Retail store & point-of-sale operations
Run sales, returns, price changes and stock counts in store POS and back office.
20 project-authored proposals · taxonomy v1.1 · 0 new benchmark runs. Verifiers and partial-credit rules below are designs, not executed results.
- Typical applications
- Square · Lightspeed · Shopify POS
- Class GUI-need label
HY· Hybrid
Task proposals · 20
Expand to inspect the complete original wording and proposed checks. Original proposal text remains English in both interfaces.
R05.13.01.02-T01 Ring up a discounted sale for a known customer
Original instruction
On an iPad simulator with Shopify POS (development store, location 'Downtown'), sell 'Linen Shirt M' x2, 'Canvas Tote' and 'Sun Hat', attach customer 'Rosa Diaz (synthetic)', apply a 20% line discount to the Sun Hat with reason 'Damaged display', take cash tender of $200, and email the receipt.
- Platforms
ios· iOS/iPadOS- Applications
- Shopify POS
- Interfaces
mob· Mobile touch- GUI need · task setting
G3· GUI-only- GUI need · ordinary access
G3· GUI-only- Interaction primitives
touch· Touch gesturestype· Text & forms- Work product
WP08· App/system state- Conditions
- None declared
- Proposed difficulty
- 2 / 5
Proposed verifier
Order read by grader: POS channel, location Downtown, lines/quantities, line discount 20% only on Sun Hat with reason, customer attached, cash tender and change exact, receipt email event. Admin API not available to agent.
Proposed partial credit
35% items; 25% discount scope and reason; 15% customer; 25% tender and receipt.
R05.13.01.02-T02 Process a no-receipt return to store credit and refuse a final-sale item
Original instruction
In Shopify POS (iPad simulator), a customer without a receipt returns 'Wool Scarf' and a 'Clearance Belt'. Per input/return_policy.md, look up the order by customer phone, refund the scarf to store credit (no receipt) and restock it; the belt is final sale, so do not refund it and add an order note.
- Platforms
ios· iOS/iPadOS- Applications
- Shopify POS
- Interfaces
mob· Mobile touch- GUI need · task setting
G3· GUI-only- GUI need · ordinary access
G3· GUI-only- Interaction primitives
touch· Touch gesturestype· Text & formsnav· Pan/zoom/scroll- Work product
WP08· App/system state- Conditions
risk· Irreversible/risky- Proposed difficulty
- 3 / 5
Proposed verifier
Refund on the located order for scarf only, to store credit (gift card/credit record created), restocked at location; no refund on belt; note present. Shopify Admin API tokens are withheld from the agent, so this must be done in the POS app on the simulator.
Proposed partial credit
40% scarf to store credit; 20% restocked; 30% belt not refunded; 10% note.
R05.13.01.02-T03 Exchange a size and collect the price difference
Original instruction
On Square POS for iPad (simulator, sandbox seller), process an exchange from receipt #A1F7: return 'Trail Runner 9' and give 'Trail Runner 9.5 Wide' which costs $12 more; collect the difference in cash.
- Platforms
ios· iOS/iPadOS- Applications
- Square POS
- Interfaces
mob· Mobile touch- GUI need · task setting
G3· GUI-only- GUI need · ordinary access
G3· GUI-only- Interaction primitives
touch· Touch gestures- Work product
WP08· App/system state- Conditions
- None declared
- Proposed difficulty
- 2 / 5
Proposed verifier
Sandbox: exchange record linked to the original payment, returned item restocked, new item sold, net cash collected 12.00 plus tax per tax rule. Square API access tokens are withheld from the agent, so this can only be done in the POS app.
Proposed partial credit
40% return line; 35% new item; 25% net difference collected.
R05.13.01.02-T04 Add new SKUs with variants and print shelf labels
Original instruction
In Lightspeed Retail (X-Series demo), add the 15 new products in input/new_skus.csv (some with size/color variants), with supplier codes, barcodes, tax class and retail price; then print shelf labels for all new variants using the 'Shelf 38x25' template to output/labels.pdf.
- Platforms
web· Any OS (web)- Applications
- Lightspeed Retail
- Interfaces
brow· Browser- GUI need · task setting
HY· Hybrid- GUI need · ordinary access
G2· GUI-essential- Interaction primitives
click· Point & clicktype· Text & forms- Work product
WP08· App/system state- Conditions
- None declared
- Proposed difficulty
- 3 / 5
Proposed verifier
Demo account product export: products/variants, barcodes, prices and tax classes exact; labels.pdf contains one label per variant and barcode decodes match.
