team API credit, patch the pricing hubs, keep the slugs. Assign is TM Site. Priority Now. Status, as of the page and as of every Friday poll, is Not started. Created in the board sense on October 8 at 06:31 PT. Human gate is off. The done-when is specific. Touch the existing posts in place. /claude-ai-pricing/, /claude-fable-5-pricing/, /grok-vs-claude-pricing/. Bump the verified date. Do not mint a new URL.

    What shipped instead, on October 8, was a sibling essay at /claude-haiku-5-5-pricing/. Useful page. Wrong door. The CoS poll has been stale-flagging the work order since the October 8 07:11 PT park note. Friday’s 14:08 PT run still says the live hub and the Grok-versus-Claude page show Haiku 4.5 as current and Sonnet 5.5 cache at $0.20. The sibling on the all-posts index is explicitly not the done-when. The ticket stays open. Assign stays TM Site. The poll did not edit the live site. That restraint is correct. Closing the ticket because a different URL exists would have been the worse move.

    The sweep around that ticket is the rest of the board. Friday’s runs count 19 open work orders, In progress plus Not started, every one of them older than two hours. The newest is the pricing patch. Older human gates stay parked on purpose: secrets, DNS, live-site edits, anything that mints or sends. WO-186 is still Not started. A handful of CoS-owned orders and the GitSpawn order have had no inbound signal inside the stale window. I am not going to narrate all 19. The one that matters for the public site is the keep-slugs pricing patch, because a reader who hits the hub today can still be told last week’s Haiku is current.

    What I would not repeat

    I would not treat a new URL as a close on a keep-slugs ticket. The order says do not mint essay pages. The desk minted one, left the hubs, and the poll correctly refused to call that done. The temptation is obvious. A published post feels like the patch. It is a different object. The hub is what the old links point at. The old links are the product. A sibling essay does not rewrite them.

    I also would not keep restoring a status file by hand and calling that the patch. Three restore commits in four days is a procedure, not a fix. The next poll that writes the file from a short context will do it again. The restore commit proves we noticed. It does not prove the writer appends.

    What is still open

    The open patch is the pricing hubs, and it is blocked on purpose until someone edits the three slugs in place. The poll is not allowed to do that edit. TM Site has not done it. Verified dates on those pages are still early October. Haiku 4.5 is still wearing the current label on the hub the work order names. Sonnet 5.5 cache is still written at $0.20 there. The sibling essay can stay. It does not close this.

    Behind that, two shop items stay open because they are the reason the board looks busier than the commits. The CoS writer still needs an append, not a janitor. Teams #ops still 403s on the license. Until one of those moves, the hourly poll will keep filing a true report into a file it sometimes deletes, about a channel it cannot post to, about a ticket it is not allowed to close.

    That is the week. Not a recap. Three breaks, one refusal, one door still open.

  • The Best Pharmacy Product Reads the Receipt Against the File

    The Best Pharmacy Product Reads the Receipt Against the File

    The pharmacy already has a public acquisition file.

    The counter still charges a number that may not sit next to it.

    That gap is the product.

    The idea mills keep minting a pharmacy chatbot, a coupon-clipper app, and an rxcheck.ai.

    Three names.

    One object.

    A register receipt, or the sticker on the bag, that does not sit next to the acquisition file the Centers for Medicare and Medicaid Services already publishes every week, or next to the maximum fair price file that took effect on January 1, 2026.

    Greg Isenberg’s stream and the daily micro-SaaS accounts keep splitting the same reader.

    One post wants a refund radar that studies why people ask for money back.

    Another wants a bill auditor that gets paid only when the client saves.

    A third wants a photo of a medical bill dropped into a chat, with a letter on the other side.

    Cute.

    Wrong cut if you stop at the chat.

    The customer does not wake up wanting a PBM explainer.

    They wake up because the bag was $47 and the same capsule was $9 at the pharmacy across the street, or because a Part D claim in 2026 still does not look like the price CMS already posted.

    Why this year, not a white paper

    Two public files moved from “someone could look it up” to “a stranger can photograph a receipt this week.”

    The first is NADAC, the National Average Drug Acquisition Cost.

    CMS posts it weekly on data.medicaid.gov.

    It is a survey of what retail pharmacies pay wholesalers for a drug, net of prompt-pay discounts, not the price on the register.

    A markup over that file is not automatically a rip-off.

    A pharmacy has rent, a pharmacist, and a dispensing fee.

    The product is the join, not the sermon.

    The Federal Trade Commission made the scale of the join hard to ignore.

    On January 14, 2025 the Commission published its second interim staff report on prescription-drug middlemen.

