Action Orchestrator: Don’t let iPaas slow down your AI agents

As businesses embrace AI agents a critical challenge emerges: connecting these intelligent agents with the complex web of APIs that drive modern business systems. While AI agents excel at understanding and responding to human language, they struggle to interact effectively with traditional integration platforms like iPaaS and middleware, which were designed for precise, deterministic API interactions, rather than the nuanced world of human language.

This disconnect can lead to a frustrating experience for both users and developers. Users encounter cryptic error messages and stalled processes when AI agents fail to interpret responses from backend systems.

Developers can end up needing to write excessive amounts of code to bridge this gap, leading to increased tech debt and slower development cycles. Moveworks' Agentic Automation Engine helps to address these challenges head-on with its Action Orchestrator.

iPaaS and Middleware are a black box to AI agents

AI agents need to be able to ultimately take action in business systems. Modern SaaS tools use APIs to allow other systems to take action. APIs let you interact with business systems, but they are not an integration themselves.

Developers who have integrated with APIs before understand that integrations need a little more than just an API – code also needs to be written somewhere.

The Integration Platform-as-a-Service (or iPaaS) industry was born to solve this problem. iPaaS tools today (Such as Zapier, Workato, Microsoft Power Automate, ServiceNow Flow Designer, Salesforce Flow Builder, Mulesoft, etc.) allow developers to write code that connects APIs across business systems. 

Unfortunately, some of these iPaaS tools and middleware can be a black box to AI agents. Meaning that AI agents don’t understand what is happening inside these automations, they simply know what data they require and what data they return.

So, if your automation runs into an error, all the AI agent could see would be an unclear error message like this:

What is an AI agent supposed to do with that information?

There’s little helpful information that allows it to recover the conversation with the user. The user is probably left confused, wondering if the action actually failed, or if the AI agent is just not able to deliver.

Introducing Moveworks Action Orchestrator

The Moveworks Action Orchestrator creates a deeply connected bridge between the AI agent and integration code. Instead of integration code being a black box for AI agents, the integration code is clear and interpretable. 

In the example above, you notice two key benefits to an integrated Action Orchestrator.

1. Our Action Orchestrator keeps track of all the actions that are planned, in progress, and complete. As a result, it can offer progress updates to the user more efficiently than traditional iPaaS and middleware. 

2. Further, it can interpret the actions and responses themselves. This means developers no longer need to write code for dialogs, edge cases, or exception handling – the Action Orchestrator handles it for them.

Our Action Orchestrator helps significantly reduce the amount of code needed to build great end user experiences. Developers get to stay focused on building working integrations instead of formatting minutiae – ultimately accelerating your ability to build a Copilot that touches every business system.

Furthermore, our Action Orchestrator is built to handle conversation tasks. We’ve pre-loaded it with native actions so developers can build whatever kind of workflow they need. Everything from notifications to approvals, to calling the LLM of your choice – the Action Orchestrator has these abilities and many more.

Unlock next generation automations

Let’s put the Action Orchestrator to work in one more use case. For many of our customers, IT service management is a critical focus of their Moveworks investment. They want to find ways to make their service desks more efficient. Some of that starts from providing IT agents with access to AI agents that make their lives easier.

Whenever an outage occurs, IT agents are typically overwhelmed with hundreds, if not thousands, of IT tickets all about the same outage. To keep themselves organized, they typically create a “major incident” to track the outage and link all these tickets to the outage ticket – but this process can still take hours for your team to read every single ticket, determine if it’s related to the outage, and link it to the major incident.

With our Agentic Automation Engine, IT professionals could hardly be more efficient. Here's how:

1. Slot Resolvers collects requirements to create a major incident (title = “Cisco AnyConnect VPN Outage”, owner=Kyle)

2. Slot Resolvers determine the filtering criteria for child incidents (status = ‘new’, created_at > 2024-10-25T08:00:00)

3. The Action Orchestrator uses a “for loop” control flow to paginate over the ServiceNow APIs and retrieve all tickets that meet the criteria

4. The Action Orchestrator uses “parallel processing” control flow to process each ticket that meets the criteria. This completes the task much faster.

5. The Action Orchestrator uses LLM actions to classify each ticket as related to the major incident based on the ticket description.

6. The Action Orchestrator uses notification actions to inform the employees who filed the tickets that their ticket is related to the outage.

7. The Action Orchestrator keeps the incident manager apprised throughout the process with progress updates.

Developers who want to build this themselves outside of Moveworks Creator Studio would have had to write an inordinate amount of code and get access to heavy-duty infrastructure, entailing the following:

1. Developers would need an API key for using LLMs to classify each ticket.

2. Developers would need to implement rate limiting for those LLM calls.

3. Developers would need to write multithreading logic.

4. Developers would need to manage notifications and rate limits for every ticket that’s been linked.

Why do any of that? Just build on the Action Orchestrator instead.

Don’t let iPaas slow down your AI agents 

As businesses continue to adopt and integrate a multitude of software applications, the need for AI agents capable of navigating this complex landscape becomes increasingly critical. The Action Orchestrator is essential for ensuring these AI agents can more effectively interact with the diverse systems that comprise this landscape. By providing a reliable mechanism for connecting AI agents with integration code, the Action Orchestrator paves the way for the development of truly versatile and trustworthy AI agents.

With the Action Orchestrator as a core component of the Agentic Automation Engine, organizations can build AI agents that more seamlessly connect with their entire business ecosystem. These AI agents can intelligently interpret responses from various systems, manage actions in progress, and dynamically adapt to real-time feedback, all while maintaining a transparent and user-friendly experience.

That’s why we’re proud to have built Action Orchestrator to empower businesses to use AI agents to streamline operations, reduce development overhead, and help to unlock the full potential of AI across their organizations.

Want to dive deeper into the Agentic Automation Engine? Why not read our white paper to learn more.