Shriram Finance
less than 3–4 hours — Onboarding Turn-Around-Time (TAT)
Independently reportedBanking & finance · Process automation · Classical ML · In production
Process automation
Meeting Tomorrow · Addepto
Vendor-reportedOtherUnited StatesPilotAI agents
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 addepto.com (vendor self-report). Checked against the source page on 2026-09-06. 1 of 1 figures below appear on that page word for word.
The problem
The process of converting vague client requests into detailed technical orders with hundreds of inventory line items was entirely manual, creating significant delays and limiting capacity. Critical operational knowledge existed only in the minds of senior employees, making the quoting process difficult to scale and vulnerable to knowledge loss.
What was deployed
- Vendor
- Addepto
- Products
- LangGraph, NetSuite
- Technique
- AI agents
- Build or buy
- Built in-house or to order
- Deployment
- Custom build
- Data used
- company's actual database, NetSuite ERP inventory IDs, multiple data sources (CSV files, PDFs, email correspondence)
- Timeline
- 2 months
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.
50-70% automaticallystandard equipment selection automationfrom 100% manual effort
“AI pilot handles 50-70% of standard equipment selection automatically”
Quoted word for word from the source
minutesdraft order generation timefrom hours
“Draft orders generated in minutes instead of hours, dramatically increasing throughput capacity”
Quoted word for word from the source
“Our approach was simple: automate the 70–80% of work that’s mechanical, and protect the 20–30% that requires judgment. That’s not a compromise, it’s good system design. Every attempt to push AI beyond its reliable boundaries is just another way of manufacturing technical debt.”
Difficulties and limits
- Preventing hallucinations required dedicated prompt engineering and statistical validation on each workflow node
Sources
- addepto.com — vendor self-report, 2025-12-22
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
icare · SAS
increased by 15% — accuracy
Independently reportedInsurance · Process automation · Classical ML · Scaled · 2019
Amazon · Amazon
10% more — shopper spend
Independently reportedRetail & e-commerce · Process automation · Computer vision · Scaled · 2024