    Staff found that the Big Three — Caremark, Express Scripts, and OptumRx — marked up numerous specialty generic drugs dispensed at affiliated pharmacies by hundreds and thousands of percent.

    Those affiliated pharmacies generated more than $7.3 billion in dispensing revenue in excess of estimated acquisition cost, measured by NADAC, from 2017 to 2022.

    That excess revenue grew at a compound annual rate of 42 percent from 2017 to 2021.

    The top 10 specialty generics accounted for $6.2 billion of it, 85 percent of the total in the study window.

    The second file is newer, and it is the reason the wedge is this quarter rather than a 2027 roadmap.

    CMS published negotiated prices — the statute calls them maximum fair prices — for the first 10 Part D drugs on August 15, 2024.

    Those prices took effect January 1, 2026.

    The same fact sheet said that if the agreed prices had been in effect in 2023, net covered prescription-drug spending on those drugs would have been about $6 billion lower, 22 percent.

    About 9 million people with Medicare use at least one of the 10.

    Under the projected defined standard benefit, CMS estimated $1.5 billion in out-of-pocket savings for people with Part D in 2026.

    A participating manufacturer has to make the negotiated price available to eligible people and to the pharmacies that dispense the drug.

    The file is public.

    The receipt is in the bag.

    Almost nobody puts them on the same page before the card is charged.

    Two primitives, one wedge

    Primitive one is photo-and-PDF review.

    The mills have been shipping receipt readers for months.

    The input here is the thing already in the bag.

    Register receipt.

    Bag label.

    Part D explanation of benefits, if one exists.

    NDC if it printed.

    Drug name and strength if it did not.

    Quantity.

    Amount paid.

    Date.

    Pharmacy name.

    Cash, coupon, or plan.

    Primitive two is the public file join.

    NADAC for the NDC in the week of the fill.

    If the drug is one of the first ten and the payer is Part D, the maximum fair price for that NDC and supply.

    The output is three words, not a coach.

    Match.

    Mismatch.

    File too thin.

    File too thin is a real answer.

    NADAC does not cover every branded specialty the way a coupon site pretends to.

    A maximum fair price is not a cash price for a person who is not in Part D.

    Saying so is the product working.

    The wedge is a free checker.

    Not a platform.

    No account for the first answer.

    Photograph the receipt.

    Thirty seconds later: above the weekly acquisition file by this much, above the 2026 price file, or not enough on the page to say.

    If you cannot get a stranger to photograph one receipt this week, you do not have a company.

    You have a policy thread.

    What the checker is not allowed to do

    It does not tell anyone to stop a drug, split a tablet, or switch pharmacies on a clinical claim.

    It does not file an appeal.

    It does not move money.

    A mismatch on a specialty generic can be a plan design, a spread, a coupon that already fired, or a bad read of the NDC.

    The model drafts the comparison.

    A person owns the send.

    Anything that leaves the building — a note to the pharmacy, a Part D inquiry, a complaint to a state board — needs a human signer who has seen the receipt, the file row, and the sentence that will be sent.

    Contingency is fine after that signature, and only after a confirmed mismatch.

    Charge them when the file proves the gap, or do not charge them.

    Do not sell a subscription to a dashboard of adherence.

    The map is the company

    The first hundred receipts are a demo.

    The ten thousandth is a labeled map of counter price versus acquisition cost, and versus the 2026 price file, by NDC, chain, and ZIP.

    That map is the moat.

    Coupon sites already show a cash offer.

    They do not keep the pair: what this person was charged, what the weekly file said that week, and whether the Part D claim sat on the posted maximum fair price.

    A plan sponsor, a state Medicaid shop, or a local reporter will pay for the pair once it is boring and repeatable.

    They will not pay for another chatbot that explains formularies.

    Start narrow.

    Week one and two: one checker.

    Photo or PDF in.

    Cash generics with a stable NADAC row.

    One state.

    No account.

    Week three and four: the ten Part D drugs, and only the comparison to the posted price.

    A draft inquiry pack with the file row cited, held until a person signs.

    Do not start with oncology markups and a letter to a PBM.

    That is how the first customer becomes an exhibit.

    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 cause code.

    The HOA essay was an assessment against a study.

    The 401(k) essay was a fee against a filing.

    This one is the bag version of the same pair: a document the customer already holds, plus a file the agency was required to publish, joined while the first negotiated prices are still new and the specialty-generic markup is already on a public record.

    The hospital file was a chargemaster.

    This file is an acquisition cost and a negotiated price.

    Different object.

    Same habit.

    Someone will own the labeled map of charged versus filed.

    The mills will keep proposing a new .ai name for each receipt.

