Known peaks still catch teams out
Salary day, Diwali, Eid, Black Friday. Everyone knows they're coming, but capacity plans rarely link them to monitoring and screening workloads.



28 specialized agents
See an agent work your alert queue
AI agents investigate and prepare the case. Your analysts decide, with evidence an examiner can replay.View All Solutions
Rhea LedgerSenior AI KYC/AML Compliance DirectorKYC/AML & Sanctions Screening
Iris VermaSenior AI Identity Verification SpecialistIdentity Verification & KYC
Nova SentinelLead AI Zero Trust Security ArchitectZero Trust Access Security
Cian GatekeeperLead AI Customer Identity DirectorIdentity Management & Account Takeover
Zara TrustwellDirector AI Regulatory ComplianceSTR / SAR Reporting & Regulatory Evidence
Arin NarrateSenior AI Audit Trail SpecialistAudit Trail & Evidence Management
Riya IntelDirector AI Governance & Model RiskModel Governance & Model Risk
Nolan BriefwellSenior AI Incident Response NarratorCase Management & Investigations


28 specialized agents
See an agent work your alert queue
AI agents investigate and prepare the case. Your analysts decide, with evidence an examiner can replay.View All AI Agents


28 specialized agents
See an agent work your alert queue
AI agents investigate and prepare the case. Your analysts decide, with evidence an examiner can replay.View All Industries
Percy Planner: Senior AI Capacity Planning StrategistPercy Planner is an AI agent that forecasts how much compute and storage your transaction monitoring and sanctions screening will need. He reads transaction growth, seasonal peaks and new product launches, then recommends capacity changes to your platform team. The goal is simple: checks keep pace with volume, every day of the year.

Payment volumes grow every quarter and spike on salary days, festivals and sales events. Monitoring and screening capacity is usually sized once and revisited after something goes wrong. When checks fall behind, queues build, alerts arrive late and instant payments settle before anyone looks.
builds when checks can't keep up
Instant payments don't wait for capacity.
Salary day, Diwali, Eid, Black Friday. Everyone knows they're coming, but capacity plans rarely link them to monitoring and screening workloads.
A new wallet, a UPI or FedNow launch, or a merchant partnership can change volume overnight. Compliance systems often hear about it after go-live.
Operational resilience reviews ask whether critical services can absorb stress. A capacity decision made in a meeting with no record is hard to defend.
Percy Planner is a Senior AI Capacity Planning Strategist. He reads your volumes and system metrics, forecasts what monitoring and screening will need, and recommends changes to the people who own capacity.

We don't publish forecast accuracy from our own tests. Measure Percy Planner's forecasts against your actual volumes, next to your current planning, before you act on them.
Percy Planner reads metrics and volumes through APIs. He doesn't need write access to your infrastructure to start.
Transaction volumes by channel, processing times from monitoring and screening, resource metrics from your cloud or data centre, and your calendar of launches and campaigns arrive through APIs.
Percy combines a forecasting model with seasonal patterns and known events. Signals from Theo Surge on real-time spikes feed back into the next forecast.
Your autonomy settings decide what happens next. Pre-approved scaling steps can apply on their own if you allow it. Other recommendations go to your platform lead by default. Anything that puts monitoring or screening coverage at risk always goes to the platform lead and MLRO.
Every forecast comes with its assumptions, the data behind it and the service it affects. Forecasts, recommendations and approvals go into tamper-evident evidence storage.
Run Percy Planner in shadow mode on your volumes. He forecasts and recommends, and nothing in your infrastructure changes. Compare his forecasts with what actually happened before you rely on them.
Percy doesn't make you resilient. He produces the evidence these frameworks expect about how you size critical compliance services.
Capacity planned around compliance load, with a record of why.
| CRITERIA | Spreadsheet forecast | Cloud autoscaling alone | Percy Planner |
|---|---|---|---|
| When it acts | At the next planning cycle | After load arrives | Ahead of forecast peaks |
| Who decides | Platform team | Scaling rules | Platform lead, inside bands you set |
| Knows compliance workloads | If the author does | No, it sees CPU and memory | Yes, monitoring and screening are sized separately |
| Handles known events | Manually | No | Yes, from your launch and campaign calendar |
| Evidence for examiners | A spreadsheet version | Scaling logs | Forecasts, assumptions and approvals on record |
| Where it's weaker | Stale between cycles | Reacts late to sudden peaks and can't scale fixed systems | Forecasts are only as good as your history and event calendar, and new products have little of either |
Percy plans ahead. These agents handle what happens on the day.

Tells legitimate peaks from attack spikes in real time and feeds that back into Percy's forecasts.
Meet Theo
Watches latency and uptime of monitoring and screening, so Percy sees where capacity is already tight.
Meet Sol
Shares the volume changes a core migration will bring.
Meet CoryLow risk can run on its own if you allow it. Medium risk goes to a person by default. High risk always goes to a person. You set the bands per rule, channel and transaction type.
Turn Percy off without touching the other agents or your core systems. The switch, and who used it, is stamped on the record.
Run Percy on live data with nothing blocked or closed. Compare the calls with your team's before anything changes.
Every decision answers why, in plain English, with the signals and the rule or policy behind it.
Each decision is stored with its inputs, its reasoning and the person who approved it, in tamper-evident evidence storage.
Agents connect beside your systems through APIs. Your core banking, screening and case tools stay where they are.
What we're learning about AML, fraud and the evidence examiners ask for.






Talk to the people who build the agents. We'll answer per capability, yes or no.
Percy Planner forecasts the compute and storage your monitoring and screening need, using transaction growth, seasonal peaks and your launch calendar. He flags shortfalls ahead of time and recommends changes to your platform team with the forecast attached.
Only where you allow it, and only with scaling steps you've pre-approved. Other recommendations go to your platform lead by default, and anything that risks screening or monitoring coverage always goes to a person. A kill switch turns Percy off without touching your other systems.
Autoscaling reacts once load arrives and only works where systems can scale on demand. Percy plans ahead for known peaks and growth, and he sizes monitoring and screening specifically.
Percy forecasts on your real volumes and makes recommendations, but nothing changes. You compare his forecasts with what actually happens before acting on any of them.
Transaction volumes by channel, processing times from monitoring and screening, resource metrics, and a calendar of launches and campaigns. More history gives better forecasts.
Yes. He reads metrics through APIs. On fixed infrastructure his recommendations give your team more lead time to add capacity.
FluxForce runs as SaaS, on-premise or hybrid, built on Microsoft Azure. We agree data residency and which components run inside your environment during deployment design, before any data moves.
Run Percy Planner beside your current process. He works on your live data and records every call, and nothing is blocked, closed or sent until you decide.
Shadow mode results belong to you.
Start with one workflow in shadow mode, then decide how much each agent does on its own.
Share a few details and we'll email the deck straight to your inbox.