Proposed partial credit
45% products and variants; 20% barcodes; 15% prices/tax; 20% labels.
R05.13.01.02-T05 Post a partial stock count with variance thresholds
Original instruction
In Lightspeed Retail (X-Series demo), create a partial inventory count for aisle 4 (38 products), enter counts from input/count_aisle4.csv, and complete it so that variances worth <= $20 are applied; for larger variances, set the count line to a recount and add a note listing the products.
- Platforms
web· Any OS (web)- Applications
- Lightspeed Retail · Excel
- Interfaces
brow· Browser- GUI need · task setting
HY· Hybrid- GUI need · ordinary access
G2· GUI-essential- Interaction primitives
click· Point & clicktype· Text & formsmulti· Cross-app- Work product
WP08· App/system state- Conditions
- None declared
- Proposed difficulty
- 3 / 5
Proposed verifier
Inventory levels after count: small-variance products updated to counted; large-variance products unchanged; note lists exactly the large-variance products (key).
Proposed partial credit
45% small variances applied; 35% large variances held; 20% note correct.
R05.13.01.02-T06 Transfer stock between stores and receive a short shipment
Original instruction
In Square Dashboard (sandbox, 2 locations), send a transfer of 30 'SKU-551 Ceramic Mug' and 12 'SKU-560 Saucer' from Main to Store 2. At Store 2, receive the transfer: the box arrived with 28 mugs (2 broken). Receive 28, record 2 as damaged, and receive all saucers.
- Platforms
web· Any OS (web)- Applications
- Square Dashboard
- Interfaces
brow· Browser- GUI need · task setting
HY· Hybrid- GUI need · ordinary access
G2· GUI-essential- Interaction primitives
click· Point & clicktype· Text & forms- Work product
WP08· App/system state- Conditions
- None declared
- Proposed difficulty
- 3 / 5
Proposed verifier
Sandbox inventory: Main -30/-12; Store 2 +28/+12; 2 units in damaged/waste state; transfer status completed.
Proposed partial credit
30% transfer created; 40% receipt with 28 and 12; 30% damage recorded.
R05.13.01.02-T07 Close the register and record the over/short
Original instruction
On Square POS for iPad (simulator), end the cash drawer for register 1. Expected cash is 1,402.15; the counted drawer in input/count.txt totals 1,398.15. Enter the counted amount, record the -4.00 short with note 'Count verified twice', and end the drawer.
- Platforms
ios· iOS/iPadOS- Applications
- Square POS
- Interfaces
mob· Mobile touch- GUI need · task setting
G3· GUI-only- GUI need · ordinary access
G3· GUI-only- Interaction primitives
touch· Touch gesturestype· Text & forms- Work product
WP08· App/system state- Conditions
- None declared
- Proposed difficulty
- 2 / 5
Proposed verifier
Cash drawer shift record: actual cash 1398.15, difference -4.00, note text, state ENDED. Square API access tokens are withheld from the agent, so this can only be done in the POS app.
Proposed partial credit
50% counted amount; 30% note; 20% drawer ended.
R05.13.01.02-T08 Schedule a weekend markdown and reprint affected labels
Original instruction
In Lightspeed Retail (X-Series demo), apply the markdown in input/weekend_sale.csv (40 SKUs, sale prices) as a price book for outlet 'Harbor' active Saturday 2026-10-17 00:00 to Sunday 23:59 only. Then print sale shelf labels for those SKUs with the 'Sale 50x30' template to output/sale_labels.pdf.
- Platforms
web· Any OS (web)- Applications
- Lightspeed Retail
- Interfaces
brow· Browser- GUI need · task setting
HY· Hybrid- GUI need · ordinary access
G2· GUI-essential- Interaction primitives
click· Point & clicktype· Text & forms- Work product
WP08· App/system state- Conditions
- None declared
- Proposed difficulty
- 4 / 5
Proposed verifier
Price book with outlet restriction, validity window and 40 prices exact; base prices unchanged; label PDF has 40 labels with sale prices (text parse).
Proposed partial credit
30% price book scope/dates; 40% prices; 10% base prices untouched; 20% labels.