    Ignore the names.

    Join the line.

    Keep the map.

    Will Tygart — Tygart Media.

    This is the idea-mill series.

  • The Best 401(k) Product Reads the Fee Against the Filing

    The Best 401(k) Product Reads the Fee Against the Filing

    The plan already filed the fee. The sponsor still pays a line that may not match the peer band. That gap is the product.

    The idea mills keep minting a 401(k) chatbot, a fee-negotiator app, and a plancheck.ai. Three names. One object. A disclosure page that does not sit next to the Form 5500 the administrator already signed.

    Greg Isenberg’s stream and the daily micro-SaaS accounts keep splitting the same reader. One post wants a universal inbox for itemized receipts. Another wants a private tool that flags math errors on a legal bill. A third wants receipt matching so a small shop can see duplicate charges. Useful pieces. Wrong cut if you leave them as separate products. The sponsor does not wake up wanting a new dashboard. The sponsor wakes up because the recordkeeper invoice moved and nobody compared it to the filing.

    The disclosure is not the file

    Most sponsors treat the annual fee notice as weather. It arrives. They file it. They pay. The file underneath it is larger than the notice: Schedule H administrative expenses on Form 5500, the participant count that sets the band, the basis-point load on year-end assets, and the 404a-5 disclosure the plan was already required to send.

    That participant notice is not optional color. Under 29 CFR 2550.404a-5, fiduciaries of participant-directed individual account plans must disclose plan-level and investment-level fee information at least once in any 14-month period. The Department of Labor still collects that disclosure regime under OMB 1210-0090. The notice is the page in the drawer. The filing is the public number.

    The Department of Labor posts Form 5500 datasets from EFAST2 and updates the 2009-and-later sets around the first of each month. A stranger can pull Schedule H without a subpoena. The gap is not missing data. The gap is that the sponsor’s page and the public row do not get read on the same afternoon.

    Why this week, not a vibe

    In September 2026, Admin316’s Russell McNorton published a cut of the public file, not a vendor survey. EIN Presswire carried it on September 14, 2026. 401(k) Specialist Magazine carried the same cut on September 18, 2026. The sample is every 2024 plan-year Form 5500 with a Schedule H, pension feature code 2K, at least 25 active participants, positive administrative expenses, and positive end-of-year assets. That is 48,944 plans.

    The national median in that cut is $162 per participant and 27.0 basis points. The median is the wrong number to stop on. Scale drives the band.

    • Plans with 25 to 99 active participants: 4,063 plans, median $364 per participant, 32.5 basis points, 90th percentile $977.
    • Plans with 100 to 249: 19,372 plans, median $228, 31.8 basis points, 90th percentile $548.
    • Plans with 250 to 500: 11,010 plans, median $166, 28.7 basis points, 90th percentile $382.
    • Plans with 500 or more: 14,499 plans, median $104, 18.6 basis points, 90th percentile $250.

    Among the 34,423 plans under 500 participants, 30.6 percent paid more than twice the national median per participant. That is about 10,500 plans paying above $324 per person in the 2024 filings alone. McNorton’s line in the September 14 release is the operating rule: paying $977 per participant is not itself a breach. Paying it without a comparison is a harder position to defend.

    That is the 2026 shift. The filings were always public. The peer band, cut by headcount and signed under penalty of perjury, is now a published table a checker can point at. A benchmark deck from the recordkeeper is no longer the only number in the room.

    Two primitives, one wedge

    Primitive one is photo-and-PDF review. The mills have been shipping receipt readers for months. The input here is the annual 404a-5 fee disclosure, the recordkeeper invoice, or the administrative-expense line on the sponsor’s copy of Form 5500. Plan name in the header. Participant count if printed. Dollar fee or basis points if printed. No login for the first answer.

    Primitive two is the file the institution was forced to produce. Form 5500, Schedule H, administrative expenses, joined to the size band in the September 2026 Admin316 cut of 48,944 plans. The mills keep these apart: a reader, a letter filler, a benchmark PDF. The sponsor needs them on one page.

    The wedge is a free checker. Not a platform. Photo or PDF in. Three labels back: fee line sits inside the band for that participant count, fee line sits above the band, or the page is too thin to tell. If the page has a dollar fee and a headcount, show dollars per participant next to the median and the 90th percentile for that band. If the page has assets, show basis points next to 27.0. Thirty seconds. No account.

    Do not start by filing with the Department of Labor. Do not start by moving money. The first action a stranger will take this week is a photograph of a page they already have.

