Services provided
- Artificial Intelligence
- Data & Analytics
- Cloud Engineering
- Serverless Architecture
Platforms used
- AWS (Amazon Bedrock, AWS Lambda,
AWS Step Functions, Amazon API
Gateway, Amazon S3, Amazon
DynamoDB, AWS CDK)
Engagement length
- 12 weeks
Other stats
- Average assessment processing time of
26.8 seconds - 11 AWS Lambda functions orchestrated
through Step Functions
Background on the customer
Jacaranda Finance is one of Australia’s largest privately owned digital non-bank lenders,
purpose-built to provide responsible credit options for consumers who may not meet
mainstream bank lending criteria. Jacaranda aims to be a trusted alternative for everyday
Australians who need a personal loan or car loan after being declined by their bank.
Founded in 2014, Jacaranda has built a technology-led lending platform that combines
proprietary data, behavioural insights, verified bank transaction information and its internally
developed Edge Score to support more holistic credit assessment. Rather than relying solely
on traditional bureau credit scores, Jacaranda assesses suitable customers based on their
current financial behaviour and affordability capacity.
Jacaranda provides a fast, fully digital lending experience. The business also participates in
Comprehensive Credit Reporting, helping customers build a more complete credit profile
through positive repayment behaviour over time. Jacaranda demonstrates how a modern
non-bank lender can use AI, automation and cloud infrastructure responsibly. Its technology
is designed with governance, auditability, explainability and compliance controls embedded
into core lending workflows, helping Jacaranda scale while maintaining accountability in a
highly regulated consumer credit environment.
Challenge
Quality assurance reviews of all loan assessments are an important internal
quality-assurance step within Jacaranda Finance’s lending process, helping ensure
assessments are aligned to defined internal review criteria and operational compliance
requirements before formal approval.
Historically, this review process relied heavily on manual assessment by QA specialists.
While effective, the approach introduced operational bottlenecks as application volumes
increased and created challenges around consistency, turnaround times, and scalability.
Key challenges included:
- High operational effort required to review each assessment
- Manual review introduced natural variation in turnaround and formatting across
reviewers - Slower turnaround times during peak lending periods
- Difficulty scaling review capacity without increasing headcount
- Review rationale was captured manually and not consistently structured for
downstream analysis - Growing compliance and governance expectations within a regulated environment
Jacaranda Finance needed a solution capable of adding advanced automation to
assessment validation while preserving explainability, auditability, and confidence in review
outcomes.
Stack Highlights
The Approach
Codex partnered with Jacaranda Finance to design and deliver a serverless AWS-native Quality Assurance Engine that added advanced automation to the review of loan assessments using a combination of deterministic business rules and AI-assisted validation.
Our approach included:
1. Working with lending subject matter experts to translate assessment review requirements into structured validation rules.
2. Designing a scalable event-driven architecture using AWS Step Functions and Lambda.
3. Building deterministic validation checks for objective policy, data quality, and calculation requirements.
4. Leveraging Amazon Bedrock for AI-assisted analysis for defined review tasks, with
flagged outputs presented for human review under Jacaranda’s internal quality
assurance processes.
5. Implementing automated ingestion and normalisation of assessment artefacts.
6. Creating structured rule-level outputs with rationale, issue categorisation, and supporting references.
7. Establishing audit logging, monitoring, and operational observability capabilities.
8. Delivering infrastructure-as-code deployment pipelines using AWS CDK and GitLab CI/CD.
This approach enabled consistent, repeatable, and transparent assessment reviews while maintaining flexibility for future rule enhancements and evolving lending requirements.
Technical Outputs
“From the outset, our objective was to build a solution that could leverage AI responsibly within a highly governed lending environment. We needed an architecture that delivered scalability, observability and auditability while remaining flexible enough to evolve alongside our lending and compliance requirements.
Working with Codex, we designed and implemented a modern serverless platform that combines deterministic validation rules with AI-assisted review capabilities. The result is a highly scalable and resilient solution that provides structured, explainable outputs while maintaining strong operational controls and traceability throughout the review lifecycle.
What stands out is the extensibility of the platform. The architecture provides a strong foundation for future automation and AI-enabled capabilities, allowing us to continue enhancing operational efficiency while ensuring governance and transparency remain embedded in the design.”
— Brent Wardlaw, Chief Technology Officer, Jacaranda Finance
Codex delivered a production-ready QA platform that transformed how Jacaranda Finance validates loan assessments before providing a formal approval to a consumer.
Key outputs:
The platform provides a scalable and governed foundation for automated assessment review while reducing operational effort and increasing consistency.
QA Platform Highlights
Intelligent Loan Assessment Validation
Combines deterministic business rules with AI-assisted review capabilities to add advanced
automation to quality assurance across lending assessments.
Explainable and Auditable Outcomes
Every validation result includes rule-level rationale, references, issue tracking, and audit
records to support governance and compliance requirements.
Rapid Processing at Scale
Average assessment review times reduced to just 26.8 seconds while maintaining very high
validation accuracy.
Serverless by Design
Built using Lambda, Step Functions, API Gateway, DynamoDB, and S3, allowing the
platform to scale automatically while minimising operational overhead.
Designed for Regulated Financial Services
Governance, observability, auditability, and explainability were embedded from the outset to
support lending operations and regulatory expectations.
Business and Commercial Outcomes
“Quality assurance is a critical control within our lending operations, helping ensure assessments are reviewed consistently and in line with our internal standards and legal obligations. As application volumes continued to grow, we saw an opportunity to improve the efficiency and consistency of this process while maintaining strong oversight and accountability.
The platform delivered by Codex has enabled us to significantly reduce review times, increase the repeatability of outcomes, and provide greater transparency into the quality assurance process. By automating routine validation activities, our teams can focus more of their expertise on exceptions, judgment-based reviews, and continuous improvement initiatives.
Importantly, the solution was designed with governance, auditability and explainability at its core, giving us confidence that we can continue to scale our operations while maintaining the high standards expected in a regulated lending environment.”
— Timothy Kuusik, Chief Operating Officer, Jacaranda Finance
The QA platform delivered measurable operational improvements for Jacaranda Finance while creating a scalable foundation for continued growth and lending-volume expansion.
Key outcomes included:
- Reduced assessment review times to an average of 26.8 seconds.
- Increased consistency and repeatability of QA outcomes.
- Reduced reviewer effort through automated validation and issue identification.
- Improved governance through auditable rule-level outputs and decision traceability.
- Enabled lending teams to focus on exceptions and higher-value review activities.
- Established a scalable architecture capable of supporting increasing application volumes without proportional increases in operational effort.
- Created a foundation for future AI-enabled assessment and compliance capabilities.
The platform now enables Jacaranda Finance to process assessments faster, improve quality assurance consistency, and scale lending operations with greater confidence while maintaining strong governance and compliance controls.
Governance Statement
Jacaranda Finance remains responsible for all lending decisions and for meeting its responsible-lending and other regulatory obligations. The platform described here supports internal quality-assurance review of credit assessments. AI-assisted components are used within defined review tasks and are subject to human oversight, documented escalation pathways and ongoing monitoring. This case study describes one internal quality-assurance workflow. It is not intended to describe Jacaranda Finance’s full lending decision-making framework or all controls relevant to credit assessment.
Talk to Us
We would love the opportunity to connect and understand more about the problems you are trying to solve.
Adrian Campbell
Chief AI Officer
Martin Campbell
Managing Partner
Get in touch to coordinate a meeting with one of our technical experts.
Australia: +61 7 3132 3002.
