Zenpanik
Deep Dive

Scheduling the money: job shops, Hungarian matching and AI agents in payments

Every Friday afternoon, a treasury team solves a scheduling problem and a matching problem by hand. AI agents can frame both problems. Algorithms from the 1950s and 1960s already solve them.

By Pavel Nikolov, November 8, 2026
Bank ABank BPayment queueNet funding
Payments going opposite ways cancel in the queue. Only the difference needs funding.

On an average day in 2025, banks settled $2.014 trillion through CHIPS, The Clearing House's large-value dollar system, and funded it with about $96 billion. Under plain real-time gross settlement, the same payments would have needed an estimated $442 billion (The Clearing House, April 2026). The gap is an algorithm. Payments wait in a queue, and the CHIPS engine keeps choosing which ones to release, alone or offset against others, so each dollar of funding settled about $26 of value.

Funding needed to settle $2.014 trillion of payments a day, 2025Gross settlementestimate$442 billionCHIPS algorithmactual average$96 billionAbout $346 billion of funding stays free for lending and investment, worth an estimated $5.5 billion a year.
Figure 1. The same payments, two ways to settle them. Source: The Clearing House.

That is a scheduling decision, made continuously. Most other money movement still runs on the same kind of decision, made by people with spreadsheets and a calendar of cut-off times.

A treasury team on a Friday afternoon is solving a scheduling problem. Which payments go first, through which rail, funded from which account, before which window closes? A reconciliation team on Monday morning is solving a matching problem: which bank statement line belongs to which invoice, and which ones belong to nothing.

AI agents are now being handed parts of this work. Adyen launched Adyen Agentic on June 16, 2026, Google's AP2 lets an agent present a signed mandate at checkout, and the Machine Payments Protocol makes payment the authentication step for API calls (Fintech Wrap Up covered all three in its deep dives). Agents that buy things will soon be agents that move money between accounts, rails and currencies.

Language models frame

An agent can read “get the suppliers paid before the weekend without dipping below our buffer” and turn it into variables, costs and constraints. It can read a mandate, price a route and notice that a rail closes in 30 minutes.

Solvers decide

Job shop scheduling has had a standard benchmark since 1963. The Hungarian algorithm dates from 1955. Both return a plan and a measure of how good it is, which a language model guessing at the answer cannot.

I think the useful design for payment agents is that old pairing. Part 2 treats money movement as a job shop, with rails as machines and cut-offs as deadlines. Part 3 uses the Hungarian algorithm to decide who pays what, with a worked Friday-afternoon example. Part 4 shows how an agent frames the problem, hands it to a solver and runs the plan. Part 5 covers where this breaks, including the Taleb problem with optimizing away every buffer.

The rails, as a scheduler sees them

Every rail is a machine with opening hours, a capacity and a processing time. Their calendars do not line up, and the gaps between them are where most of the scheduling work sits.

MonTueWedThuFriSatSunFedwireT2 (euro)FedNowSEPA InstantStablecoinsFedwire closed for 50 hoursNew York time in November; CET is six hours ahead. Open hours only; customer cut-offs fall earlier.
OpenWeekend
Figure 2. A week on five rails. The cursor runs through the week: wherever it crosses a gap, a payment on that rail waits. Sources: Federal Reserve, ECB, FedNow, PXP.
RailOpenCut-off or limitHow it settles
Fedwire Funds9 p.m. ET the day before to 7 p.m. ET, Monday to FridayCustomer transfers close 6:45 p.m. ETGross, final, central bank money
CHIPSAbout 21 hours per business dayPrefunded balance; payments queue until the algorithm releases themContinuous netting, final on release
FedNow24/7/365$10 million network limit since November 12, 2025Gross, instant
T2, the euro RTGS22.5 hours, 19:30 to 18:00 CET, Monday to FridayCustomer payments 17:00 CETGross, final, central bank money
SEPA Instant24/7/365Funds in under 10 seconds; euro-area PSPs must send since October 2025Instant
Tokenized deposits (JPM Coin on Kinexys)24/7Limited to the bank's client networkAtomic, on a permissioned ledger
Public stablecoins (USDC, USDT)24/7On- and off-ramp capacity, conversion spreadDepends on the chain's finality

The weekend shows the problem most clearly. From Friday 7 p.m. ET to Sunday 9 p.m. ET, Fedwire is closed, while FedNow, SEPA Instant and every stablecoin keep running. The Federal Reserve will open Fedwire on Sundays and weekday holidays in 2028 or 2029, and the ECB's 2026 consultation sets a path toward a near 24/5 T2.

Tokenized money removes the window and adds other limits. Corporate clients already use JPM Coin for overnight liquidity moves, and can pay between their own accounts in two countries on a Saturday (Fintech Wrap Up's deep dive on JPMorgan's payments strategy). A stablecoin payout still has to land in a bank account at the other end, through an off-ramp partner with its own limits and hours.

So the inputs to every Friday decision are calendars, capacities, costs and deadlines. That is the vocabulary of a job shop.

Continue to Part 2: Money movement as a job shop