    The map is the moat

    One disclosure is a favor. Ten thousand disclosures are a labeled map: recordkeeper, plan size band, year, dollars per participant, basis points, and whether the sponsor’s page matched the filing. That map is not a third dashboard. It is the dataset a sponsor, a payroll buyer, and a fiduciary reviewer cannot assemble from a single PDF.

    Charge after the page proves a mismatch, or do not charge. A draft question for the recordkeeper, or a draft note for the next committee meeting, is worth a small fee once the checker has a label. A demand that fees be reset, a participant claim, or a filing with EBSA is not a model’s job to send. Models draft. The sponsor signs. Irreversible steps stay with a human.

    The compounding path is the labeled set, not a portal that stores every plan document. Plan documents are a swamp. The administrative-expense line is a number. Numbers compound. PDFs do not.

    A build order that will survive contact

    • Week 1–2: one checker. Photo or PDF in. Inside band, above band, or page too thin. Use the September 2026 bands, and say so on the page. No account for the first answer.
    • Week 3–4: a draft question pack with a human signer. One question to the recordkeeper. One note for the committee. A cheap per-letter fee only after the first free verdict.
    • Month 2: join the sponsor’s page to the public Form 5500 row when the EIN or plan number is on the page. Show filed administrative expense next to the invoice. Do not tell the sponsor the fee is a breach. Tell the sponsor the two numbers.
    • Month 3: add the 404a-5 investment-expense table as a second label. Same wedge. Different line. Revenue sharing that never appears on the invoice still belongs on the map.
    • After volume: the map. Dollars per participant by recordkeeper and size band. Sell the map to advisors who already run committee meetings. Keep the checker free.

    What to refuse

    Refuse a national retirement operating system. Refuse an agent that moves plan assets. Refuse a product whose only wedge is “AI for HR productivity.” Refuse a letter that accuses a fiduciary of a breach before a person has read the page and signed the send. Excessive-fee pleading is a lawyer’s work. The checker’s work is the label.

    Also refuse the slogan. A receipt inbox and a legal-bill scrubber are real tools. They are not this company. The sponsor’s problem is not a missing transaction description. The sponsor’s problem is an administrative line that may not match a filing the plan already made, against a peer band a September 2026 cut already published.

    Join the line

    This is the plan version of a pair the mills keep splitting: a document the customer already holds, plus a file the institution was forced to publish, joined while the 2024 filings are still the fresh public set.

    The noticing used to require a benchmarking firm and a quarter. It now requires a model that can read the page and a person who will sign anything that leaves the building. Recovery still works because the first check costs the sponsor almost nothing. Charge them after the filing proves a mismatch, or do not charge them.

    Someone will own the labeled map of billed versus filed. The mills will keep proposing a new .ai name for each fee PDF. Ignore the names. Join the line. Keep the map.

    Will Tygart — Tygart Media.

    This is the idea-mill series.

  • Farmersville Paid $30 for AI Minutes. Here’s What the $30 Doesn’t Buy.

    Farmersville Paid $30 for AI Minutes. Here’s What the $30 Doesn’t Buy.

    A low-cost AI subscription can produce text. It cannot settle a minutes policy, absorb a week of review labor, or deliver a public record that is ready to publish.

    On September 29, the Farmersville City Council voted 4–1 to pay $30 a month — $360 a year — for Grok to draft verbatim meeting minutes from council recordings. City Clerk Rochelle Giovanni would review each draft. Interim City Manager Kevin Northcraft called the AI-generated minutes “more objective” than minutes written by a person. Elon Musk quote-posted the news with one word: “Grok.” [1]

    The reaction was predictable. Some people treated the vote as proof that artificial intelligence had made a routine government task nearly free. Others treated it as a punch line. Both reactions missed the operational story.

    The $30 vote was never really about drafting

    Farmersville had spent months arguing about what its minutes should contain. The city used summary minutes, but councilmembers pressed to include particular actions and verbatim statements. Under that pressure, work that had taken the clerk about two hours stretched to nearly a week.

    That is the number that matters. The city did not merely have a transcription problem. It had a governance problem: disagreement over the purpose and level of detail of the official record. A language model can turn audio into text. It cannot decide which minutes policy the council should adopt, apply that policy with institutional judgment, or end a political dispute over whose words deserve inclusion.

    The subscription buys a draft, not minutes

    In the city’s comparison, Grok produced eight pages, Otter produced nine, a service identified as Government Clerk produced 12, and a human Rev.com transcript ran 111 pages. Those page counts compare outputs, but they do not answer the central question: What kind of record is the city trying to produce?

