AustraliaTechnology and telecom2026 – ongoingEllby
Generative AI for invoice-workflow setup and customer onboarding
Ellby reduced customer onboarding time by over 55% with generative AI
Problem
Ellby's team manually configured invoice templates for customers and maintained them as supplier formats changed. This work slowed customer onboarding.
Approach
Ellby embedded Anthropic's Claude models through Amazon Bedrock into EllbyExtract. Prompts replaced static templates for interpreting invoice formats. A rules-based engine checked model responses and flagged low-confidence invoices for human review.
Results
Takeaway
Removing supplier-specific templates reduced Ellby's setup work for new customers. Low-confidence invoices still required human review.
Categories
- Size
- Small business
- Industry
- Technology and telecom
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Generative AI
- Adoption
- Off-the-shelf tool or platform
- Evidence
- Vendor case study
Sources
Source summaries
AWS described how Ellby replaced invoice templates with generative AI to reduce configuration work. It reported customer onboarding time falling by over 55%. The page carries no date; the Internet Archive first saved it on January 13, 2026.
Full details are in the original sources.
