> This page is for Tools.

> 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 AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.moveworks.com/_mcp/server.

# Core Concepts

Tool 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.

## Architecture Map

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

```mermaid
flowchart TB
    subgraph Triggers["Trigger Layer"]
        UT["User Utterance"]
        WT["Webhook Trigger"]
        ST["Scheduled Trigger"]
    end

    subgraph Plugins["Plugin Types"]
        CP["Conversational Plugin"]
        AA["Ambient Agent"]
    end

    subgraph RE["Reasoning Engine"]
        PR["Plugin Retrieval"]
        PL["Planner"]
        PO["Policies"]
        SL["Slots"]
        SR["Slot Resolvers"]
        DB["Data Bank"]
    end

    subgraph Actions["Actions"]
        HA["HTTP Action"]
        CA["Compound Action"]
        SA["Script Action"]
        LA["LLM Action"]
        BA["Built-in Action"]
    end

    CON["Connectors"]
    EXT["External Systems"]

    UT --> CP
    WT --> AA
    ST --> AA

    CP --> RE
    AA --> RE

    PO --> SL
    SL -->|"resolved by"| SR

    RE --> PL
    PL --> Actions

    Actions --> CON
    CON --> EXT
    EXT -->|"stored in"| DB
    SL -->|"stored in"| DB

    PR -.->|"selects plugin"| CP
    PO -.->|"decides next step"| PL

    style RE fill:#eef2ff,stroke:#6366f1
    style Triggers fill:#f0fdf4,stroke:#10b981
    style Plugins fill:#fff7ed,stroke:#f59e0b
    style Actions fill:#fef2f2,stroke:#ef4444
    style DB fill:#faf5ff,stroke:#a855f7
```

### 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](/tool-studio/core-concepts/assistants-agents-plugins)

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

#### [Conversational Plugins](/tool-studio/core-concepts/conversational-plugins)

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

#### [Ambient Agents](/ai-assistant/ambient-agents)

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

#### [Why Plugins](/tool-studio/why-plugins)

Where MCP tools and skill files break on real enterprise work, and how Plugins enforce your business rules with Slot Resolvers, Policy Validators, and the Action Orchestrator.

#### [Data Bank](/tool-studio/core-concepts/data-bank)

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

#### [Data Types](/tool-studio/core-concepts/data-types)

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

#### [Citations](/tool-studio/plugins/citations)

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

#### [Structured Data Analysis](/tool-studio/core-concepts/structured-data-analysis)

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

---

## Recommended Reading Order

> **Tip**
>
> **If you're new to Tool Studio**, read in this order:
>
> 1. [LLM Fundamentals](/harness/llm-fundamentals) — how LLMs predict tokens, context windows, and attention (explains **why** every design pattern exists)
> 2. [Assistants, Agents, & Plugins](/tool-studio/core-concepts/assistants-agents-plugins) — understand the hierarchy
> 3. [Conversational Plugins](/tool-studio/core-concepts/conversational-plugins) — the most common plugin type
> 4. [Designing Conversation Processes](/tool-studio/core-concepts/conversational-plugins/designing-conversation-processes) — the best practices guide (required reading)
> 5. [Data Bank](/tool-studio/core-concepts/data-bank) — how data flows between steps
> 6. [Actions overview](/tool-studio/actions) — what operations are available
> 7. [Why Plugins](/tool-studio/why-plugins) — why business rules belong in a Plugin, not a skill file