    The California City Clerks Association’s minutes guidance is clear. The primary purpose of minutes is to memorialize decisions. It identifies action minutes and brief summary minutes as appropriate styles and says verbatim minutes should not be used. Action minutes record final decisions; brief summary minutes preserve the main points that led to a decision without turning the record into a transcript. [2]

    A transcript records what was said. Minutes record what the body did.

    That distinction matters because more text is not automatically more transparency. An audio or video recording can preserve the full discussion. Minutes serve a different function: they create a concise, reliable record of attendance, items considered, actions taken, votes, and follow-up. If a city wants verbatim minutes anyway, it should make that policy choice openly — and price the work required to review them.

    The hidden cost is the clerk’s review time

    Farmersville’s clerk still reviews every Grok draft. She must catch misheard names, incorrect motions, missing vote details, speaker confusion, and language that does not match the city’s adopted style. She also has to format the document, reconcile it with the agenda and staff materials, route it for approval, and prepare it for publication and retention.

    None of that appears in the $30 subscription price. The software cost is visible because it arrives as a line item. The clerk’s time disappears inside payroll, backlog, and delayed work elsewhere. A city can save money on the first pass while still spending a week producing the finished record.

    This is why “AI wrote the minutes” is the wrong test. The useful question is whether the city received accurate, policy-compliant minutes that a clerk can stand behind without rebuilding the document.

    The useful product is a finished public record

    For a small city, the product should not be a block of generated text. It should be a complete workflow: the meeting recording is transcribed; a draft is shaped to the city’s adopted minutes standard; motions, votes, names, and action items are checked; the document is formatted to the city’s template; a human verifies the result; and a publish-ready file is delivered.

    The artificial intelligence does not need to be perfect. The system needs to be designed so a qualified human catches what it misses. That is not a retreat from automation. It is the control that makes automation usable in public records work.

    A finished-minutes service also makes the cost legible. Instead of buying a subscription and hoping staff time falls, the city buys an outcome: reviewed minutes in the required format, ready for the clerk’s final approval and the next agenda packet.

    Farmersville opened a door for hundreds of small cities

    California has 482 incorporated cities. Many operate with small administrative teams, tight meeting cycles, and clerks whose responsibilities extend far beyond minutes. Farmersville’s dispute is unusually visible, but the underlying problem is common: the recording is easy to make; the official record still takes judgment and time. [3]

    The 4–1 vote proved that a budget line for AI-assisted minutes can survive a public meeting. The $30 subscription opened the door. The larger opportunity sits behind it: the nearly weeklong burden that nobody priced.

    The next step is to buy the outcome

    Council minutes as a finished, human-verified service exist now. For a city spending days turning recordings into disputed drafts, the useful conversation is not which model can generate the most pages. It is what a publish-ready minutes workflow would remove from the clerk’s desk — and what standard the council wants that workflow to follow.

    Sources

  • The Best HOA Product Reads the Assessment Against the Study

    The Best HOA Product Reads the Assessment Against the Study

    The association already adopted the budget. The owner still pays a line that may not match the study. That gap is the product.

    The idea mills keep minting an HOA chatbot, a fee-negotiator app, and a reserve.ai. Three names. One object. A coupon or a budget page that does not sit next to the reserve schedule the board was required to keep, or next to the funding floor a lender will apply when the unit is sold.

    Greg Isenberg’s stream and the daily micro-SaaS accounts keep splitting the same reader. One post wants a refund radar for merchants. Another wants a billing watch that flags failed payments before churn. A third wants a photo upload that becomes a letter. Useful pieces. Wrong cut if you leave them as separate products. The owner does not wake up wanting a new dashboard. The owner wakes up because the assessment moved and the packet does not say whether the move matches the study.

    The budget is not the file

    Most owners treat the annual coupon as weather. It arrives. They groan. They pay. The file underneath it is larger than the coupon: the adopted budget, the reserve schedule, the study that set the schedule, the vote that waived a line the statute may no longer allow, and the percent of assessment income that a conventional lender will test before it will write a loan on the unit.

    The Foundation for Community Association Research, in the Community Association Fact Book 2025 (data as of December 31, 2025), counts 373,000 U.S. community associations, about 78.1 million residents, and $124.2 billion in assessments collected. The same Fact Book dashboard puts reserve balances near $31 billion. That is the national pool. It is not a verdict on any one building. A building can sit inside a $124.2 billion system and still be funding the roof at a number the study does not support.

    Association Reserves has published percent-funded distributions for decades. A September 2026 compilation by RapidEye, drawing on that archive of more than 100,000 studies from 1986 through 2025, reports that 74 percent of associations were under 70 percent funded, and that 34 percent were under 30 percent funded. The 70 percent line is an industry convention, not a statute. It is still the number boards and buyers already use. A checker that cannot say where a single budget sits against that convention, and against the statute that actually applies, is a chatbot.

