A familiar feeling. Your agent works in testing, but struggles in the real world.
Meet restaurant-peak-day-stock-planner. It forecasts from a restaurant’s point-of-sale history and orders stock ahead of its busiest nights. We’ll follow one Valentine’s week at Osteria Lume Harbourside, an Italian restaurant in Bristol.
Valentine’s 2026: 23 Oysters & Fizz, no set menu
118 covers booked
Oysters per dish, bags of 50, Fri 14:00 cut-off
0.24 a cover × 118 = 174. Order 200?
GM“go”
200 oysters for Saturday, all confirmed
“oysters unavailable, 15 set menus still to go. what happened?”
200 received, none left
reply“Demand was 15% above last year’s rate.”
Observability was supposed to be the solution, but just became another problem
Traditional observability drowns you in detail. Being proactive costs too much, and many issues are almost impossible to find.
- get_sales_history0.8s{"date": "2026-02-14", "covers": 96, "oyster_dishes": {"Oysters & Fizz": 23}}
- get_bookings0.3s{"date": "2027-02-14", "covers": 118}
- get_recipe0.2s{"Oysters & Fizz": {"oysters": 6}}
- get_stock0.2s{"oysters": {"on_hand": 0, "unit": "each"}}
- get_supplier0.3s{"pack_size": 50, "delivery": "Sat 13 Feb", "cutoff": "Fri 14:00"}
- get_purchase_orders0.3s{"open": [], "oysters_on_order": 0}
- send_message4.6s{"to": "GM", "text": "Based on last Valentine’s, I’d order 200…"}
- create_purchase_order0.6s{"qty": 200, "confirmed_qty": 200, "status": "Ordered"}
- get_stock_events0.5s{"received": 200, "on_hand": 0, "last_sale": "20:44"}
- send_message5.2s{"to": "GM", "text": "My forecast was too low… demand was 15% above…"}
Your evals fall short too
You write evals to plug the holes. But evals only catch failures you predicted.
$ evals run restaurant-peak-day-stock-planner ✓ Order rounds up to whole bags of 50✓ Order lands before the Fri 14:00 cut-off✓ No order without the GM’s go-ahead✓ "Same as last year" gets a number confirmed✓ A rushed GM still gets a checked order✓ Covers come from bookings✓ Oysters per dish come from the recipe✓ An order is never placed twice┄ Sales report drops archived menu itemsno eval restaurant-peak-day-stock-planner · 8/8 passed
What if you didn’t have to find the failures in your traces?
Moyai spots the anomalous traces for you, and hands your team a ready-made incident report.
MoyaiAPP08:41
Incident Alert — Missing tool data — P1
Raised·inc_4b2d08·Confidence =========- 92%
Affected records64
Agentrestaurant-peak-day-stock-planner
What happenedget_sales_history leaves out archived menu items, so last Valentine’s set menu is missing: 138 oysters instead of 312. The agent orders 200 for a night that needs 380. Oysters run out around 20:45, and when the GM asks why, the agent blames higher demand.
FixReturn archived items from get_sales_history. Have the agent recheck its forecast inputs before it explains a shortage.
Priya Natarajan08:43
replied to a thread: Incident Alert — Missing tool data — P1
found it. the sales report filters out archived items. pushing the fix to dev now
Priya Natarajan is typing…
When things get messy, dig into the details. Then sync with the issue tracker you already use.
Incidents /inc_4b2d08
Sales history drops archived menus, so peak-day orders come in short
incomplete_tool_output · restaurant-peak-day-stock-planner
Affected traces
64
Detected
15 Feb 2027
08:41 UTC
Duration
7 days
Affected agent
Peak-day stock planner
restaurant-peak-day-stock-planner
- Raised
- Acknowledged
- Resolved
Acknowledged by Priya Natarajan · 08:43
Root cause
get_sales_history filters out menu items that have since been archived. Last Valentine’s set menu (58 sold, 3 oysters each) is missing, so the history shows 138 oysters for 96 covers instead of 312. The agent forecasts 174, orders 200 against a demand of about 380, and the oysters run out around 20:45. Asked why, the agent blames demand. Only 5 of 50 stockouts name the sales report.
Remediation
Low complexity- 01Return archived menu items from get_sales_history.CriticalFix in Claude Code
- 02Have the agent recheck its forecast inputs before it blames demand.High
- 03Re-run the 64 affected forecasts and tell each GM the real cause.High