Let's talk
Restaurants, bars and cafés

Fairtable

Thirty-two small agents that check a restaurant's back office from the files it already exports, food cost, labor, tips, cash, delivery apps, fees, tax and compliance, and wait for a named person before anything is paid, sent or changed.

A plate with a fork and knife beside a receipt with a check

Engagements

$1,800 · One location

Food cost pack

Actual against theoretical food cost, recipe costs, vendor price creep, deliveries and credits, counts, waste and 86s (7 agents)

$1,500 · One location

Bar and menu pack

Pour cost and liquor variance, menu engineering, discounts and promotions (3 agents)

$1,500 · One location

Front of house and cash pack

Voids and comps, discounts, cash drawers, gift cards, no-shows, catering deposits (6 agents)

$2,000 · One location

Labor pack

Tip pool and tip credit, overtime and split shifts, schedule against actual, labor by daypart, breaks and minors, set to your state (5 agents)

$1,500 · One location

Delivery apps and fees pack

DoorDash, Uber Eats and Grubhub payouts against orders, marketing fees, card processing fees (3 agents)

$1,500 · One location

Back office pack

Sales tax by jurisdiction, duplicate invoices and GL coding, utility bills, weekly prime cost (4 agents)

$1,200 · One location

Compliance calendar pack

Equipment maintenance, health inspections and permits, food handler cards, allergen matrix (4 agents)

$5,500 · One location

Whole restaurant

All 31 single-location agents, mapped to your exports and set to your rules, one training session

$9,500 · 2 to 5 locations

Small group

Everything in Whole restaurant for each location, plus the location comparison against the group

$15,000 · Up to 15 locations

Partner rollout

For multi-unit groups, franchise operators and accounting firms serving many restaurants: all 32 agents, one shared setup, every location mapped

Support after setup: $150 a month for one pack, $300 a month for the whole restaurant, $200 a month per location for groups. Includes export changes, rule and rate updates, and a monthly check-in.

Reads the files you export; it does not log in to your POS, scheduling, payroll, delivery-app, reservation, distributor or bank account.

Wage, tip, overtime, break, tax, inspection and allergen rules are settings you confirm with your accountant, payroll provider or health department; the defaults are examples.

Column layouts for Toast, Square, 7shifts, Sysco, DoorDash and the other named exports were written from knowledge of those systems; the first setup confirms them on your files.

Lost-sales and premium figures are estimates from your own numbers, not forecasts.

Not legal, tax, payroll, health-code or food-safety advice.

Report pages come in nine languages, translated by Claude and not yet reviewed by native speakers.

Your files and reports stay on your computer. Staff and guest names are masked in anything sent to the AI model. No agent pays, refunds, charges a card, changes the POS, publishes a schedule, runs payroll, files taxes or messages anyone: drafts wait for one named person.

Thirty-two checks.

Food, purchasing and the bar
Food, purchasing and the bar

Actual against theoretical food cost

What the recipes and sales say you used against what the counts and invoices say you did, per ingredient.

Food, purchasing and the bar

Recipe costs at latest invoice prices

Every plate costed at today's prices, with the menu price that would meet your target.

Food, purchasing and the bar

Vendor price creep

Price per pound or each across invoices, prices over your bid, packs that quietly got smaller.

Food, purchasing and the bar

Invoices against deliveries and credit memos

Shorts and cases refused at the door that were never credited.

Food, purchasing and the bar

Inventory count variance

Counts against expected, priced, and counts that look like the wrong unit.

Food, purchasing and the bar

Waste log

What was thrown out and why, and the days nobody logged anything.

Food, purchasing and the bar

Bar pour cost and liquor variance

Bottles used against drinks sold, per spirit, and pour cost against target.

Food, purchasing and the bar

Menu engineering

Stars, plowhorses, puzzles and dogs from your sales and plate costs.

Food, purchasing and the bar

Items 86ed and stockouts

Items that keep running out, for how long, and what that likely cost.

Front of house and cash
Front of house and cash

Voids and comps by employee

Self-approved voids, voids after payment, missing reasons, rates against sales.

Front of house and cash

Discounts and promotions

Promos used after they ended, outside their hours, over their cap, or not on your list.

Front of house and cash

Cash over and short by drawer

Expected cash against the count and the deposit, and shorts that repeat.

Front of house and cash

Gift card liability

What you still owe on cards, by location, and cards whose numbers do not add up.

Front of house and cash

Reservation no-shows

No-show rate, repeat no-shows, large parties with no deposit, fees your policy sets.

Front of house and cash

Catering deposits and balances

Deposits missing before the event, balances overdue after it, refunds owed.

Labor
Labor

Tip pool and tip credit

Pool shares by hours and role, and cash wage plus tips against the minimum for your state.

Labor

Overtime and split shifts

Weekly and daily overtime, double time, split shifts, spread of hours and clopens, priced.

Labor

Scheduled against actual labor

Early clock-ins, late clock-outs, no-shows and shifts nobody scheduled.