R05.13.01.02-T09 Take a split-tender sale on an Android countertop POS
Original instruction
On a Clover Station emulator (Android, sandbox merchant), sell the 4 items in input/basket.txt, apply the customer's gift card for $25.00 (test card number given), take the remainder in cash, and print the receipt to the virtual printer.
- Platforms
and· Android- Applications
- Clover POS
- Interfaces
mob· Mobile touchhmi· Device/HMI- GUI need · task setting
G3· GUI-only- GUI need · ordinary access
G3· GUI-only- Interaction primitives
touch· Touch gesturestype· Text & forms- Work product
WP08· App/system state- Conditions
- None declared
- Proposed difficulty
- 3 / 5
Proposed verifier
Sandbox order: line items, tax, two tenders (gift card 25.00, cash remainder) summing to total; printer job logged. Clover REST API tokens are withheld and adb is disabled on the emulator, so the sale must be rung up in the Register app.
Proposed partial credit
35% items; 40% split tender exact; 25% receipt printed.
R05.13.01.02-T10 Receive a vendor order with scanner input and discrepancy notes
Original instruction
In Lightspeed Retail (X-Series demo), receive purchase order PO-1882 from 'Nordic Knits'. Use the barcode scan log in input/scans.txt (a scanner-wedge transcript) to enter received quantities; one unknown barcode is a substitute product: add it as a new line per the packing slip input/slip.pdf and note the substitution.
- Platforms
web· Any OS (web)- Applications
- Lightspeed Retail
- Interfaces
brow· Browser- GUI need · task setting
HY· Hybrid- GUI need · ordinary access
G2· GUI-essential- Interaction primitives
type· Text & formsclick· Point & clickmulti· Cross-app- Work product
WP08· App/system state- Conditions
- None declared
- Proposed difficulty
- 3 / 5
Proposed verifier
PO received quantities equal scan counts; substitute line added with correct product and qty; note mentions substitution; inventory updated accordingly.
Proposed partial credit
50% received quantities; 30% substitute line; 20% note.
R05.13.01.02-T11 Create a store transfer slip and receive it in Retail Pro
Original instruction
In Retail Pro Prism (training server, Windows client), create a transfer slip from Store 001 to Store 004 for the 9 items in input/transfer.xlsx, out-slip it, then log in to Store 004 and receive it as a voucher, recording 1 item received short.
- Platforms
win· Windows- Applications
- Retail Pro Prism
- Interfaces
desk· Desktop GUI- GUI need · task setting
G3· GUI-only- GUI need · ordinary access
G3· GUI-only- Interaction primitives
click· Point & clicktype· Text & formsnav· Pan/zoom/scroll- Work product
WP08· App/system state- Conditions
licensed· Licensed pro app- Proposed difficulty
- 4 / 5
Proposed verifier
Training DB: transfer slip with 9 lines and status sent; voucher at 004 with quantities and short item recorded; inventory per store updated. Prism REST API access is disabled for the agent's user and no DB login is issued, so slips must be made in the Prism client.
Proposed partial credit
35% slip lines; 15% sent; 35% voucher received; 15% short recorded.
R05.13.01.02-T12 Flag cashiers with abnormal refund and void activity
Original instruction
From Square Dashboard reports (sandbox, last 30 days), find cashiers whose refunds exceed 3% of their sales or who logged more than 5 voids or no-sale drawer opens in any single shift. Write output/lp_flags.csv (employee, metric, value) and add the tag 'LP review' to each flagged team member.
- Platforms
web· Any OS (web)- Applications
- Square Dashboard
- Interfaces
brow· Browser- GUI need · task setting
HY· Hybrid- GUI need · ordinary access
G2· GUI-essential- Interaction primitives
nav· Pan/zoom/scrollclick· Point & clickvis· Visual judgment- Work product
WP12· Answer/decision- Conditions
- None declared
- Proposed difficulty
- 3 / 5
Proposed verifier
CSV equals key computed from sandbox transactions; flagged team members carry the tag; no others tagged.
Proposed partial credit
60% flags correct; 20% values; 20% tags.
R05.13.01.02-T13 Configure a mix-and-match promotion and test it at the register
Original instruction
In Lightspeed Retail (X-Series demo), create promotion 'Socks 3 for $20' (any 3 from tag 'socks', repeats, excludes 'premium' tag, outlet Harbor only, Oct 20-31). Then on the Lightspeed Register for iPad (simulator), ring up 7 socks (2 premium) and park the sale.
