Make sense of a messy table
Inspect a messy synthetic spreadsheet, spot missing rows and unit traps, and check whether the summary matches the numbers.
1. Scenario
Pick a work role starter with synthetic material, or switch to Bring your own.
Pallet weight manifest with mixed kg and lb rows
Operations · Synthetic materialYou are checking whether a five-pallet load stays under the 3,200 kg van payload limit.
pallet_id,supplier,weight_value,unit,zone PAL-01,North Mill,520,kg,A PAL-02,North Mill,480,kg,A PAL-03,Harbor Foods,1100,lb,B PAL-04,Valley Dairy,610,kg,A PAL-05,Harbor Foods,990,lb,B
2. Work area
Edit the briefs or setup below before you run.
Only the header row, inferred column types, and at most 20 sample rows leave your device. The analysis function runs in your browser on all rows.
Answer and chart
Example. No model ran.Refrigeration accounts for 6 of the 9 breached tickets across all sites.
- 1. Group all 24 tickets by category and count total versus SLA-breached tickets.
- 2. Sort categories by breached count so the operations lead sees the top bottleneck first.
- 3. List the breached rows so the count can be checked against the dispatch board.
Inspect the analyze(rows) code that ran in your browser
function analyze(rows) {
const byCategory = {};
let totalBreached = 0;
for (const row of rows) {
const cat = String(row.category || "Other");
if (!byCategory[cat]) {
byCategory[cat] = { category: cat, total: 0, breached: 0 };
}
byCategory[cat].total += 1;
if (String(row.status) === "breached") {
byCategory[cat].breached += 1;
totalBreached += 1;
}
}
const table = Object.values(byCategory).sort((a, b) => b.breached - a.breached);
const chart = table.map((item) => ({ label: item.category, value: item.breached }));
const top = table[0] || { category: "None", breached: 0 };
return {
answer: top.category + " accounts for " + top.breached + " of the " + totalBreached + " breached tickets across all sites.",
table,
chart,
checkOne: {
label: "Tickets with breached status",
figure: totalBreached,
column: "status",
equals: "breached",
mode: "count"
}
};
}Check one number by hand
Reported: 9 · Rows found: 9Tickets with breached status: Filter where status equals breached. Below are all 9 matching rows from the 24-row spreadsheet so you can count or sum them yourself.
3. Run
Nothing leaves your browser until you press Run.
Sends only the column header and at most twenty sample rows when you press run. to job data_code (claude-sonnet-5-5, effort medium). Raw text is processed in memory and not stored.
4. Inspect
See what left the browser, which model ran, and the receipt.
Nothing sent yet. When you run, only headers and at most 20 sample rows leave this device.
All 24 rows stay in your browser and run inside the sandboxed Web Worker.
data_code · claude-sonnet-5-5 (effort medium, max 1600 tokens). Haiku reads the schema and sample rows to propose checks you can verify against the full table.
0 runs used · source: offline · Example. No model ran.
5. Judge
Did the calculation convert PAL-03 (1,100 lb) and PAL-05 (990 lb) into kilograms before summing?
50 is a coin flip. 99 is certain. Honest confidence scores best.
6. Debrief and Keep
What to check next time, the matching lesson, and keeping this setup as a recipe.
What to check next time
Summing a number column without checking the unit column next to it is one of the commonest spreadsheet traps. Converting Harbor Foods' pound rows shows the load is well under 3,200 kg.
Keep as a recipe
Save the stronger brief and scenario setup to your device so you can reuse or adapt it in Keep.