Intelligent pieces of software, known as enterprise AI agents, that can perform specific tasks are emerging as a natural outcome of generative artificial intelligence. Salesforce Inc.’s MuleSoft recently announced a composability solution to help organizations build discrete AI services to facilitate this technology.

MuleSoft and Salesforce are tackling the challenging computer science problem of converting an open-ended planning and reasoning problem into a much simpler search problem. Customers can create enterprise AI agents, equip them with a task and tools fueled by a library of workflows, and the agents will find their way toward achieving an objective.

“We have this notion of autonomous agents and how they are going to help simplify work for various creators and various business users in the enterprise,” said Vijay Pandiarajan, vice president of product management at Salesforce. “What we’re going to see is that more of the hands-on, day-to-day coding is going to be delegated over to agents themselves.”

Pandiarajan spoke with George Gilbert, senior analyst at theCUBE Research, in the latest episode of The Road to Intelligent Data Apps, theCUBE’s continuing conversation about the sixth data platform. This emerging framework’s leading vendors include Databricks Inc., Snowflake Inc., Amazon Web Services Inc., Microsoft Azure and Google LLC. The discussion focused on the latest releases and how enterprise AI agents will have a significant impact on operational performance.

Creating an event-driven architecture using enterprise AI agents

MuleSoft’s announcements in June provide a composability solution with Anypoint Platform to design and deploy application programming interfaces, an API management offering, and automation driven by MuleSoft RPA and MuleSoft Intelligent Document Processing. The company also announced support for AsynchAPI to enable the adoption of event-driven architectures.

“It’s a composable way of bringing these agents together,” Pandiarajan said. “AsyncAPI support is extremely important as events themselves transpire. How are we proactively bringing that information to bear onto all the work that we’re doing? It’s an event-driven architecture that we have to bring in.”

The MuleSoft solutions provide an intriguing glimpse into how the technology for generative AI is evolving from one autonomous agent to multiple AI agents working in concert. Pandiarajan described how this multiplicity will become especially important in supply chain management.

“There’s both a planning aspect and an execution aspect in the supply chain world, and sometimes these two actually collide, and you have to make changes,” Pandiarajan said. “Your chief of staff agent is … alerting to you say, ‘In about a month or so, we’re expecting unreasonable temperatures in these certain places, and you may want to take action to make changes to the allocation of goods.’ There’s the inventory agent that came in, there’s the store agent that came in, there’s a fulfillment agent that came in, and even a supplier agent. The point is the supply chain manager has a lot of help in assessing end goals, and it’s really because of this interconnection of these independent but verified agents that are being pulled together by this chief of staff agent.”

Leveraging Salesforce APIs to take action

Salesforce and MuleSoft can accomplish this through Invocable Actions, an ability to invoke decision matrices using Salesforce APIs and use the integration of key data flows.

“We have these little bits of magic called Invocable Actions,” Pandiarajan explained. “That’s one of the ways we can get to all these different systems, interpolate what is going on and then surface them back up inside Salesforce so you can have access to all of this information. It’s a set of tasks that you’re doing with the same entity that’s likely going to get wrapped up into a connector so that you have all the related functions together. That gets pulled together into our Salesforce ecosystem.”

The latest announcements from Salesforce and MuleSoft provide another chapter in the area of process mining techniques used to analyze event data to better understand operational performance. Salesforce has invested in process mining startup Apromore Pty Ltd. to take advantage of its AI-driven process improvement technology.

“Are we providing the right quality of service, and are we hitting the [service level agreements] that we want? If not, why?” Pandiarajan said. “Process mining lets us get into it and understand what is standing in the way of that and what should be changed in the overall orchestration. Apromore is able to come back through, help us find the places where we’ve got the process blockers, understand what those blockers are [and] what’s causing it.”

The ability of AI agents to identify process blockers and then take action represents a transformation in how businesses will manage their operations, according to Pandiarajan. The way the company is creating these agents and how they will be used is going to change many professions very quickly, he added.

“The human can do the last-mile part,” Pandiarajan said. “I think that’s where the productivity is going to come from. Having these tools directly available where people work is going to make a huge difference.”

Here is the complete conversation, part of The Road to Intelligent Data Apps series:

Image: Pixabay