For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Logo
DeveloperAcademyCommunityStatus
ReferenceGuides
ReferenceGuides
  • Agent Studio
    • Overview
    • Quickstart Guides
    • Core Concepts
      • Assistants, Agents, & Plugins
      • Agentic Automation Engine
      • Conversational Plugins
      • Ambient Agents
      • Data Types
      • Citations
      • Data Bank
      • Structured Data Analysis
    • Conversation Process
    • Actions
    • Connectors
    • System Triggers
    • Agent Architect
    • Cookbooks
    • Development and Testing
    • AI Agent Marketplace
    • Developer Tools
  • Agentic AI
    • LLM Fundamentals
    • The Agentic Reasoning Engine
    • Memory Constructs
    • Conversational Context
    • Guardrails
    • Grounding and Hallucinations
    • Continuous Learning
    • LLMs & SLMs
    • Steerability Tools
    • Multilingual Support
  • Core Platform
    • User Identity
    • Moveworks Agent (On-Prem)
    • Approvals Engine
    • Entity Catalog
    • Moveworks Data Objects
    • Security Information and Event Management (SIEM) Logs Overview
DeveloperAcademyCommunityStatus
On this page
  • How a Plugin Executes
  • Architecture Map
  • Key relationships
  • Core Concepts Reference
  • Recommended Reading Order
Agent Studio

Core Concepts

||View as Markdown|
Was this page helpful?
Edit this page
Previous

Assistants, Agents, & Plugins

Next
Built with

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

Assistants, Agents, & Plugins

The hierarchy: Assistants contain Agents, Agents use Plugins. Start here to understand what you’re building.

Conversational Plugins

Plugins triggered by user messages. Covers natural language triggers, slot design, conversation processes, and reasoning instructions.

Ambient Agents

Plugins triggered by system events (webhooks) or schedules. Run without user interaction.

Agentic Automation Engine

The runtime that powers your plugins: Plugin Retrieval, Planner, Policies, Slot Resolvers, and the Data Bank.

Data Bank

The centralized data store for plugin execution. Access slot values, action outputs, and system metadata via data.* paths.

Data Types

The type system for slots and action inputs: strings, numbers, booleans, lists, objects, dates, and structured types.

Citations

How to provide source attribution in plugin responses so users can verify the information.

Structured Data Analysis

How the reasoning engine interprets and presents tabular data returned by actions.


Recommended Reading Order

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