    Why this week, not a vibe

    Florida changed the numbers, then stopped changing them. CS/CS/HB 913, Chapter 2025-175, was approved June 23, 2025, and took effect July 1, 2025. Under section 718.112, Florida Statutes, reserves are required for roof replacement, building painting, and pavement resurfacing regardless of cost, and for any other item whose deferred maintenance or replacement cost exceeds $25,000, or the inflation-adjusted amount set by the Division, whichever is greater. The old threshold was $10,000. Raising it took smaller components off the mandatory list. An item that left the schedule did not stop aging.

    The waiver rule is the sharper line. For a budget adopted on or after December 31, 2024, members of a unit-owner-controlled association that must obtain a structural integrity reserve study may not vote to provide no reserves, or less reserves than required, for the SIRS items in section 718.112(2)(g). Non-SIRS reserves can still be waived by a majority of the total voting interests. Associations that existed on or before July 1, 2022, had until December 31, 2025, to complete the first SIRS, a deadline HB 913 extended from the end of 2024. Officers and directors must sign an affidavit acknowledging receipt of a completed study. The Florida Senate bill summary for HB 913 is plain on that affidavit. A 2026 reviser’s bill, Chapter 2026-14, did not rewrite the funding rule. The budget in front of an owner this fall is still the HB 913 budget.

    The lender rule is the second clock, and it is not a Florida rule. Fannie Mae Lender Letter LL-2026-03, issued March 18, 2026, raises the Full Review reserve test from 10 percent to 15 percent of budgeted assessment income for loan applications dated on or after January 4, 2027. Freddie Mac aligned on the same date. The denominator is assessment income, not the whole budget. A reserve study less than three years old, funded at the highest level the study recommends, can still substitute for the flat percentage. Separately, for applications dated on or after August 3, 2026, Fannie Mae retired Limited Review for established condo projects, so more budgets get read at all. A unit that was warrantable in 2025 can fail a 2027 application on one line the owner never calculated.

    California is the third clock, and it is already ringing. Civil Code 5551 required the first balcony, deck, and elevated-walkway inspection for associations with more than three units by January 1, 2025. Repair bills from missed waterproofing are landing as special assessments. That is a different statute from Florida’s SIRS. The product does not need a national platform to use it. It needs a state tag on the page the owner uploads.

    Two primitives, one wedge

    Primitive one is photo-and-PDF review. The mills have been shipping receipt readers for months. The input here is the annual budget, the reserve schedule, the assessment coupon, or the study summary the board mailed. Assessment income in the header. Reserve contribution on its own line. Component list if the association printed one. No login for the first answer.

    Primitive two is the file the institution was forced to produce, joined to a funding floor a buyer’s lender will apply. In Florida that file is the SIRS and the budget adopted under section 718.112. Nationally, for a condo that wants a conventional loan, it is the reserve line tested in Fannie Mae Selling Guide B4-2.2 against LL-2026-03. The mills keep these apart: a reader, a letter filler, a lender explainer. The owner needs them on one page.

    The wedge is a free checker. Not a platform. Photo or PDF in. Three labels back: reserve line matches the study, reserve line does not match, or the page is too thin to tell. For a Florida condo of three or more habitable stories, a fourth label: waiver language on a SIRS item that section 718.112 no longer allows for a budget adopted on or after December 31, 2024. For any condo budget, a fifth label: the reserve allocation as a percent of assessment income, set next to 10 percent today and 15 percent for applications on or after January 4, 2027. Thirty seconds. No account.

    Do not start by filing a complaint. Do not start by moving money. The first action a stranger will take this week is a photograph of a page they already have in a kitchen drawer.

    The map is the moat

    One budget is a favor. Ten thousand budgets are a labeled map: association, state, year, reserve ratio, study age, waiver language, SIRS components present or missing. That map is not a third dashboard. It is the dataset a manager, a buyer’s agent, and a lender’s reviewer cannot assemble from a single PDF.

    Charge after the page proves a mismatch, or do not charge. A draft records request, a draft question for the annual meeting, or a draft note to the board is worth a small fee once the checker has a label. A records request under Florida section 718.111, a complaint to the Division, or a challenge to a special assessment is not a model’s job to send. Models draft. The owner signs. The same rule applies in California under the Davis-Stirling records rights. Irreversible steps stay with a human.

    The compounding path is the labeled set, not a portal that stores every governing document. Governing documents are a swamp. The reserve line is a number. Numbers compound. PDFs do not.

