Core Concepts

View as Markdown

Agent Studio is Moveworks’ platform for building AI-powered plugins that automate business processes. You define what your plugin does — the reasoning engine handles how to execute it at runtime.

This page maps the core building blocks and how they connect. Read it first, then dive into the sections that match what you’re building.

How a Plugin Executes

Every plugin follows the same lifecycle: a trigger fires, the reasoning engine selects a plugin, slots are collected, actions execute, and a response is returned.

Plugin Data Flow
User Message
Reasoning Engine
Plugin
PTO Balance
Response
Connector
Action
Slots
"Check my PTO balance"
The complete lifecycle of a plugin execution.
Step 0 of 7

Architecture Map

The diagram below shows how every core concept in Agent Studio relates. The reasoning engine sits at the center — your plugin configuration tells it what to do, and it orchestrates everything else.

Key relationships

  • Triggers determine how a plugin activates. User utterances invoke Conversational Plugins. Webhooks and schedules invoke Ambient Agents.
  • The Reasoning Engine is the runtime that powers every plugin. It retrieves and ranks plugins, collects slots, resolves values, plans action execution, and stores results in the Data Bank. Policies are the decision layer — they determine each next step (collect a slot, call an action, respond to the user).
  • Slots are the inputs your plugin needs. Slot Resolvers convert natural language values (“White Fox conference room”) into system IDs (R-3824).
  • Actions are the operations your plugin performs. Five types exist, each for a different use case.
  • The Data Bank stores all data generated during execution — slot values, action outputs, and system metadata — so downstream steps can reference upstream results.
  • Connectors authenticate and route requests to external systems (ServiceNow, Jira, Salesforce, your own APIs).

Core Concepts Reference


If you’re new to Agent Studio, read in this order:

  1. LLM Fundamentals — how LLMs predict tokens, context windows, and attention (explains why every design pattern exists)
  2. Assistants, Agents, & Plugins — understand the hierarchy
  3. Conversational Plugins — the most common plugin type
  4. Designing Conversation Processes — the best practices guide (required reading)
  5. Data Bank — how data flows between steps
  6. Actions overview — what operations are available
  7. Agentic Automation Engine — how the runtime works under the hood