Labor

Labor percentage by daypart

Labor against sales for breakfast, lunch, dinner and late night.

Labor

Meal and rest breaks

Missed, short and late meals, and minors working too long or too late.

Delivery apps, fees, tax and bills
Delivery apps, fees, tax and bills

Delivery app payouts against orders

Commissions over your rate, short payouts, error charges and orders never paid.

Delivery apps, fees, tax and bills

Delivery app marketing fees

Ad and promo charges outside the campaigns you opted into, and what each campaign returned.

Delivery apps, fees, tax and bills

Card processing fees

Effective rate, markup over your agreement, and fees you never agreed to.

Delivery apps, fees, tax and bills

Sales tax by jurisdiction

Tax collected against your rates per location and category, marketplace orders kept apart.

Delivery apps, fees, tax and bills

Duplicate invoices and GL coding

Invoices entered twice, line math, and liquor or paper goods coded to food.

Delivery apps, fees, tax and bills

Utility bills

Usage spikes, rate jumps, estimated reads, duplicate bills and late fees.

Compliance and multi-unit
Compliance and multi-unit

Equipment maintenance schedule

Hoods, grease traps, fire suppression and refrigeration overdue or coming up.

Compliance and multi-unit

Health inspection calendar

Re-inspections due, critical violations not followed up, permits about to expire.

Compliance and multi-unit

Food handler cards

Missing, expired and expiring cards, and locations without a certified manager.

Compliance and multi-unit

Allergen matrix against recipes

Allergens in a dish that the matrix does not declare, and free-from claims a recipe breaks.

Compliance and multi-unit

Prime cost

Weekly food, beverage and labor against sales for each location.

Compliance and multi-unit

Location comparison

Every location against the group median, on the same measures.

Each one does one job, on your computer, from a file you export. Nothing is paid, refunded, sent or changed in your POS until a named person on your team says so. Pairs with G6daddy's restaurant-and-bar AI agent: that one talks with your guests, these check the back office.

Measured in the final pass, 19 Nov 2026

Measured, not promised.

217 of 217planted problems found
0false alarms on 490 clean rows
64 of 64one-change tests caught
2public data sources run

On fictional test data, 19 Nov 2026. The clean set covers 31 of the 32 agents: menu engineering sorts every dish into a group, so a menu with no labels does not exist. This pass also found and fixed one wrong finding on the demo data and five wrong or noisy results on public data. The test files and the checks were written by the same team, so these numbers show the rules do what they say. How often they are right on your own files is measured at your setup.

Run it yourself

git clone https://github.com/fpavia111-creator/fairtable-agents
cd fairtable-agents
npm install
node packages/fairtable-food-cost/bin/fairtable-food-cost.js demo

Open source, MIT licence, on GitHub: fpavia111-creator/fairtable-agents. Needs Node.js 20 or later. The demo runs on made-up files and needs no network and no setup.

Common problems it finds

  • Ingredients used well beyond what the recipes and sales say (chicken breast 27% over in the demo week).
  • Vendor prices above the bid sheet, and cases that got smaller at the same case price.
  • Short or refused deliveries with no credit memo.
  • A bartender's drawer short four nights running, and a deposit that does not match the count.
  • Voids approved by the server who rang them, and comps over the limit with no approver.
  • Delivery orders charged more commission than the contract, error charges, and orders never paid.
  • Tip credit shortfalls, where cash wage plus tips fell under the minimum set for your state.
  • Expired or expiring permits and certificates, and hood or fire suppression service past due.

Run on public data

SourceWhat ran and what it foundLicence
NYC Department of Health, Restaurant Inspection Results (one ZIP code, 2024 to Nov 2026)
2026-11-19
fairtable-health-inspections on 1,758 inspections at 648 restaurants (5,479 published rows, one per violation, grouped into one row per inspection). It showed four problems, now fixed: NYC scores count violation points (lower is better), NYC names routine visits Cycle Inspection, same-day records changed the result, and critical violations after a passing visit were reported as open (now a follow-up score setting). After the fixes, 0 disagreements in 499 checks against an independent re-count from the same rows. Tested from one year earlier, routine-due had flagged 36 of the 48 restaurants inspected in the next 45 days, and 57 of its 199 flags were inspected within 90 days.NYC Open Data, public; NYC Open Data terms of use
U.S. Bureau of Labor Statistics average retail prices, 8 food items, via FRED
2026-11-19
fairtable-price-creep on the last 13 monthly prices of each item, written as invoice lines. Price rises over 5% were reported for ground beef (+6.8%) and tomatoes (+9.1%), as the series show. The steady-creep rule was too noisy: it fired for 7 of 8 items, including items that ended cheaper. It now needs a current run of rises that adds up to 5%, and fires once (eggs, up three months running). 0 disagreements with an independent re-check.BLS data, public domain; served by FRED, Federal Reserve Bank of St. Louis

Public, lawful files only; no private data was used. The files are not copied into the repository: a script there downloads them again.

