Two Papers on the Kitchen Table: Why the Best AI Job Isn’t Writing — It’s Checking the Bill Against the Deal

Original mid-century editorial illustration of a warm Sunday-night oak kitchen table lit by a brass pendant lamp, showing an unfolded household bill with a redacted lower corner beside a torn envelope and black marker, paired side by side with a teal-tabbed public rulebook folder, bridged by a brass magnifying glass and terracotta pencil pointing across two mismatched highlighted bars.

About Will

I run Tygart Media, an AI-first agency that gets businesses cited and recommended by AI assistants — and I write about what we do, including what breaks.

Connect on LinkedIn →

Most people meet AI as a machine that writes things from scratch — polite emails, slide decks, birthday toasts, or blog paragraphs nobody wanted to read anyway. That is the parlor trick. It is also the exact job where a language model is most tempted to bluff, pad, and invent smooth sentences out of thin air.

The real household and small-business money sits on your kitchen table on Sunday night, where two pieces of paper never quite sit next to each other: the insurance renewal that arrived in the mail and the rate schedule filed with the state; the contractor’s invoice and the original scope; the government letter and the agency’s own published rulebook; the dashboard total and the raw server log. Humans get tired around line fourteen. A model does not. Engineers call this two-document reconciliation — laying two existing records side by side to flag every divergence where the bill parts company with the deal. Put both papers on the table and ask where they disagree.

Printable Edition + Sunday-Night Card
Download Two Papers on the Kitchen Table (5-Page PDF)
Includes both visual charts, the Tear-Out 3-Prompt Reconciliation Card, and verified sources.

Why Checking Beats Writing From Scratch

There is a simple mechanical reason AI is sharper as an auditor than as an improviser. Hand a model an empty page and ask it to invent facts from memory, and it guesses smooth averages — the same fill-in-the-blank habit we mapped in Mad Libs for Machine Learning. Hand it two concrete documents and ask only where Paper A disagrees with Paper B, and you have pinned the model to grounded text — what AI researchers call retrieval-augmented generation (Lewis et al., 2020), which measurably raises factual specificity and gives every answer a traceable source line.

University of Washington and Meta researchers formalized the checking move in FActScore (Min et al., 2023): instead of grading a whole page on gut feel, break it into atomic claims — single checkable dates, dollar figures, and rules — and test each line one by one against a primary record. That is the same truth behind Standing in the Middle: meaning shows up only where two independent records are forced to agree. One paper tells a story; two papers create a receipt.

Six Real Gaps Sitting in Everyday Paperwork

Across our shop and our ongoing idea-mill briefs, the exact same two-paper join keeps surfacing in places where ordinary households and business owners quietly lose real money — not because rules do not exist, but because nobody lays both pages flat together:

1. Your order vs. the charge. In The Receipt Is the Authorization, Visa’s November 5, 2026 shopping-agent benchmark showed 22 models failed 42.8% of tasks — and in 54% of those failures, the agent still completed a purchase. Matching the instruction you gave against the confirmation receipt inside the 60-day federal written dispute window of the Fair Credit Billing Act (15 U.S.C. §1666) catches overruns before they settle.

Get The Signal

What we actually ran, what it measured, and what it means for a restoration shop — every week, including the flops.

Subscription Form

2. Your insurance renewal vs. the public state filing. As we laid out in The Best Insurance Product Reads the Renewal Against the Filing, states like Texas (Insurance Code Chapter 2251) make rate filings public upon filing, and Florida’s October 29, 2026 announcement documented over 824,300 homeowners receiving rate decreases up to 12.1%. Reading your renewal notice beside the public rate filing reveals when a cut or surcharge has not lined up with your cycle.

3. Your gate voucher vs. federal cash-refund law. In The Best Delay Product Tells You Cash Is Owed Before You Take the Voucher, federal rule 14 CFR Part 260 requires automatic cash refunds — within seven business days on a card — when a domestic flight cancels or shifts three or more hours and you decline rebooking. Comparing your itinerary and delay screen against Part 260 stops you from tapping a travel credit while cash is owed.

4. An agency notice vs. the agency’s own rulebook — and old names vs. state holds. In The Best Clawback Product Reads the Notice Against the Rule, an SSA Office of the Inspector General audit found 46% of sampled Social Security overpayment notices failed agency completeness rules — missing calculations or waiver rights right as default withholding jumped to 50%. And in The Best Recovery Product Reads the Name Against the Hold, matching old utility stubs and prior addresses against official state treasury databases linked through NAUPA puts families onto billions sitting unclaimed.

5. The building on paper vs. the wall — and the dashboard vs. the logs. On commercial job sites, You Bid the Drawings. The Building Didn’t Get the Memo shows how walking a 2004 plan set against actual capped pipes and patched chases turns ugly change-order fights into an honest upfront divergence allowance. And on our own websites in My Analytics Said 1,000 Visitors. My Logs Said Otherwise, reconciling a JavaScript dashboard (~1,000 users) against raw origin logs (64,561 requests across 10,345 IPs, over 80% headless) exposed a 10× gap neither instrument could hide once laid side by side.

