> 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. # Tools Overview Tools covers everything you build in Tool Studio to connect the Moveworks AI Assistant to your business systems and content: the connectors that hold a system's credentials, the plugins and MCP servers the assistant calls, the actions and system triggers that automate work in the background, and the logs you read once a tool is live. Moveworks offers four **tool frameworks**, each optimized for a different kind of connection: **Search** to find content, **Plugins** for reliable write actions that respect business rules, **MCP** for live reads and reversible actions in productivity apps, **Agent-to-Agent (A2A)** to delegate work to other agents. #### [Quickstart Guides](/tool-studio/quickstart-guide) Build your first plugin in minutes against the Purple Suite mock APIs. #### [Tool Frameworks](/tool-studio/tool-frameworks) Search, Plugins, MCP, and A2A, and when to use each. #### [Cookbooks](/tool-studio/cookbooks) Collection of best practices and recommendations for common types of use cases. # New to Tool Studio? Start Here #### Set up the Purple Suite Every quickstart uses the Purple Suite mock APIs. Complete [Purple Suite Setup](/tool-studio/quickstart-guide/purple-suite-setup) once to create your instance and connector. #### Build your first plugin Follow [Quickstart #1: Build Your First Plugin](/tool-studio/quickstart-guide/quickstart-build-your-first-plugin) to build a working plugin in minutes. #### Understand the architecture Read [Core Concepts](/tool-studio/core-concepts), starting with [Assistants, Agents, & Plugins](/tool-studio/core-concepts/assistants-agents-plugins), to understand how the pieces fit together, then [Choosing the Right Tool Framework](/tool-studio/cookbooks/choosing-the-right-tool-framework) before you pick a framework for a real use case. #### Learn the Golden Rule Read [The Golden Rule](/tool-studio/guides/best-practices/the-golden-rule) before building anything complex β€” it's the most important design pattern. #### Build with the reference below Use the By Job and Quick Reference sections on this page to find specific docs as you build. #### Test before you ship Review [Testing & Error Handling](/tool-studio/guides/getting-started/testing-and-error-handling) and the [Plugin Go-Live Checklist](/tool-studio/development-and-testing/plugin-critique-checklist) before publishing your plugin. # Pick a Framework Match the framework to the kind of work the assistant needs to do. An assistant can use several frameworks at once: when users chat, the assistant decides which tool to use to search for information, analyze data, or take action. #### [Search](/tool-studio/enterprise-search/search-connectors) Find content and files across your systems, such as knowledge base articles and attachments. #### [Plugins](/tool-studio/conversation-process) Reliable, agent-safe write actions against enterprise APIs, with step order and business rules enforced. #### [MCP Workspace](/tool-studio/mcp-workspace/overview) Live reads and reversible operations on productivity apps through a connected MCP server. #### [Agent-to-Agent (A2A)](/tool-studio/a2a/connect-to-other-ai-agents) Delegate open-ended tasks to other agents and existing AI investments. When no built-in search connector covers a source, build one with [Content Gateway](/tool-studio/enterprise-search/content-gateway), starting from its [Starter Code](/api-reference/content-gateway/starter-code). Plugins that users activate by chatting are [conversational plugins](/tool-studio/core-concepts/conversational-plugins); plugins activated by system events are ambient agents. For the side-by-side comparison, read [Choosing the Right Tool Framework](/tool-studio/cookbooks/choosing-the-right-tool-framework). Productivity Assistants on the Agentic Orchestrator use the same plugins, MCP servers, and A2A agents; [Tool Orchestration](/harness/agentic-orchestrator/tool-orchestration) explains how the Orchestrator exposes them. # By Job #### [Build your first tool](/tool-studio/quickstart-guide/quickstart-build-your-first-plugin) Quickstart #1 walks through a working plugin end to end. #### [Connect a system](/tool-studio/connectors) Create a connector that holds a system's base URL and authentication; every HTTP action inherits it. #### [Automate on events or schedules](/tool-studio/automation) Pair actions with webhook or scheduled system triggers to build ambient agents that run without a user prompt. #### [Let ToolSmith build it](/tool-studio/toolsmith/overview) Describe the workflow, review the proposed plan, and ToolSmith builds or edits the plugin for you. #### [Test and debug](/tool-studio/development-and-testing) Launch to yourself, read the logs, and work through common errors before publishing. #### [Watch it run](/tool-studio/agent-telemetry) Execution logs, MCP tool call logs, assistant analytics, and the Data API once a tool is live. Event-driven and scheduled plugins follow the ambient agent pattern; [Ambient Agents](/ai-assistant/ambient-agents) explains the Listen β†’ Understand β†’ Act cycle. Systems behind your firewall connect through the [Moveworks On-Prem Agent](/tool-studio/moveworks-agent). If another system needs to call Moveworks APIs, create its credentials under [API Credentials](/api-reference/api-credentials). # Quick Reference Starting from an outcome and not sure which primitive to use? Start here. | I want to… | Use | | ----------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------ | | Call an API | [HTTP