Across global banking and financial services, agentic AI has emerged as one of the most promising yet complex frontiers in software testing and delivery.
The idea of autonomous AI “workers”, agents that can execute tasks, learn from data, and optimise software pipelines without constant human oversight, has captured the imagination of QA teams and CTOs alike.
But as the technology moves from the lab to large-scale enterprise use, its success will depend on one critical factor: openness.
Industry leaders warn that agentic AI cannot thrive in the closed, proprietary environments that have long defined enterprise software.
Instead, interoperability, observability and transparency will determine whether AI-driven systems can meet the demands of regulated sectors like finance.
That’s the view of Nic Benders, chief technical strategist at San Francisco-based software development and testing firm New Relic, who says the evolution of AI agents will be shaped by how well they integrate with the tools and data ecosystems that already drive modern engineering.
“The promise of AI is that we can accelerate and automate large swaths of undifferentiated work by augmenting human effort or creating agentic AI ‘workers’ who can complete tasks on their own,” Benders said.
“To realie that vision, there is a lot of work ahead to take agents from the lab to production quality and safety.”
For QA and software engineering teams in banking, the implications are clear: closed, siloed systems slow innovation.
“Agentic AI thrives on interoperability, but tooling vendors often want to lock you into their own system,” Benders explained.
“While closed ecosystems may offer short-term convenience, they’re fundamentally incompatible with how modern engineering teams, and now AI agents, actually work.”
He warned that vendor lock-in “limits interoperability and cuts off real-time visibility that agents need to perform accurately,” leading to “fragmentation, slower innovation, and reduced agility.”
Trust and adoption
In contrast, open ecosystems “foster transparency and interoperability across the tools engineers already rely on, like GitHub and ServiceNow,” said Benders.
Developers are more likely to embrace AI “when it fits seamlessly into their existing workflows, rather than forcing them to toggle between disconnected systems.”
Beyond convenience, he added, openness “makes agentic AI more powerful: it allows agents to gather context across the entire tech stack, collaborate with other systems, and act with greater accuracy.”
With agent-based AI projected to automate tasks worth over $6 trillion by 2030, he argued, “vendors would be wise to prioritise open ecosystems since they make it much easier for agentic AI to collect data and work across the tech stack.”
“Open ecosystems for agentic AI are essential in an interconnected, composable future.”
– Nic Benders
Benders pointed to new industry standards such as the Model Connectivity Protocol (MCP), developed by Anthropic in 2024, as key enablers of this shift.
“Compared to the complex, and full-featured, RPC protocols of the past, MCP is extremely simple, but it has still driven a huge change because it standardized how different pieces can work together and did so in a way anyone could implement,” he shared.
By reducing vendor lock-in and enabling composable AI architectures, MCP “accelerates the development of a flexible, open AI landscape” and “simplifies how large language models connect to external data, tools, and applications.”
That, Benders argued, “democratises access to AI and lays the groundwork for agent-to-agent collaboration, allowing them to solve complex problems together and accelerate human productivity.”
Observability
Just as interoperability is essential for open ecosystems, Benders said, observability is vital to trust in autonomous agents.
“When agents act autonomously and learn from their environments, teams need a clear line of sight into how those decisions are made,” he noted.
“Without visibility into these actions, it’s difficult to notice when something goes wrong or when an agent is behaving in ways that aren’t aligned with an organization’s goals.”
He argued that “observability builds trust with developers and external users by showing the logic behind an agent’s decisions and providing a clear activity trail.”
When integrated with existing engineering tools, observability data can be fed directly into agentic applications such as autonomous coding systems.
Benders highlighted OpenTelemetry, an open-source project managed by the US-based Cloud Native Computing Foundation, for ensuring “consistent data collection across applications and languages”, a foundation without which, he said, “AI agents would fly blind.”
For banks and financial services firms deploying AI across critical software pipelines, the message is simple: openness equals resilience.
“Open ecosystems for agentic AI are essential in an interconnected, composable future,” Benders concluded.
“Embracing them fuels innovation, strengthens resilience, and ensures seamless data flow across tools and tech stacks,” he summarised.
“Ultimately, open ecosystems accelerate progress and foster a more inclusive, collaborative digital future.”
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
WATCH NOW
QA FINANCIAL PODCASTS
