Agent Studio Overview

Connect AI assistants to your business systems & content

Build your first plugin in minutes

Detailed information about how Moveworks AI agents work in our platform

Collection of best practices & recommendations for common types of use cases

New to Agent Studio? Start Here

Build your first plugin

Follow Quickstart #1: Basic Task Agent to build a working plugin in minutes.

Understand the architecture

Read Assistants, Agents, & Plugins to understand how the pieces fit together.

Learn the Golden Rule

Read The Golden Rule before building anything complex — it’s the most important design pattern.

Build with the reference below

Use the Building Blocks Reference and Guides sections on this page to find specific docs as you build.

Test before you ship

Review Testing & Error Handling before publishing your plugin.

Agentic Frameworks

Agent Studio lets you connect AI assistants to your business systems & content. There are three Agentic Frameworks that you can build on.

Content Gateway

Index your content for semantic search experiences.

Conversational AI Agents

Execute real-time actions to create, modify, read, & remove data from business systems.

Ambient AI Agents

Set up Ambient AI agents that run in the background

These agentic frameworks are interoperable on the Moveworks platform, so you can build experiences that span multiple patterns.

Guides & Best Practices

The Golden Rule

The single most important pattern for building reliable plugins

Decision Frameworks

When to use compound actions vs conversation processes, slot types, and more

Slot Best Practices

Anti-patterns and best practices for slot design

Conversation Process Best Practices

Anti-patterns and best practices for conversation processes

LLM Action Best Practices

When NOT to use LLM actions and the decision matrix

Building Blocks Reference

Quick links to every Agent Studio building block.

Common tasks

Starting from an outcome and not sure which primitive to use? Start here.

I want to…	Use
Call an API	HTTP Action
Orchestrate multiple actions	Compound Action
Call an LLM inline	generate_text_action / generate_structured_value_action
Send a message to a user	`notify` expression
Branch on a condition	`switch` expression
Handle an API failure	`try_catch` / `raise`
Loop over a list	`for` expression
Run actions concurrently	`parallel` expression
End a compound action and return data	`return` expression
Look up a user by email	`get_user_by_email`
Look up many users at once	`batch_get_users_by_email`
Request human approval	`create_generic_approval_request`
Send batch chat notifications	`batch_send_plaintext_chat_notification`
Collect user input	Slots
Validate a slot value	Validation policy with DSL
Branch a conversation on an action result	Decision Policy
Display a knowledge article or form	Content Activity
Handle large API responses (>7K tokens)	Response Sizes / SDA

Actions

REST API calls to external systems

Compound Actions

Orchestrate multi-step workflows

generate_text and generate_structured_value

Compound Action Expressions

Invoke an HTTP, script, or compound action

Loop over arrays sequentially

Conditional branching

Run expressions concurrently

End execution and return data

try / catch / raise

Error handling

Send messages with action buttons

Conversation Process

Collect input values from users

Resolver Strategies

Convert natural language to data types

Action and content blocks

Decision policies, exit, and continue

Data & Configuration

Reference patterns: data., meta_info., response, value

Validation rules, conditions, string functions

MAP(), MERGE(), FILTER(), RENDER(), LOOKUP()

Built-in and custom data types

Triggers

Natural Language Triggers

Conversational plugin activation

System Triggers

Webhooks and scheduled triggers

Samples

You can view hundreds of AI agents on our AI Agent Marketplace and import example templates to better understand how they are built.

Ready to get started?

Dive into our Quickstart Guides to start building your first plugins