What a person still decides

PackageWhat a person reviews and decides
Food cost packA manager checks each flagged ingredient against the count sheet, recipe and invoices, then decides whether to recount, retrain, or change a recipe or vendor.
Bar and menu packThe bar manager decides whether a pour gap is over-pouring, unrung drinks or a count error; menu and price changes are the owner's call.
Front of house and cash packA manager talks through each void, comp and drawer short with the staff member, and a person decides on any no-show fee, refund or gift card correction.
Labor packThe owner or payroll provider checks wage, tip, overtime and break findings against your state's current rules and payroll records; the agents never run payroll.
Delivery apps and fees packSomeone disputes commissions, error charges and card fees in each platform's portal or with the processor; a draft letter is sent only by a person.
Back office packThe bookkeeper confirms tax rates and returns and decides which possible duplicate invoices to hold; nothing is paid or filed by the agents.
Compliance calendar packA manager books service visits, renews permits and certificates and confirms allergen labels with the kitchen; intervals and rules come from your own jurisdiction.
Whole restaurantEvery finding in every pack goes to a named person, who looks and acts; the agents only read files and write reports and drafts.
Small groupEach location manager reviews their own findings; the owner or operations lead reviews how each location compares with the group median.
Partner rolloutEach location's manager acts on its findings, and the firm or head office confirms each location's settings (wage, tax and inspection rules) with the client.
Export formats (25): 2 tested on a real or public file, 23 not yet tested on a real export.
SystemReport or exportStatus
ToastItemSelectionDetails exportNot yet tested on a real export
ToastTimeEntries exportNot yet tested on a real export
ToastPaymentDetails exportNot yet tested on a real export
ToastVoid and discount details exportNot yet tested on a real export
SquareItem Sales export (CSV)Not yet tested on a real export
SquareTimecards export (CSV)Not yet tested on a real export
CloverItem sales exportNot yet tested on a real export
Lightspeed RestaurantProduct sales report exportNot yet tested on a real export
Revel SystemsProduct Mix report exportNot yet tested on a real export
7shiftsWorked hours and wages exportNot yet tested on a real export
7shiftsSchedule exportNot yet tested on a real export
HomebaseTimesheets exportNot yet tested on a real export
MarginEdgeInvoice line items exportNot yet tested on a real export
Restaurant365AP invoice detail exportNot yet tested on a real export
Restaurant365Inventory count exportNot yet tested on a real export
xtraCHEF by ToastInvoice details exportNot yet tested on a real export
SyscoInvoice download (CSV)Not yet tested on a real export
US FoodsInvoice download (CSV)Not yet tested on a real export
DoorDash Merchant PortalFinancials, Transactions exportNot yet tested on a real export
Uber Eats ManagerPayment details reportNot yet tested on a real export
Grubhub for RestaurantsTransactions exportNot yet tested on a real export
OpenTableReservations exportNot yet tested on a real export
ResyReservations exportNot yet tested on a real export
NYC Department of HealthRestaurant Inspection Results (open data CSV)Tested on a public sample
U.S. Bureau of Labor Statistics via FREDAverage price series (CSV)Tested on a public sample

No layout has yet been tested on a customer's own export. Every setup starts by confirming the layout on your files, and any column can be mapped by hand.

Security

What reaches the AI model

When an assistant calls a tool, its model sees the result: totals, findings, amounts, quantities, dates, rates and finding codes in clear. It also sees text such as item, recipe and vendor names, locations, and free-text reasons and notes exactly as they were typed. Staff, guest and client names, phone numbers, emails, employee IDs, gift card numbers and certificate numbers are replaced by tokens such as A.R.#3f9a2c or card#7ecbb1 (checked with 118 fictional values in 14 agents, 0 leaks). The report and draft files written on your computer keep the real values. Results go to whatever model your assistant uses; for staff pay and schedule data, use a model covered by your own agreements or a local model.

Support

Who keeps the rules current

Every rule that changes with the law or a contract is a setting, not code: the minimum and tipped cash wage, overtime and break rules, minors' hours, sales tax rates, marketplace channels, the allergen list, food handler grace periods, inspection and equipment intervals, card fee caps and delivery commission rates. Defaults live in each agent's src/logic.js, with the source named in the review. Your own values go in a settings JSON file that is merged over the defaults, and every result lists the settings it used. You change the file yourself, or support updates it when a rate or rule changes.

How a setup runs.

1

You export the files

We send the list of reports by name. You export them from the systems you already use; nothing is connected.

2

Setup on your computer

Over a shared screen: the checks are installed, your columns are matched, and your own rules and dates are set.

3

The first report

The checks run on your files. We go through the worklist with you, and every flagged row is a person's call.

4

After that

You run them whenever you like. Support keeps the dated rules and the export layouts current.

A fixed scope and a fixed price, agreed before any work starts. Your files stay on your computer the whole time.

A sample report.

Written by the check itself on made-up files. Every person, business and number is invented.

Tip pool and tip credit All samples

The first page of the Tip pool and tip credit sample report