The power of AI-enabled, adaptive RPA: X-ray Vision

RPA development can be a burden. Citizen developers can ease this burden by creating simpler automations. However, working with processes dependent upon multiple legacy applications can get difficult – leaving citizen developers struggling to automate applications that are too complex or constantly changing.

Technical developers, who are also trying to build robust automations at scale, are buried with manual application control identification on the front-end.

And when you just want to change the application UI code or layout, the bot breaks. The manual configuration has to be completely re-done. It’s a mess on top of a mess.

You don’t have to choose between power and efficiency when it comes to building bots. X-ray Vision, part of Pega’s RPA solution, gives you both.

PegaWorld iNspire 2020: New innovations in Pega RPA

Video duration: 12:05

X-ray Vision is a proprietary AI-driven method that automates the identification of application controls. Automations can be built faster and with more resilience, as well as require less technical expertise.

Pega’s patented RPA technology automates at the application object-level for faster and more accurate automations. X-ray Vision is built on that technology – changing the automation development game further by:

• Empowering citizen developers to build more, by drastically reducing the technical knowledge requirement needed to build automations


• Reducing time to automation, by eliminating manual identification and moving automations to production – in order to solve business problems faster


• Eliminating broken bot syndrome, by seeing when an automated application’s controls change and adapt to those changes – so bots don’t break as frequently


• Getting smarter through training, by continuously learning about the dynamic characteristics of the applications being automated – increasing the response time to application changes and automation resiliency

X-ray Vision has an unprecedented combination of power and efficiency. It eliminates the burden of control identification and employs AI and machine learning for self-learning, resilient automations that can adapt to changes at the speed of business.