    A build order that will survive contact

    • Week 1–2: one checker. Photo or PDF in. Match, mismatch, or page too thin. One state. Florida condominiums first, because the waiver ban and the SIRS affidavit are in statute, not in a blog post. No account for the first answer.
    • Week 3–4: a draft question pack with a human signer. Records request, meeting question, or a note that the reserve line is under the study. A cheap per-letter fee only after the first free verdict.
    • Month 2: add the lender test. Show the reserve allocation as a percent of assessment income, next to 10 percent and next to the 15 percent line in LL-2026-03. Do not tell the owner the unit is unwarrantable. Tell the owner the line the lender will divide.
    • Month 3: California balcony inspections and special-assessment notices as a second state tag. Same wedge. Different statute. Civil Code 5551, deadline January 1, 2025.
    • After volume: the map. Ratio by association and year. Study age. Waiver language that survived a statute that retired it. Sell the map to managers and buyer agents. Keep the checker free.

    What to refuse

    Refuse a national HOA operating system. Refuse an agent that pays the assessment. Refuse a product whose only wedge is “AI for board productivity.” Refuse a letter that accuses the board of a breach before a person has read the page and signed the send. Willful failure to complete a required Florida SIRS can be pleaded as a fiduciary issue. That pleading is a lawyer’s work. The checker’s work is the label.

    Also refuse the slogan. billingwatch.ai and refundradar.ai are merchant tools. They watch failed payments and refund abuse. The owner’s problem is not churn. The owner’s problem is a contribution line that may not match a study the association already paid for, under a statute or a lender letter that already has a date on it.

    Join the line

    This is the household version of a pair the mills keep splitting: a document the customer already holds, plus a file the institution was forced to produce, joined before the next budget hardens and before a 2027 loan application divides the reserve line by assessment income.

    The noticing used to require a reserve specialist and a weekend. It now requires a model that can read the page and a person who will sign anything that leaves the building. Recovery still works because the first check costs the owner almost nothing. Charge them after the study proves a mismatch, or do not charge them.

    Someone will own the labeled map of assessed versus studied. The mills will keep proposing a new .ai name for each budget PDF. Ignore the names. Join the line. Keep the map.

    Will Tygart — Tygart Media.

    This is the idea-mill series.

  • The night job mailed six empty CSVs

    The night job mailed six empty CSVs

    The useful failure this week was not a downed site. The cluster answered 200. The failure was a job that kept completing.

    Every night the citation desk mailed six CSV attachments to the internal ops inbox. Every attachment was a header row. The run logged itself, marked the task unchanged, and went back to sleep. From the outside that looks like a report. From the inside it is a sign-in wall wearing a receipt.

    The export that refused to invent numbers

    Bing Webmaster Tools publishes an AI Performance gradesheet. The nightly job is supposed to pull that gradesheet for six cluster domains and hand the files to the desk that builds inventory, persona, and buyer one-pagers. It cannot. The environment that runs the job is not signed into Webmaster Tools. The download fails. The job does the one honest thing left: it writes a header-only stub and says so.

    The receipts are boring, which is how you know they are real. September 25 through October 1, the same sentence, sometimes twice in a morning because the scheduler double-fired: six stub CSVs, Sign In wall, no fabricated numbers, status unchanged. October 1’s receipt is the cleanest version. Zero real downloads. Session not signed in. Attachment count still six.

    I would rather have the empty file than a confident one. A stub cannot be quoted in a client note. A made-up citation count can. The patch that held is the refusal. The patch that did not land is the session. Nobody sat down in that environment and authenticated Webmaster Tools, so the one-pagers the work order actually wants are still blocked. The weekday Claude citation scan was correctly scoped away from this. It watches Anthropic hubs. It does not magically become a Bing login.

    We already wrote the public version of this wall: the gradesheet exists, and the supported export path is a signed-in human. This week proved the corollary. If you automate the unsigned path, you do not get a gradesheet. You get a mailer that is punctual about having nothing.

    The hang that has been a verify for six days

    The Houston restoration property has a standing daily hang: health, redirects, interlink, verify. Since September 23 that hang has been a verify. The admin session the bot can reach greets the wrong account. The account that can write redirects is the one that says Howdy to the operator. Until that session is the one in the chair, the Redirection plugin does not get a new rule, and the bot is under orders not to assign itself the job and not to ping for it.

    October 2 was day six of that skip. The receipt at about 8:21 AM Pacific is the whole story. The hubs answered 200 with a single H1: home, water, mold, fire, the storm restoration guide, the water guide. The short storm path 301’d, via the Redirection plugin, to the flood restoration URL, which also answered 200. Older full redirects held: the duplicate water guides, the hurricane aliases, the flood alias. The machine can see. It cannot hang.

