Overview
Daily 07:30 AST credit-portfolio briefing: 12-rule anomaly engine flags early-delinquency signals, auto-generates SAMA Fintech Unit-compliant risk summary PDF, and pushes WhatsApp alert to credit committee. Portfolio review prep 4 h → 19 min; delinquency early-detection rate rises from 41% to 89%.
The challenge
Ruwad's credit team was pulling data from three disparate systems — Mambu loan origination, a custom SQL warehouse, and SAMA's open credit registry API — and manually stitching together a PowerPoint deck for the 8 AM credit committee meeting. The process consumed four hours of analyst time daily and the lack of systematic anomaly detection meant delinquency signals were often noticed only after the 30-day window for SAMA reporting had passed.
The solution
Lirevon built an overnight orchestrator that authenticates into all three data sources, runs 12 deterministic delinquency-signal rules (days-past-due trends, payment-frequency drops, sector-concentration spikes), and produces a structured JSON risk object. Gemini converts the JSON into a narrative Arabic summary with risk-tier colour coding. The final PDF is formatted to match SAMA Fintech Unit reporting templates and delivered to the credit committee via WhatsApp and email by 7:30 AM.
Outcomes
Daily portfolio review preparation time fell from 4 hours to 19 minutes, saving 65 analyst hours per month
Early delinquency detection rate improved from 41% to 89%, enabling proactive restructuring conversations
Zero SAMA reporting deadline misses since go-live, down from three in the preceding quarter
Credit committee meeting duration reduced from 90 minutes to 35 minutes due to pre-digested briefing material
Key metrics
Tech stack
Services
Client testimonial
“We used to walk into the credit committee with stale data. Now the briefing is on everyone's phone before they've finished their morning coffee.”
— هند المطيري، رئيسة قسم الائتمان
Related work
Full-service digital marketing agency · Riyadh
Automated weekly client performance report: aggregates Google Ads, Meta, TikTok, and GA4 data, applies 9-rule anomaly engine, and delivers a branded Arabic PDF plus WhatsApp voice-note summary to each client. Report prep 3.5 h → 14 min per client; client churn drops 22%.
Result:Report prep 3.5h → 14min/client; client churn −22%
Long-haul trucking company (42 trucks) · Dammam–Riyadh corridor
Daily fleet-pulse report: GPS telematics anomaly engine (harsh braking, idle-excess, route deviations), automated SFDA waybill-compliance checks, and WhatsApp driver-alert system. Fuel cost per km drops 14%; SFDA compliance violations fall from 22/month to 1.
Result:Fuel cost/km −14%; SFDA violations 22 → 1/month
Multi-brand FMCG distributor (18 SKU families) · Jeddah
Self-hosted Metabase instance with 22 dashboards covering sellout velocity, territory performance, and returns analysis — replacing monthly Excel decks with live answers accessible to all 60 territory reps.
Result:Monthly report prep 3 days → real-time; territory disputes −74%
Book a free 30-minute audit, or message us on WhatsApp. We'll send a fixed-price proposal in two days.