> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.moveworks.com/llms.txt.
> For full documentation content, see https://docs.moveworks.com/llms-full.txt.
# Agent Studio Overview
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
Follow [Quickstart #1: Basic Task Agent](/agent-studio/quickstart-guide/quickstart-basic-task-agent) to build a working plugin in minutes.
Read [Assistants, Agents, & Plugins](/agent-studio/core-concepts/assistants-agents-plugins) to understand how the pieces fit together.
Read [The Golden Rule](/agent-studio/guides/best-practices/the-golden-rule) before building anything complex — it's the most important design pattern.
Use the Building Blocks Reference and Guides sections on this page to find specific docs as you build.
Review [Testing & Error Handling](/agent-studio/guides/getting-started/testing-and-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.
Index your content for semantic search experiences.
Execute real-time actions to create, modify, read, & remove data from business systems.
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 single most important pattern for building reliable plugins
When to use compound actions vs conversation processes, slot types, and more
Anti-patterns and best practices for slot design
Anti-patterns and best practices for conversation processes
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](/agent-studio/actions/http-actions) |
| Orchestrate multiple actions | [Compound Action](/agent-studio/actions/compound-actions) |
| Call an LLM inline | [generate\_text\_action / generate\_structured\_value\_action](/agent-studio/actions/llm-actions) |
| Send a message to a user | [`notify`](/agent-studio/actions/compound-actions/notify) expression |
| Branch on a condition | [`switch`](/agent-studio/actions/compound-actions/switch) expression |
| Handle an API failure | [`try_catch` / `raise`](/agent-studio/actions/compound-actions/try-catch-and-raise-error) |
| Loop over a list | [`for`](/agent-studio/actions/compound-actions/for) expression |
| Run actions concurrently | [`parallel`](/agent-studio/actions/compound-actions/parallel) expression |
| End a compound action and return data | [`return`](/agent-studio/actions/compound-actions/return) expression |
| Look up a user by email | [`get_user_by_email`](/agent-studio/actions/built-in-actions#get_user_by_email) |
| Look up many users at once | [`batch_get_users_by_email`](/agent-studio/actions/built-in-actions#batch_get_users_by_email) |
| Request human approval | [`create_generic_approval_request`](/agent-studio/actions/built-in-actions#create_generic_approval_request) |
| Send batch chat notifications | [`batch_send_plaintext_chat_notification`](/agent-studio/actions/built-in-actions#batch_send_plaintext_chat_notification) |
| Collect user input | [Slots](/agent-studio/conversation-process/slots) |
| Validate a slot value | [Validation policy](/agent-studio/guides/best-practices/slot-best-practices#missing-validation-policy) with DSL |
| Branch a conversation on an action result | [Decision Policy](/agent-studio/conversation-process/control-flow#pattern-action--decision-policy--branch) |
| Display a knowledge article or form | [Content Activity](/agent-studio/conversation-process/activities/content-activities) |
| Handle large API responses (>7K tokens) | [Response Sizes / SDA](/agent-studio/conversation-process/activities/response-sizes) |
## Actions
REST API calls to external systems
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
Error handling
Send messages with action buttons
## Conversation Process
Collect input values from users
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
Conversational plugin activation
Webhooks and scheduled triggers
# Samples
You can view hundreds of AI agents on our [AI Agent Marketplace](https://aka.mw/marketplace) and import example templates to better understand how they are built.
# Ready to get started?
Dive into our [Quickstart Guides](/agent-studio/quickstart-guide) to start building your first plugins