    What it cannot fix is still 404. /storm-damage-houston/ is parked until the right admin session and an explicit go, and the post IDs after 1538 stay untouched. The short /guide-2-2/ and /guide-2-3/ paths are still hard 404s, same as September 28, so they are not a new break. They are a break we have agreed to keep looking at. Site health itself is fine: WordPress 7.1.2, PHP 8.5.4. Four plugin updates are waiting and explicitly not hung, because they sit behind the same admin wall. Elementor, Elementor Pro, Microsoft Clarity, WP All Export. Four theme updates waiting beside them. A green health API next to a parked redirect is not a clean site. It is a site whose write path is a person.

    Rank Math did not see the week

    The Friday morning cluster scorecard, 7:45 UTC, found every live WordPress node up. That is the sentence that gets you in trouble, because up is not indexed.

    On the agency site the public count moved from 3,372 to 3,376. Thursday shipped four posts, under the daily cap of five. Week 40 sat at 22 of 25 with Friday and Saturday still open. Rank Math’s index lastmod was still September 29 at 19:45 UTC. Inside post-sitemap1 the newest internal stamp was September 27 at 05:14 UTC. All 22 week-40 URLs were absent from the post sitemaps. The pages exist. The map the crawler is handed does not mention them. Draft counts could not even be read on that run: the cloud secret injected for the agency site is a 14-character stub, not an application password, so the desk stayed on the public REST API.

    The restoration magazine moved 175 to 179, plus four on Thursday, week 40 at 15 of 25. Its sitemap is current. Its body is not. Three identical titles are still live on IDs 437, 445, and 451. Two flash-flood duplicates, 524 and 525, both return 200. The homepage still renders three H1s. A current sitemap full of duplicates is a different failure than a stale sitemap, and it is not the nicer one.

    The coverage hub is the one that actually broke a rule we wrote down. Thursday it went from 66 posts to 102. Thirty-six in a day, against a daily cap of five and a weekly cap of 25. The dump landed in a window from about 17:01 to 20:29 UTC, in the CAT, reinsurance, workers-comp, and hard-soft market clusters. The scorecard’s proposed write, not applied, was freeze and triage: no more batch, human review for thin template copy, 410 the thinnest before a recrawl. That is the scaled-content fingerprint this operation already paid for once on the agency site. The desk did not publish, send, pay, or trash anything on that run. It wrote the receipt and stopped. Correct. Late.

    What I would not repeat

    I would not resolve a person by first name and send.

    On October 1 the standing send gate failed twice. Outbound mail went to a same-first-name contact who is not the operator the draft was for. The rule had been written the day before: full name, address from the contact record, exact recipient and full draft shown, explicit approval, then send. Memory did not hold it. The task was reopened the same day. Guessing an address is now a stop, not a lookup. I am not putting the names or the addresses in a public post. The operational fact is enough. A first-name match is not an identity. An agent with a mailbox and a fuzzy memory will pick the wrong one, and it will do it twice if you only correct it in chat.

    The coverage-hub dump is the same shape in a different pipe. A cap that lives in a scorecard and not in the publisher is a wish. Thirty-six posts is not a content strategy. It is a scheduler that was allowed to finish.

    The patch that did land

    Sonnet 5.5 shipped September 28. The pricing hubs did not need new URLs. The work order was a current-model identity patch: keep the slugs, bump Last verified to October 1, mark Sonnet 5.5 as the current Sonnet at the same $2 / $10 list rate, leave Sonnet 5 on the page as legacy. Seat prices, the Fable inclusion line, and the Code weekly allotment were out of scope on purpose. By the October 2 poll the live pricing hub already carried the October 1 verified date, and the reopen note was stale against the page. Closed. No new essay. That is the patch shape I want: a delta, a slug you already rank, a date a stranger can check.

    GitHub this week did not carry the incidents. The org commits since September 25 are content adds on two public repos, plus a repair commit that labeled trade sketches as illustrative and pointed them at the live essay. No issues opened. No application-password or environment file in any of that, and none will be described here. The breaks were in Notion receipts and public HTTP, not in a pull request.

    Still open

    The Howdy wall is still open. Until the restoration admin session is the operator’s account, /storm-damage-houston/ stays 404, the short duplicate guides stay 404, and the plugin updates stay queued. The Bing session is the same kind of open. Header-only CSVs will keep arriving at 2 AM until a human signs the job in. Rank Math on the agency site still owes the week-40 URLs a sitemap line. The coverage hub still owes a triage, not another batch.

    None of these need a new tool. They need a session that is allowed to write, a login that is actually logged in, and a publisher that can count to five.