> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.moveworks.com/agent-studio/guides/plugin-building-masterclass/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.moveworks.com/_mcp/server. # Plugin Building Masterclass ## Docs - [Design the Outcome and Trigger](https://docs.moveworks.com/agent-studio/guides/plugin-building-masterclass/design-the-outcome-and-trigger.md): Define the business outcome, execution identity, API contract, and trigger before creating assets. - [Configure the Connector](https://docs.moveworks.com/agent-studio/guides/plugin-building-masterclass/configure-the-connector.md): Convert the downstream system's identity, permissions, base URL, and authentication contract into a reusable connector. - [Build Focused Actions](https://docs.moveworks.com/agent-studio/guides/plugin-building-masterclass/build-focused-actions.md): Create reusable HTTP actions with typed inputs, a single API operation, safe request mapping, and concise outputs. - [Map Data and Context](https://docs.moveworks.com/agent-studio/guides/plugin-building-masterclass/map-data-and-context.md): Understand each execution scope, move data across boundaries, and choose Mustache, Data Mapper, DSL, or Python. - [Collect Slots and Resolve Values](https://docs.moveworks.com/agent-studio/guides/plugin-building-masterclass/collect-slots-and-resolve-values.md): Design typed conversational inputs with inference policies, deterministic validation, and static or dynamic resolvers. - [Compose the Workflow](https://docs.moveworks.com/agent-studio/guides/plugin-building-masterclass/compose-the-workflow.md): Separate deterministic backend orchestration from user-facing conversation and expose one useful result. - [Publish and Trigger the Plugin](https://docs.moveworks.com/agent-studio/guides/plugin-building-masterclass/publish-and-trigger-the-plugin.md): Package the capability, configure retrieval metadata and launch access, and add a conversational or system trigger. - [PurpleSuite Build Reference](https://docs.moveworks.com/agent-studio/guides/plugin-building-masterclass/purple-suite-build-lab.md): Review the complete PurpleSuite feature-request build and finish any missing Agent Studio assets. - [Test and Operate](https://docs.moveworks.com/agent-studio/guides/plugin-building-masterclass/test-and-operate.md): Validate each module, the full execution path, retrieval, permissions, security boundaries, and production behavior. > **Note:** This page contains both a page directory (above) and the landing page content (below). The page directory is generated for agent use and does not appear on the landing page. > For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.moveworks.com/agent-studio/guides/plugin-building-masterclass/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.moveworks.com/_mcp/server. # Plugin Building Masterclass A plugin is a deployable capability that the Moveworks AI assistant can select or a system event can start. You build it from small, reusable modules: connectors, actions, typed data contracts, orchestration, and a trigger. This masterclass teaches the complete architecture. You will learn where each module begins and ends, what data it can access, what the reasoning engine can see, and when to use deterministic logic instead of model instructions. > **What You Will Build** > > The hands-on path uses the PurpleSuite Community API to build one continuing capability: **Manage Product Feature Requests**. Every chapter adds a working asset, from the connector and HTTP actions through slots, mappings, orchestration, publication, and testing. Keep the same PurpleSuite instance and assets as you progress. Each chapter includes a **Build Along** section with a concrete checkpoint, so the concepts immediately become a working plugin. ## The One-Picture Mental Model Choose a trigger, then select a stage to see what changes and what stays reusable. The architecture follows one rule: > Use the reasoning engine for language, intent, and conversation. Use typed inputs, mappings, DSL, policies, and code for business rules that must behave predictably. The two sides work together: | Probabilistic layer | Deterministic layer | | ----------------------------------------------- | ----------------------------------------------- | | Selects the most relevant conversational plugin | Constrains which APIs and operations can run | | Infers slot values from natural language | Validates collected values with DSL | | Asks follow-up questions | Maps exact values into typed action inputs | | Presents useful results | Filters, renames, and structures action outputs | | Chooses the next conversational step | Executes backend sequences in compound actions | ## The Running PurpleSuite Trace Every chapter uses the same live record and call sequence. Select a stage to see the Agent Studio asset that owns it, the exact PurpleSuite operation, and the data passed to the next module. ## The Building Blocks #### Plugin A plugin packages a capability for deployment. A conversational plugin uses a user utterance as its trigger. A plugin with a system trigger, often called an ambient agent, uses a webhook or schedule. #### Connector A connector represents one external system's base URL and authentication configuration. Build it from the downstream system's account and permission model, then reuse it across compatible HTTP actions. #### Action An action is one reusable executable operation. An HTTP action represents one HTTP request. Script, built-in, LLM, and compound actions provide other execution patterns. #### Compound Action A compound action coordinates uninterrupted backend work behind one action boundary. Its intermediate steps remain internal; its return value becomes the contract for the caller. #### Conversation Process A conversation process coordinates user-facing work. It collects slots, applies policies, invokes actions through activities, and decides when to ask, confirm, or display information. #### Slots and Resolvers Slots are typed values collected during a conversation. Resolvers translate natural-language selections into allowed values or stable business objects such as a system ID. #### Data Bank and Mappings Each execution scope exposes a specific set of runtime values. Input mappings, output mappings, and compound action returns move selected data across those boundaries. ## Course Map Complete the course in order the first time. Return to individual modules later as an architecture reference. #### [1. Design the Outcome and Trigger](/agent-studio/guides/plugin-building-masterclass/design-the-outcome-and-trigger) Start from the business outcome, identify the execution identity, and choose a conversational or system trigger. #### [2. Configure the Connector](/agent-studio/guides/plugin-building-masterclass/configure-the-connector) Translate the downstream system's permission and authentication model into a reusable connection. #### [3. Build Focused Actions](/agent-studio/guides/plugin-building-masterclass/build-focused-actions) Create single-purpose HTTP actions with typed inputs, test values, request fields, and concise response schemas. #### [4. Map Data and Context](/agent-studio/guides/plugin-building-masterclass/map-data-and-context) Learn what data exists in each scope and when to use Mustache, Data Mapper, DSL, or Python. #### [5. Collect Slots and Resolve Values](/agent-studio/guides/plugin-building-masterclass/collect-slots-and-resolve-values) Design typed conversational inputs, deterministic validation, inference policies, and static or dynamic resolvers. #### [6. Compose the Workflow](/agent-studio/guides/plugin-building-masterclass/compose-the-workflow) Separate user-facing orchestration from backend sequences and shape the output that crosses each boundary. #### [7. Publish and Trigger the Plugin](/agent-studio/guides/plugin-building-masterclass/publish-and-trigger-the-plugin) Package the capability, write retrieval metadata, configure launch access, and add conversational or system triggers. #### [8. PurpleSuite Build Reference](/agent-studio/guides/plugin-building-masterclass/purple-suite-build-lab) Review the completed architecture, compare every asset with the reference build, and finish any remaining checkpoints. #### [9. Test and Operate](/agent-studio/guides/plugin-building-masterclass/test-and-operate) Validate components, context boundaries, trigger behavior, permissions, failure paths, and production logs. ## Before You Begin You should have: * Access to Agent Studio with permission to create connectors, actions, processes, and plugins. * Access to the downstream system's API documentation and an approved test account. * A [PurpleSuite instance](/agent-studio/quickstart-guide/purple-suite-setup) for the build-along exercises. * A non-production environment and test data for any write operation. > **Protect Credentials and Production Data** > > Do not paste API tokens into plugin descriptions, slot descriptions, example utterances, URLs, or screenshots. Store credentials in a connector. Test mutations only against approved non-production data. ## Continue Start with [Design the Outcome and Trigger](/agent-studio/guides/plugin-building-masterclass/design-the-outcome-and-trigger).