Zenpanik
Scheduling the money: job shops, Hungarian matching and AI agents in paymentsBy Pavel Nikolov, November 8, 2026

Part 5: Where it breaks

Part 5 of 5 in a deep dive on money movement as an optimization problem, and how AI agents can use scheduling and matching algorithms. Start with Part 1 if you are new to the series.

Six ways it fails

A solver does exactly what the model says, at machine speed. Every failure below comes from that.

Bad costs in, confident plans out
A stale FX quote or a mistyped PSP fee sends the whole batch the wrong way, faster and more consistently than a person would. Fees are the weakest input, because they sit in each provider's own settlement report format. Compare planned costs with realized ones every day and treat a gap as an incident.
The solver finds every rule you forgot
If no constraint says “no more than 40% of volume through one PSP,” a solver will put everything through the cheapest one until its contract cap breaks. Mandate limits, sanctions rules and concentration caps belong in the model as hard constraints, and the validator from Part 4 checks them again outside it.
Optimization eats buffers
In 2024 each dollar of CHIPS funding settled about $29 of payments. In 2025 it settled $26, because bank treasurers chose to pre-position extra liquidity in volatile conditions. They gave up some efficiency to buy certainty. An agent should be told to do the same, with the minimum balance as a hard constraint the solver cannot trade against fees.
Agents herd
If many treasury agents run similar solvers on the same public quotes, they all pick the same cheapest off-ramp at the same minute, its capacity fills and its spread moves. Treat shared capacity as a constraint and cap the share of any single route.
The executing agent is an automated signer
In my last deep dive, Binance's signing service did what an authenticated caller asked and about $6.3 billion left. An agent that executes its own plan needs the same rule: it proposes, and people approve the irreversible, high-value steps.
Big problems need time limits
Job shop scheduling is NP-hard, so a large day may not solve to proven optimality in minutes. Run with a time limit, take the best plan and its bound, and replan on a rolling horizon.
No cap per routeOff-ramp A, cheapestOff-ramp BBank wire9 treasury agentsover capacityCap of one third per routeOff-ramp A, cheapestOff-ramp BBank wire9 treasury agentsIllustrative. The dashed amber line marks the off-ramp's capacity for this window.
Figure 7. Herding. The same nine agents, with and without a cap on any single route. Without one, every agent picks the cheapest off-ramp at once and overruns it.

A Taleb lens

Taleb's turkey is the warning behind the buffer and herding failures. A plan that has worked for a thousand Fridays says little about the Friday an off-ramp partner freezes or a correspondent bank fails.

In his 2013 letter to Stewart Brand, Taleb's first precautionary rule is to split sources of harm into small, independent pieces. For a treasury agent that means caps per rail, per partner and per account, written into the model so the optimizer cannot take them out.

Final thoughts

Money movement has always been scheduling and matching, and CHIPS shows the payoff at $5.5 billion a year. Agents change who writes the model. A fintech that could never afford an operations research team can now have an agent turn its Friday into a cost matrix and a schedule in seconds, and hand both to algorithms that operations researchers have refined since the 1950s.

What the agent owns

The framing: reading the mandate, pricing the routes, noticing that a rail closes in 30 minutes, and replanning when a partner pauses.

What the solver owns

The answer and the proof. Buffers and caps stay outside its reach as hard constraints, and people keep the irreversible steps.

The cheapest place to start is one recurring decision with a clear cost, such as choosing funding sources or matching bank statement lines. Let the agent build the matrix and run the Hungarian method in shadow mode for a quarter, compare its choices with what the team actually did, and only then let it move money.

Sources

  1. CHIPS delivers record value and resilience for participants in 2025, The Clearing House, April 7, 2026
  2. The strategic role of CHIPS, The Clearing House
  3. Clearing House Interbank Payments System, Wikipedia
  4. Fedwire Funds Service, Federal Reserve Board
  5. Fedwire Funds Service and NSS operating hours, Federal Reserve Financial Services
  6. Board memo on expanding Fedwire and NSS to 22x6, Federal Reserve Board, October 2025
  7. FedNow network limit increases, Federal Reserve Financial Services, November 12, 2025
  8. Outcome of the public consultation on the extension of T2 operating hours, ECB, 2026
  9. Eurozone payment systems and T2 cut-offs, BNP Paribas Cash Management
  10. SEPA Instant Credit Transfer, PXP
  11. Hungarian algorithm, Wikipedia
  12. Kuhn's algorithm and Jacobi's 1890 solution, Wikiwand
  13. Hungarian algorithm for the assignment problem, cp-algorithms
  14. An algorithm for solving the job-shop problem, Carlier and Pinson, Management Science, 1989
  15. A computational study of the job-shop scheduling problem, Applegate and Cook, 1991
  16. LLMs can schedule, Abgaryan, Harutyunyan and Cazenave, arXiv
  17. Starjob: dataset for LLM-driven job shop scheduling, arXiv, 2025
  18. OptiMUS-0.3: using large language models to model and solve optimization problems at scale, arXiv
  19. Two clocks: quantum breaks the math, AI breaks everything around it, Zenpanik
  20. Fintech Wrap Up deep dives: Adyen Agentic; the Machine Payments Protocol; Shopify and Google's Universal Commerce Protocol and AP2; JPMorgan's payments strategy; data intelligence in a multi-PSP stack
  21. Nassim Nicholas Taleb, letter to Stewart Brand on fragility and precaution, July 3, 2013
Back to Part 1