- Platforms
web· Any OS (web)ios· iOS/iPadOS- Applications
- Lightspeed Retail · Lightspeed Register
- Interfaces
brow· Browsermob· Mobile touch- GUI need · task setting
HY· Hybrid- GUI need · ordinary access
G3· GUI-only- Interaction primitives
click· Point & clicktype· Text & formstouch· Touch gestures- Work product
WP08· App/system state- Conditions
xdevice· Cross-device- Proposed difficulty
- 4 / 5
Proposed verifier
Promotion record conditions exact; parked sale total equals key (one 3-for-20 group applied once on 5 eligible socks + rest at price); promotion line present.
Proposed partial credit
45% promotion rules; 15% scope and dates; 40% register test total correct.
R05.13.01.02-T14 Fulfill in-store pickup orders including a partial
Original instruction
On Shopify POS (iPad simulator, location 'Downtown'), process the 6 local pickup orders: mark 5 ready for pickup (customer notified), and for order #1248 one item is missing: mark the available items ready and move the missing line to fulfill from location 'Warehouse' per input/pickup_policy.md.
- Platforms
ios· iOS/iPadOS- Applications
- Shopify POS
- Interfaces
mob· Mobile touch- GUI need · task setting
G3· GUI-only- GUI need · ordinary access
G3· GUI-only- Interaction primitives
touch· Touch gesturesnav· Pan/zoom/scroll- Work product
WP08· App/system state- Conditions
- None declared
- Proposed difficulty
- 4 / 5
Proposed verifier
Fulfillment orders: 5 orders ready-for-pickup with notification events; #1248 split with missing line reassigned to Warehouse location; others untouched. Shopify Admin API tokens are withheld from the agent, so this must be done in the POS app on the simulator.
Proposed partial credit
45% five ready; 40% partial handled with reassignment; 15% notifications.
R05.13.01.02-T15 Sell an out-of-stock item for ship-to-customer
Original instruction
On Shopify POS (iPad simulator), a customer wants 'Field Jacket L' which is out of stock at Downtown. Create a POS order with the jacket set to 'Ship to customer' from Warehouse with standard shipping $8, plus an in-hand 'Beanie', take card payment via the test card simulator, and capture the customer's shipping address from input/address.txt.
- Platforms
ios· iOS/iPadOS- Applications
- Shopify POS
- Interfaces
mob· Mobile touch- GUI need · task setting
G3· GUI-only- GUI need · ordinary access
G3· GUI-only- Interaction primitives
touch· Touch gesturestype· Text & forms- Work product
WP08· App/system state- Conditions
- None declared
- Proposed difficulty
- 3 / 5
Proposed verifier
Order: two fulfillment orders (jacket ship from Warehouse with shipping line 8.00, beanie fulfilled in store); shipping address exact; payment captured with test gateway. Shopify Admin API tokens are withheld from the agent, so this must be done in the POS app on the simulator.
Proposed partial credit
40% ship-to-customer line; 25% in-hand line; 20% address; 15% payment.
R05.13.01.02-T16 Complete sales through a network outage and resync
Original instruction
In Odoo POS (local server, browser kiosk), the network to the server drops during the second of 3 scripted sales (input/sales.md). Complete all 3 sales in offline mode, then after connectivity returns, sync the orders and close the session with the cash count from the script.
- Platforms
web· Any OS (web)- Applications
- Odoo POS
- Interfaces
brow· Browser- GUI need · task setting
G3· GUI-only- GUI need · ordinary access
G2· GUI-essential- Interaction primitives
click· Point & clicktouch· Touch gesturestype· Text & forms- Work product
WP08· App/system state- Conditions
interrupt· Interruptionshidden· Hidden/stale state- Proposed difficulty
- 4 / 5
Proposed verifier
pos.order: 3 orders synced with exact lines and payments, no duplicates; session closed with counted cash and difference; offline orders flagged by client timestamps. Odoo's /xmlrpc and /jsonrpc endpoints are firewalled and no API key is issued, so orders must come from the POS kiosk client.
Proposed partial credit
45% 3 orders correct; 25% no duplicates after resync; 30% session closed correctly.
R05.13.01.02-T17 Run a layaway from deposit to completion
Original instruction
In Lightspeed Retail R-Series (desktop app, demo store), create a layaway for 'Oak Bookcase' ($640) for customer 'Tom Bauer (synthetic)' with a 20% deposit in cash, take a second payment of $200 by test card, then complete the layaway with the remainder and release the item.