Action](/tool-studio/actions/http-actions) | | Run custom code (APIthon) | [Script Action](/tool-studio/actions/script-actions) | | Orchestrate multiple actions | [Compound Action](/tool-studio/actions/compound-actions) | | Call an LLM inline | [generate_text_action / generate_structured_value_action](/tool-studio/actions/llm-actions) | | Send a message to a user | [`notify`](/tool-studio/actions/compound-actions/notify) expression | | Branch on a condition | [`switch`](/tool-studio/actions/compound-actions/switch) expression | | Handle an API failure | [`try_catch` / `raise`](/tool-studio/actions/compound-actions/try-catch-and-raise-error) | | Loop over a list | [`for`](/tool-studio/actions/compound-actions/for) expression | | Run actions concurrently | [`parallel`](/tool-studio/actions/compound-actions/parallel) expression | | End a compound action and return data | [`return`](/tool-studio/actions/compound-actions/return) expression | | Look up a user by email | [`get_user_by_email`](/tool-studio/actions/built-in-actions#get_user_by_email) | | Look up many users at once | [`batch_get_users_by_email`](/tool-studio/actions/built-in-actions#batch_get_users_by_email) | | Request human approval | [`create_generic_approval_request`](/tool-studio/actions/built-in-actions#create_generic_approval_request) | | Send batch chat notifications | [`batch_send_plaintext_chat_notification`](/tool-studio/actions/built-in-actions#batch_send_plaintext_chat_notification) | | Collect user input | [Slots](/tool-studio/conversation-process/slots) | | Validate a slot value | [Validation policy](/tool-studio/guides/best-practices/slot-best-practices#missing-validation-policy) with DSL | | Write a condition or validation rule | [DSL Reference](/api-reference/configuration-languages/dsl) | | Reshape an API response | [Data Mappers](/api-reference/configuration-languages/mapper/examples-parsing-a-streamed-response): MAP(), MERGE(), FILTER(), RENDER(), LOOKUP() | | Branch a conversation on an action result | [Decision Policy](/tool-studio/conversation-process/control-flow#pattern-action--decision-policy--branch) | | Display a knowledge article or form | [Content Activity](/tool-studio/conversation-process/activities/content-activities) | | Handle large API responses (>7K tokens) | [Response Sizes / SDA](/tool-studio/conversation-process/activities/response-sizes) | #### [Actions](/tool-studio/actions) HTTP, Script, Compound, LLM, and Built-in actions #### [Conversation Process](/tool-studio/conversation-process) Slots, resolver strategies, activities, and control flow #### [Natural Language Triggers](/tool-studio/core-concepts/conversational-plugins/natural-language-triggers) Conversational plugin activation #### [System Triggers](/tool-studio/system-triggers) Webhooks and scheduled triggers #### [Data Bank](/tool-studio/core-concepts/data-bank) Reference patterns: data.*, meta_info.*, response, value #### [Data Types](/tool-studio/core-concepts/data-types) Built-in and custom data types # Guides & Best Practices #### [The Golden Rule](/tool-studio/guides/best-practices/the-golden-rule) The single most important pattern for building reliable plugins #### [Decision Frameworks](/tool-studio/guides/getting-started/decision-frameworks) When to use compound actions vs conversation processes, slot types, and more #### [Plugin Building Masterclass](/tool-studio/guides/plugin-building-masterclass) Build a plugin end to end, from the downstream API through launch, testing, and operation #### [Slot Best Practices](/tool-studio/guides/best-practices/slot-best-practices) Anti-patterns and best practices for slot design #### [Conversation Process Best Practices](/tool-studio/guides/best-practices/conversation-process-best-practices) Anti-patterns and best practices for conversation processes #### [LLM Action Best Practices](/tool-studio/guides/best-practices/llm-action-best-practices) When NOT to use LLM actions and the decision matrix The Guides tab also covers [Testing & Error Handling](/tool-studio/guides/getting-started/testing-and-error-handling), [Pass Data to Dynamic Resolvers with Strategy Mapping](/tool-studio/guides/getting-started/pass-data-to-dynamic-resolvers-with-strategy-mapping), [Access Control Best Practices](/tool-studio/guides/best-practices/access-control-best-practices), [Building a Conversational Plugin](/tool-studio/guides/architecture/building-a-conversational-plugin), [Building an Ambient Agent](/tool-studio/guides/architecture/building-an-ambient-agent), [Choose How to Connect External Systems to Moveworks](/tool-studio/guides/architecture/choose-how-to-connect-tool-studio), and [LLM Orchestration Patterns](/tool-studio/guides/architecture/orchestration-patterns). # Samples You can view over 100 pre-built AI agents on our [AI Agent Marketplace](https://aka.mw/marketplace) and import example templates to better understand how they are built. ![](https://files.readme.io/8c69e09ceaf6dea2c55ef9838b172d79b3466c525d9cd9bc0e3ac8176ad97104-CleanShot_2025-06-30_at_17.49.09.gif) # How Tools Fits With the Rest of the Platform Tools describes what the assistant can call. The [Harness](/harness/overview) explains how the [Agentic Reasoning Engine](/harness/agentic-reasoning-engine) decides which of your tools to use in a conversation, and [Why Plugins](/tool-studio/why-plugins) explains how plugins follow your business rules every time once selected. Who can launch and use each plugin or MCP server is set through launch configuration in [Platform Management](/platform-management/access-control/end-user-access-control).