Pegasystems adds enterprise AI tools to simplify analysis and forecasting

Pegasystems today announced it’s adding the ability to apply AI to business processes midstream to enable companies to determine whether an anticipated outcome will occur as expected.

Pegasystems is also adding a feature that lets companies analyze streaming event data on platforms such as the open source Apache Kafka software that is now being widely employed to enable organizations to transfer data in near real time.

Pega Process AI combines machine learning algorithms, event processing, business rules, natural language processing, and predictive analytics with low-code tools to analyze processes in real time, Pegasystems CTO Don Schuerman said. That approach makes it possible for organizations to make adjustments to processes to, for example, ensure a service level agreement (SLA) is met.

As organizations invest in myriad digital business transformation initiatives, many are discovering the batch-oriented legacy applications that typically process data overnight are not well-suited to driving interactions with customers in near real time, Schuerman noted. As a result, organizations are modernizing applications using platforms such as Kafka that enable them to stream data between applications and platforms. The way legacy applications handle data winds up constraining digital processes that need to process data in real time, he added.

“The shift from batch to reactive real-time processes has become table stakes,” he said.

Support for event streaming will play a critical role in enabling organizations to achieve that goal. Rather than having to wait to analyze the data at rest on a cloud platform, for example, it is possible to analyze streaming event data in transit, Schuerman noted.

Build or buy

As organizations look to infuse AI capabilities into business processes, the tensions that always exist between building a capability versus acquiring it will naturally surface. Pegasystems is making a case for an extensible platform based on AI models it creates and curates within the context of the Pega Platform. That capability makes it simpler for organizations to experiment with AI without having to hire data scientists to construct AI models using various open source toolkits. In contrast, it often takes a data science team several months to construct an AI model that may never make it into a production environment.

Schuerman said that rather than simply experimenting with AI capabilities, organizations should generally work backward from a desired business outcome. That approach reduces the chances an organization will wind up investing time and resources into an AI project that never makes it into a production environment.

AI investments

There’s no doubt organizations of all sizes are investing in various forms of AI as part of larger digital business transformation initiatives. The challenge these organizations face is that most data scientists are not especially well-versed in how any given business process should be optimized, which can lead to a lot of trial and error. Providers of platforms such as Pegasystems make it possible for the average business analyst who knows how to work with low-code tools to apply AI to processes they know intimately. It also makes it easier for them to alter those processes, should the AI models need to be updated or start drifting toward a sub-optimal outcome.

As AI becomes more democratized, the processes it can be applied to far exceed the number of data science experts that will be available anytime soon. Out of both necessity and fear, organizations are going to enable business users to at least experiment with AI before rivals apply those same capabilities. Hopefully, guardrails will ensure AI models are properly vetted so they do more good than harm.