- Platforms
mac· macOSwin· Windows- Applications
- Lightspeed Retail R-Series
- Interfaces
desk· Desktop GUI- GUI need · task setting
G3· GUI-only- GUI need · ordinary access
G3· GUI-only- Interaction primitives
click· Point & clicktype· Text & forms- Work product
WP08· App/system state- Conditions
- None declared
- Proposed difficulty
- 4 / 5
Proposed verifier
Demo DB: layaway record with deposit 128.00, payment 200.00, final payment equals remainder plus tax per rule; status completed; item inventory released. Lightspeed Retail API credentials are withheld from the agent, so the layaway must be built in the desktop app.
Proposed partial credit
30% layaway with deposit; 25% second payment; 35% completion amounts; 10% released.
R05.13.01.02-T18 Control: post the aisle-4 count through the Lightspeed API
Original instruction
Control pair of T05. Using the X-Series API token in input/ls_token.env on a fresh copy of the demo account, create and complete the aisle-4 partial count from input/count_aisle4.csv with the same <= $20 rule and note.
- Platforms
lin· Linuxmac· macOSwin· Windows- Applications
- Lightspeed Retail API · Python
- Interfaces
api· API/SDKterm· Terminal- GUI need · task setting
AP· API-sufficient- GUI need · ordinary access
AP· API-sufficient- Interaction primitives
code· Code & commands- Work product
WP08· App/system state- Conditions
- None declared
- Proposed difficulty
- 3 / 5
Proposed verifier
Same end-state checks as T05.
Proposed partial credit
45% small variances applied; 35% large held; 20% note.
R05.13.01.02-T19 Run a full store day on a tablet POS
Original instruction
On Square POS for iPad (simulator, sandbox seller), run the day in input/day_script.md: open the drawer with $200, process 15 scripted transactions (sales, returns, exchanges, discounts, gift card sale, a no-sale), apply a midday price change to 3 items in the Dashboard, then close the drawer with the counted cash and save the close report.
- Platforms
ios· iOS/iPadOSweb· Any OS (web)- Applications
- Square POS · Square Dashboard
- Interfaces
mob· Mobile touchbrow· Browser- GUI need · task setting
G3· GUI-only- GUI need · ordinary access
G3· GUI-only- Interaction primitives
touch· Touch gesturestype· Text & formsmulti· Cross-app- Work product
WP08· App/system state- Conditions
long· Long-horizonmultiapp· Multi-app- Proposed difficulty
- 5 / 5
Proposed verifier
Sandbox payments/orders equal key for all 15 transactions (lines, tenders, refunds); price change effective only for later sales; drawer shift totals and difference exact. Square API tokens are withheld from the agent, so sales and price changes must come from the POS app and the web Dashboard.
Proposed partial credit
50% transactions (pro rata over 15); 15% price-change timing; 25% drawer close; 10% report.
R05.13.01.02-T20 Run an annual physical inventory with recount rules
Original instruction
In Dynamics 365 Commerce store operations (demo, store 'Seattle'), run the annual count for departments Apparel, Footwear and Accessories from input/counts/*.csv. Lines with variance > 5% or > $100 must be recounted using input/recounts.csv before posting; post the journal and export the variance report to output/variance.xlsx.
- Platforms
web· Any OS (web)win· Windows- Applications
- Dynamics 365 Commerce · Excel
- Interfaces
brow· Browserdesk· Desktop GUI- GUI need · task setting
HY· Hybrid- GUI need · ordinary access
G2· GUI-essential- Interaction primitives
click· Point & clicktype· Text & formsmulti· Cross-app- Work product
WP08· App/system state- Conditions
long· Long-horizon- Proposed difficulty
- 5 / 5
Proposed verifier
Counting journal posted; quantities equal recount where rule triggered, else first count; on-hand per item equals key; variance report matches.
Proposed partial credit
30% counts entered; 30% recount rule applied; 25% journal posted; 15% report.
Mapped research references
No benchmark reference is assigned to this class in the current mapping.
In this workflow family
- R05.13.01.01 Hotel & restaurant operations (PMS, POS)
- R05.13.01.03 Real estate & property management
- R05.13.01.04 Insurance claims & underwriting
- R05.13.01.05 Banking & lending operations
- R05.13.01.06 Construction estimating & field management
- R05.13.01.07 Facility & building automation operations
- R05.13.01.08 Service appointment scheduling (provider side)