Dev Seth
← All work
Pharma & healthcareLive

Getting life-critical medicine to patients in time

An end-to-end platform for a UK manufacturer of late-stage cancer injections with a three-day half-life, planning, tracking and flagging risk from production to patient.

Risk modelAlertsProductionHalf-life-awareplanningShipmentPatient
30%

fewer delivery failures

3-day

half-life on every dose

End to end

from production facility to patient

the situation

The product loses its potency within days. A late shipment isn't a logistics problem, it means a patient misses treatment.

the hard part

Planning had to account for decay, demand and transit time all at once, and problems had to be caught before they happened rather than reported after.

what i built

01

Half-life-aware planning

Scheduling for manufacturing and shipments that accounts for decay constraints and demand patterns.

02

AI risk flagging

Identifies shipments at risk early, so the team can act before a dose is lost.

03

Real-time monitoring

Visibility from the production facility through to patient delivery.

04

End-to-end optimisation

Manufacturing planning and shipment logistics optimised as one system rather than separately.

how it fits together

Risk modelAlertsProductionHalf-life-awareplanningShipmentPatient

results

  • Cut delivery failure rates by 30%.
  • Live tracking across the full journey from facility to patient.

stack

Forecasting & optimisationRisk modelsReal-time data pipelinesCloud deployment

next case study

GovernmentIn production

Round-the-clock citizen service, with intelligence on every conversation

A bilingual voice AI assistant for a government entity in the Middle East that answers citizens 24/7 and shows leadership what people are actually calling about.

24/7service, up from 12 hours a day

200+enquiries handled every day

Citizen callSpeech recognition(AR/EN)Voice agentResponseConversationintelligenceManagementassistant
Read the next case study →

Open to partnerships and select projects.

If you're building something where AI has to work in production, or has to stay private, I'd like to hear about it.