Six Everyday Joins chart pairing Paper A in your hand against Paper B on public or contractual record across Agent Spend, Insurance Renewals, Airline Delays, SSA Benefits, Unclaimed Property, and Construction or Analytics Logs, anchored by four verified divergence receipts.
Six everyday two-paper joins where laying Paper A beside Paper B exposes hidden divergence.

The Sunday-Night Protocol (Without Handing Over Your Secrets)

You do not need a specialty startup app to run this Sunday night. You need a black marker, two clipped excerpts, and three plain prompts. Before you paste or photograph anything into a consumer AI chat, enforce redaction — blacking out Social Security numbers, account numbers, policy IDs, and home addresses, the exact personally identifiable information (PII) protection outlined in NIST SP 800-122. The model needs the dollar line, the date, and the clause — never your routing number. That is the everyday kitchen-table version of splitting personal life from working tools in Two Droids and a Farmboy and keeping irreversible buttons on your own desk in Leave the Keys Off the Van Seat:

THE SUNDAY-NIGHT RECONCILIATION CARD · THREE SAFE PROMPTS
Redact First, Clip Tight, Then Ask Where Paper A Disagrees With Paper B
Never upload SSNs, account IDs, or private passwords. Always require exact line quotes from both pages.
STEP 0 · BLACK-MARKER REDACTION (BEFORE UPLOAD)
Strip PII first (NIST SP 800-122). Cover or delete SSNs, account numbers, policy IDs, and street addresses; leave only dates, dollar lines, codes, and rule text.
PROMPT 1 · EXTRACT ATOMIC LINES (NO GUESSING)
“List every date, dollar figure, deadline, fee, and condition in Paper A and Paper B as separate numbered tables. Quote exact wording; mark any blank or unclear line UNKNOWN.”
PROMPT 2 · DIFF THE BILL AGAINST THE DEAL
“Compare Paper A line by line against Paper B. Output three buckets: MATCHED, MISMATCHED (quote both lines side by side), and MISSING REQUIRED LANGUAGE. Do not invent outside rules.”
PROMPT 3 · DRAFT THE QUESTION (HUMAN OWNS SEND)
“Draft a calm, factual inquiry citing only the MISMATCHED quotes above and asking for written clarification. Leave blanks for my signature — I will verify every line before sending.”

Where Two-Paper Checks Bend — And Who Signs the Letter

Two honest limits keep Sunday-night reconciliation grounded. First, long unfiltered binders make models miss the middle. Stanford and UC Berkeley researchers proved in Lost in the Middle (Liu et al., 2023) that stuffing huge documents into one prompt degrades recall for facts buried mid-text. Clip Paper A and Paper B down to the exact two sections in question — and as we showed in Don’t Hire a Finish Carpenter to Carry Drywall, never run high-stakes error hunting on a rushed low-effort setting that can stamp a missed discrepancy clean.

Second, an AI is a flashlight, not a lawyer, CPA, or benefits counselor. As we spelled out in How to Verify AI Output, fluency never proves accuracy: a model can still misread a statutory carve-out, skip a footnote, or invent a regulation number. Every item on your mismatch table must quote exact text from both pages so you can verify it with your own eyes before calling a carrier, disputing a charge, or signing a government form. The model drafts the comparison; the human owns the send.

The Sunday-Night Kitchen-Table Protocol translating six safe two-paper diff rules — Redact PII, Clip Tight, Atomic Lines, Side-by-Side Quotes, High Effort, and Human Signer — alongside two honest limits where two-paper checks bend.
Six safe Sunday-night rules for checking two papers without leaking private details, plus two honest limits.
AI Citation Restoration · Tygart Media
We do AI citation restoration. When what your dashboard says and what your server logs prove are ten times apart — or AI assistants keep misquoting your business — send us the worst mess you have. We come from water damage — we work like smokejumpers, not retainers, putting both papers on the table with receipts you can verify yourself. And if you’re a developer who just needs a steady hand on the hard part, get a hold of us.

— Will Tygart, Tygart Media.

Takeaway Edition
Print the Guide & Tear-Out Sunday-Night Card
Keep the Page 5 redaction & 3-prompt checklist by your desk for bills, renewals, and notices.

Get The Signal

What we actually ran, what it measured, and what it means for a restoration shop — every week, including the flops.

Subscription Form

Track the AI tools you actually use
Vendor-neutral prices & limits for ChatGPT, Claude, Gemini, Perplexity and more — tracked in AI Stack Watch.
See the live AI tracker →or set up your alerts

Comments

Leave a Reply

Your email address will not be published. Required fields are marked *