In the Pegasystems world, granting agents licenses to encourage end users, with the exception of research and summary can lead to trouble.
PEGA's Infinity Software Suite's latest agent AI capabilities provide the power to developers building agents for users. Developers can use RPA process prompts, documentation, automation goal descriptions, source code and video video to build workflow apps with BluePrint, PEGA's Agent AI Designer.
Other vendors like Salesforce, Microsoft, and ServiceNow rely heavily on agent prompts, but Pega draws the line to provide end users with prompts for tasks with clear ideas for desired output, such as research that can be checked.
This type of AI doesn't have to make decisions or handle complex workflows, says PredRag Jakovljevic, an analyst at the Technology Evaluation Center.
Agents driven primarily by prompts can use AI inference powers to take certain actions that the author does not intend or predict.
Predrag JakovljevicAnalysts, Technology Evaluation Center
“An agents driven primarily by prompts can use AI's inference power to get off the rails to take certain actions that the authors didn't intend or predict,” says Jakovljevic.
“Instead, Pega has its agents fixed in the workflow, which prescribes exactly how that agent will act when it runs,” he said. “This makes agents more predictable and reliable, which is especially important in the highly regulated industry where PEGA clients are active.”
Pegasystems CEO Alan Trefler said the agent workflow model is more reliable and predictable than the idea of the prompt.
“For some reason – the idea of reprogramming our business, making sure we do the right thing and doing something safe, just with the prompts, does little by little what most businesses do,” Treffler said.
MCP Standard Making Fared
Meanwhile, like its process automation competitors Microsoft, ServiceNow and Salesforce, Pegasystems integrates the Model Context Protocol (MCP) and Agent2Agent (A2A). In theory, these standards allow Genai agents from various vendors to interact with each other for cross-platform automation.
The company has also released the PEGA Agent Process Fabric, a library that assembles agents, apps, systems and data. MCP could be an enabler for that, Trefler said.
Alan Treffler
Both Trefler and Jakovljevic confirmed that agents' interoperability standards were announced earlier this spring. It takes time for users to determine their effectiveness.
“We'll need more time and proof of concept,” Jakovljevic said.
This technology is still early on, and many companies still only value Genai, not to mention adopting decision-making cousin Agent AI. Various companies define it agent It depends on how they separate inference functions from data processing, how they check the agents' own work, or what decisions they make.
“Almost everything that actually calls them, that LLM is included or as part of the way it works. agent Treffler said whether they have independent institutions or not.
Pegasystems' agent tool was released in connection with the Pegaworld User Conference held in Las Vegas this week.
Don Fluckinger is a senior news writer for Informa TechTarget. He covers customer experience, digital experience management and end-user computing. Do you have a tip? Please email him.
This website uses cookies to ensure that you get the best experience on our website. OkRead More
Privacy & Cookies Policy
Privacy Overview
This website uses cookies to improve your experience while you navigate through the website. Out of these cookies, the cookies that are categorized as necessary are stored on your browser as they are as essential for the working of basic functionalities of the website. We also use third-party cookies that help us analyze and understand how you use this website. These cookies will be stored in your browser only with your consent. You also have the option to opt-out of these cookies. But opting out of some of these cookies may have an effect on your browsing experience.
Necessary cookies are absolutely essential for the website to function properly. This category only includes cookies that ensures basic functionalities and security features of the website. These cookies do not store any personal information.
Alan Treffler
