Artificial intelligence is rapidly reshaping software development, and its influence is now being felt in quality assurance and testing within banks and financial services.
The latest wave of AI-driven coding agents, tools such as GitHub Copilot, Amazon CodeWhisperer, Cursor and Devin, is transforming how software is written, tested and maintained.
“Coding agents are intelligent systems powered by large language models that write, debug and optimize code. They generate APIs, refactor legacy systems, write tests and even build apps with minimal input,” according to Vikas Mendhe, a solution architect and digital transformation expert specialising in API-driven solutions in financial technology.
For banks, where QA is a critical safeguard against compliance failures and operational risk, coding agents are being deployed cautiously but increasingly effectively.
ANZ Bank’s 2024 pilot of GitHub Copilot, for example, showed engineers completing tasks 42% faster with improved code quality.
Across the sector, these tools promise to free QA specialists from repetitive tasks and accelerate secure code validation.
“They are reshaping how code is written, tested and maintained, marking a new era in software development,” Mendhe noted.
Popular tools show strengths aligned with enterprise needs, such as GitHub Copilot excelling in Python, JavaScript and TypeScript, widely used in data analytics and risk modeling.
Amazon CodeWhisperer is strong in Java and AWS-native environments, aligning with cloud-first banking strategies, while Tabnine supports languages including Java and C++ with offline capability, a feature attractive for firms operating under strict data residency rules, such as many banks and insurance firms.
Testing, security and supervision
Despite advances, oversight remains essential. “Coding agents still generate insecure code and lack deep understanding of intent. Recent advancements have introduced better safeguards, validation mechanisms and inline linting. However, ongoing oversight remains essential,” Mendhe warned.
For QA teams, this means doubling down on automated test coverage, linting and human review before deployment. Regulatory frameworks such as DORA in Europe underscore the stakes: insecure or untested AI-generated code could expose institutions to severe compliance penalties.
Financial institutions are advised to begin with structured pilots rather than wholesale adoption. Controlled experiments with measurable outcomes, combined with formal risk assessments and strict change-management processes, are emerging as best practices.
“Before adopting AI coding agents, focus on clear, high-value use cases and choose tools suited to those needs instead of automating everything. Keep humans in the loop by ensuring AI-generated code undergoes rigorous testing, security scans and peer reviews,” explained Mendhe.
For financial QA teams, the challenge lies in balancing productivity gains with the need for accuracy, compliance, and security. Coding agents are not replacements for skilled engineers and testers, but powerful accelerators when properly governed.
“When used responsibly, coding agents can help teams work more efficiently, come up with new ideas and change the way software is built and tested in the AI era,” Mendhe concluded.
QA FINANCIAL PODCASTS
Listen to Sudeepta Guchhait on Nasdaq’s new Mimic AI testing platform
QA Financial sits down with Sudeepta Guchhait, Senior Director of Product Framework & Quality Engineering at Nasdaq
——–
Listen to Wesley Scheffel and Robin Rain on Schroders’ DevOps strategy
We catch up with Wesley Scheffel, Head of Cloud Platform and Product Engineering at Schroders, and Robin Rain, Head of Cloud Platform Architecture
——–
Listen to Citi’s Jason Morris on Lightspeed and the future of continuous delivery
Jason Morris, Head of Developer Pipelines for Securities Markets and Banking at Citi, talks about Lightspeed
THIS NOVEMBER
Why not become a QA Financial subscriber?
It’s entirely FREE
* Receive our weekly newsletter every Wednesday * Get priority invitations to our Forum events *
REGULATION & COMPLIANCE
Looking for more news on regulations and compliance requirements driving developments in software quality engineering at financial firms? Visit our dedicated Regulation & Compliance page here.
READ MORE
- Leapwork engineering head: Why test automation so often fails to deliver
- World Economic Forum warns financial sector must strengthen AI risk controls
- How Banca Progetto is hard-wiring quality into Italy’s digital banking space
- How Wealthsimple builds quality into the product, not around it
- Digital revamp puts spotlight on internal controls at China Construction Bank
WATCH NOW
