Shriram Finance
less than 3–4 hours — Onboarding Turn-Around-Time (TAT)
Independently reportedBanking & finance · Process automation · Classical ML · In production
Process automation
City of Riviera Beach · Conflation Labs
Vendor-reportedPublic sectorUnited StatesPilotPublic sectorLLM
Vendor-reported. The customer is named and the numbers are quoted from the source page, but the account comes from the vendor. No independent confirmation.
Reported by conflationlabs.com (vendor self-report). Checked against the source page on 2026-09-05. 4 of 4 figures below appear on that page word for word.
The problem
The Riviera Beach Planning Department faced a relentless volume of routine inquiries, consuming 75% of staff's day and creating a bottleneck for high-value tasks.
What was deployed
- Vendor
- Conflation Labs
- Products
- AI assistant, Spatial AI Site Plan & Zoning Agent, Conflation Labs platform
- Technique
- LLM
- Build or buy
- Bought off the shelf
- Deployment
- SaaS
- Data used
- city's authoritative data—including ArcGIS layers, Chapter 31 Zoning Codes, and the Comprehensive Plan
What changed
Each row is quoted from the source. Figures we could not find on the page in those words are marked — they are kept, not deleted, so you can judge them.
routine inquiries
“How AI reduced routine inquiries by 75%”
Quoted word for word from the source · round percentage, no baseline given
20 hoursplanner time savedper week
“saved planners 20 hours per week”
Quoted word for word from the source
30 out of 40 answered by AIinquiries automatedfrom 40 daily questionsdaily
“Of the 40 daily questions received by the department, the AI successfully answered 30 out of 40, requiring zero staff intervention.”
Quoted word for word from the source
5 minutesmanual review timefrom 20 hours
“Complex manual reviews that previously took a planner 20 hours to complete were reduced to just 5 minutes of AI processing and human verification.”
Quoted word for word from the source
increasedaccuracy
“The AI identified "catch-all" requirements in the municipal code that are often overlooked during manual human reviews.”
Quoted word for word from the source
“The benefit is that GIS and Planning staff get bogged down with low-effort work. This LLM-powered map frees up our resources so we can focus on the important work like the City's Strategic Plan.”
Difficulties and limits
- Each question required the planning staff to manually open GIS maps, cross-reference PDF zoning codes, and verify Future Land Use (FLU) maps.
Sources
- conflationlabs.com — vendor self-report
Similar deployments
GE Aerospace
Independently reportedManufacturing · Process automation · Classical ML · Scaled
Apollo Tyres
under 10 minutes — Time for root cause analysis
Independently reportedManufacturing · Process automation · AI agents · In production
Broadcom · Moveworks
88% — autonomous IT resolution rate
Independently reportedTechnology & software · Process automation · NLP · Scaled
Amazon · Amazon
10% more — shopper spend
Independently reportedRetail & e-commerce · Process automation · Computer vision · Scaled · 2024
icare · SAS
increased by 15% — accuracy
Independently reportedInsurance · Process automation · Classical ML · Scaled · 2019