One-minute narrated stories of a flow at work. The scenarios and figures are illustrative, not customer results.
Commercial banking
The challenge. Ethan leads credit monitoring for small business loans at a big Chicago bank. His team watches over two thousand borrowers. A borrower’s trouble usually shows up in the local news weeks before a missed payment: a fire, a lawsuit, a plant closing. Nobody has time to read every paper. Last winter a warehouse fire made the evening news, and the bank found out a month later.
The flow. With xMap Flows, Ethan built Waypoint. Every morning at six, Waypoint reads the city’s business news and keeps stories about fires, closures, layoffs and lawsuits, matches them with the bank’s borrowers, writes what each story could mean for the loan, and posts it to the credit team’s channel.
The result. On Wednesday, Waypoint read three hundred stories and found two about borrowers: a fire at a bakery supplier in Pilsen and layoffs at a printing firm. Ethan’s team called both owners before lunch, and reworked one loan before a payment was missed. Ethan’s team used to read about trouble a month late. Now they call the same morning.
300stories read each morning
2borrowers flagged on Wednesday
0payments missed first
Blocks: Schedule → News → Match with my table → xMap LLM → Microsoft Teams
Watch the one-minute story →
Microfinance
The challenge. Nadia manages a branch of a microfinance bank in Dhaka. Her twelve field officers visit about three hundred borrowers a week to collect repayments. Each officer plans their own day, and Dhaka’s roads decide the rest. One closed road can cost an officer half a day, and the borrowers at the end of the list wait at home for nobody. Missed visits turn into missed payments.
The flow. With xMap Flows, Nadia built Wayfinder. Every morning at seven, Wayfinder takes the day’s visits, flags any road closure near each one, splits them fairly between the twelve officers, plans each officer’s best visiting order, and sends the branch the day’s routes.
The result. Now each officer leaves the branch with a fair list in the best order, and the visits near a closed road marked to call first. The branch made two hundred and ninety visits last week, up from two hundred and forty. Nadia’s officers still face Dhaka’s roads. They just stopped facing them blind.
290visits last week, up from 240
12fair routes every morning
7 amroutes ready, every day
Blocks: Schedule → My data → Traffic incidents → Split by territory → Route planner → Email
Watch the one-minute story →
Mortgage lending
The challenge. Omar heads mortgage risk at one of Riyadh’s largest banks. His team signs off on thousands of home loans a year. The credit committee prices risk from a valuation report that is three months old. By the time it lands, prices in the fast-growing north have moved. Two analysts spend a week each quarter pulling sales by hand, and the numbers still arrive late.
The flow. With xMap Flows, Omar built Ledger. Every Sunday at seven, Ledger brings in last week’s recorded property sales across Riyadh, keeps the homes that sold with a price, labels each one a small, family or large home, writes what moved, district by district, and sends the committee a report before Monday’s meeting.
The result. On Monday the committee reads last week, not last quarter: about nine hundred home sales, and a note that family villas in the north sold for the most per metre. Omar’s analysts spend their week on the loans, not the spreadsheets. The committee stopped looking back a quarter. Now it starts each week on fresh sales.
900home sales read each week
7 daysold at most, not ninety
0weeks of pulling sales by hand
Blocks: Schedule → Regional data sources → Filter → Calculated field → xMap LLM → Make a report
Watch the one-minute story →
Small business lending
The challenge. Thandi is a loan officer at a small lender in Durban. She lends to spaza shops, salons and takeaways in the townships. Every application comes with a story, and she cannot visit every street. Some shops have already closed by the time the money lands. Others sit on a street with five copies of the same shop. Last year one in six of her loans went bad.
The flow. With xMap Flows, Thandi built Streetwise. When a new loan application comes in, Streetwise finds the shop on the map and checks it is open, counts the same kind of shop within five hundred metres, judges how likely the shop is to keep trading, asks Thandi to approve, and sends the owner the answer on WhatsApp.
The result. This week, Streetwise checked thirty applications in an hour. Two shops had already closed, and one salon had seven others within a short walk. Thandi spent her afternoons with the strongest twenty, and gave each an answer the same day. Thandi still trusts her instinct. Now the street backs it up.
30applications checked in an hour
2closed shops caught before paying
1 dayfrom application to answer
Blocks: New rows → Map business scan → Nearby places → Jev decision → Approval → WhatsApp Business
Watch the one-minute story →
Retail banking
The challenge. Mei runs the cash machine network for one of Shanghai’s largest banks. Her team looks after four hundred machines across the city. Every year she decides which machines to move, using last year’s withdrawals. But streets change fast: a mall opens, a market closes, and a busy machine goes quiet. Moving one costs a small fortune, so a wrong guess hurts twice.
The flow. With xMap Flows, Mei built Atlas. On the first day of each quarter, Atlas takes the bank’s four hundred machines, counts the shops and restaurants within three hundred metres of each, gives each machine a busy score, picks the quietest twenty, and adds them to the team’s network plan.
The result. This quarter, Atlas flagged twenty quiet machines. Six stood on streets where most of the shops had closed. Mei’s team moved those six first, and checked the other fourteen on the ground. Mei stopped moving machines on last year’s numbers. She moves them to where people are.
400machines checked each quarter
20quiet machines flagged
6moved first, no guessing
Blocks: Schedule → My data → Nearby places → Calculated field → Sort and limit → Microsoft Excel 365
Watch the one-minute story →
Payments
The challenge. Madison sells card machines and payment apps to restaurants in Miami, on her own commission. A new restaurant is still trying things in its first weeks, and that is when it switches how it takes payment. Madison drives Little Havana and Wynwood looking for new signs, but most weeks she finds them months late, locked into a rival’s contract.
The flow. With xMap Flows, Madison built Pilot. Every Monday at seven, across Miami, Pilot finds the restaurants and cafes that opened in the last three months, skips the ones it has already sent her, sorts them into cafes, food trucks and full restaurants, keeps the best rated twenty, and emails her the week’s list.
The result. This Monday her list had twenty-six new places, among them nine new cafes in Wynwood. Madison visited the best twenty by Wednesday, every one still in its first months, and signed six of them by Friday. Madison stopped hunting for opening signs. The new places now come to her inbox.
26new places in one week
20visits, all to new places
6signed by Friday
Blocks: Schedule → Area of interest → Nearby places → Only new → Place classifier → Sort and limit → Email
Watch the one-minute story →
Mobile money
The challenge. Grace leads agent growth at a mobile money company in Kigali. Its agents are the corner shops where people put cash in and take it out. She picks new agent spots from a paper map and the sales team’s hunches. Some new agents open beside three others and starve. Meanwhile busy markets and bus parks have none, and people walk twenty minutes to send money home.
The flow. With xMap Flows, Grace built Periscope. On the first Monday of each month, across Kigali, Periscope finds the markets and bus stations, finds the company’s nearest agent to each, keeps the ones with no agent within a kilometre, and draws the gaps on a map for the sales team.
The result. This month, Periscope found fourteen markets and bus parks with no agent within a kilometre, including busy stops near Nyabugogo. Grace signed eight new agents there in a fortnight, and the first ones already take hundreds of payments a day. Grace stopped guessing where people need money. Now she goes where they already are.
14gaps found this month
8new agents in two weeks
1 kmor less to an agent now
Blocks: Schedule → Area of interest → Nearby places → Find nearest → Filter → Show on a map
Watch the one-minute story →