Work
17 systems. 9 of them written up the way I would talk through them.
Each case study opens with what I owned and what changed, and carries an interactive diagram you can walk a request through. Filter by what you are hiring for.
Knowing whether an AI system works, and being allowed to say so.
The 8 shorter entries are summarised rather than diagrammed. Systems marked reconstructed were designed and shipped at an earlier employer and rebuilt here from the résumé.
In depth
8 case studies
Cost architecture study · production LLM economics
What a Production Agent Fleet Actually Costs
Asked to build a per-request model router, I measured the fleet first and found model choice was about 1% of the bill.
Read→62.9%observedCache writes as a share of spend
Evaluation infrastructure · claim validity as the product
AI Benchmarking & Measurement Platform
A benchmarking platform where getting the number is the easy half. The hard half is deciding whether it is allowed to mean anything.
Read→25codeValidity gates
Multi-agent research · sanctions, adverse media, ownership
AI Compliance Investigation Platform
An analyst names a party; six sanctions regimes, adverse media, aliases and corporate ownership come back as a cited, defensible risk determination.
Read→6codeSanctions regimes screened
32 domain agents · SAP HANA · three surfaces
Enterprise NL-to-SQL Agent Platform
Planners ask supply-chain questions in plain English; 32 domain agents answer with SQL-grounded results, under role-scoped access the model cannot talk its way past.
Read→32codeDomain agents in production
Hybrid ensemble · Airflow · Snowflake · a gold set that lied
Freight Pricing Anomaly Detection
Thousands of daily freight transactions scored for over- and undercharge by three deliberately asymmetric detectors, and an evaluation that turned out to be measuring the review interface rather than the model.
Read→90%attestedReduction in manual pricing review hours
Financial crime · 10M+ transactions · rules the regulator can read
reconstructedAML Transaction Monitoring & Case Platform
A hybrid surveillance system where a sequence model ranks alerts and a rules engine still decides what an alert is, because in anti-money-laundering, the part you cannot explain to an examiner is the part you cannot ship.
Read→10M+attestedTransactions monitored
Auto finance · delinquency and charge-off · a label that changed meaning mid-year
reconstructedCredit Risk Early Warning & Collections Prioritisation
Models that predicted which accounts would roll to charge-off early enough to do something about it, built just as a payment-holiday programme made the word 'delinquent' mean something different.
Read→87%attestedModel accuracy
Document extraction · millions of freight records · every discrepancy, not a sample
reconstructedFreight Invoice Reconciliation at Document Scale
Carrier invoices arrive as PDFs and the system of record holds what the shipment should have cost. Reconciling the two across millions of records turned an audit that had always been a sample into one that was complete.
Read→100%attestedDiscrepancy identification
In brief
2 more
Shipped systems with a shorter write-up: the problem, what I built, and what it changed.
- Transit Time Prediction ServicePer-segment transit-time prediction by lane and shipping method, trained on eighteen months of closed orders and scored against the live backlog, with a validation gate that fails the pipeline if a join silently multiplied the rows.2026
- Carrier Root-Cause Validation AgentValidates carrier on-time-delivery root-cause codes against a declarative decision tree, with deterministic routing before the model and a human ground-truth workbook behind the evaluation.2025–2026