> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.moveworks.com/agent-studio/conversation-process/slots/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.moveworks.com/_mcp/server. # Slots # What are slots? Slots are **input values** required to execute a conversation process that requires user input. These values can be collected directly from the user or retrieved from the AI assistant's memory. Slots are critical for enabling plugins to perform actions, such as closing a Jira ticket or submitting a Workday PTO request. ### Example Use Cases * **Jira Ticket Closure**: Requires a `ticket` slot to identify the ticket. * **Slack Channel Rename**: Needs a `channel` slot (the target channel) and a `new_name` slot (the desired name). * **Workday PTO Request**: Uses a `num_days` slot to specify the duration of the leave. # Key Components of Slots ## Slot Naming and Descriptions Slot names and descriptions guide the Assistant in reasoning about and processing slots. Clear, descriptive naming and detailed descriptions improve accuracy and usability. #### Best Practices * **Be Descriptive**: Use clear, specific names and descriptions to avoid ambiguity. * **Use Semantically Unique Names**: Ensure slot names are distinct to prevent confusion during inference.
Good Examples Bad Examples
name: `ticket_comment` description: Collect user's comment for their salesforce ticket. Do NOT summarize the comment. Pass the user input verbatim. name: `slot1` description: -
name: `comment_for_approval` description: Collect user's comment for approving their request. name: `comment_for_rejection` description: Collect user's comment for rejecting their request. name: `slot1` description:- name: "slot2" description:
#### Slot Descriptions vs Policies Slot descriptions help the AI assistant understand **what** a slot is. Use them for context and light formatting guidance — not for enforcing rules or behavior. > **Warning** > > **Descriptions inform. Policies enforce.** Don't put business rules, default values, or inference logic in descriptions — use the appropriate policy instead. Descriptions are probabilistic hints; policies are deterministic guarantees. | What you want | Where to configure | How | | ---------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------- | | Format guidance (e.g., date format) | Slot description (acceptable) | Description: "Timestamp should follow YYYY-MM-DDT23:59:59." | | Default value when user doesn't specify | [Inference policy](/agent-studio/conversation-process/slots/optional-slots) — **Always Infer** with a fallback value | Set fallback to `$TIME()` for current date | | Always ask the user, never infer | [Inference policy](/agent-studio/conversation-process/slots#slot-inference-policy) — **Always Ask** | Select "Always Ask" on the `country_code` slot | | Validate input meets criteria (e.g., date not in the past) | [Validation policy](/agent-studio/conversation-process/slots#slot-validation-policy) — DSL expression | `$PARSE_TIME(value) >= $TIME()` | For more patterns and anti-patterns, see [Slot Best Practices](/agent-studio/guides/slot-best-practices). ## Slot Data Types ### Built-in Data Types * `string`: Text input (e.g., a comment or name). * `integer`: Whole numbers (e.g., number of items). * `number`: Floating-point numbers (e.g., currency or measurements). * `boolean`: True/false values (e.g., approval status). * `User`: Represents an employee in your organization, uses a built-in resolver strategy. * `File`: Represents a file attachment. [*See more about file slots*](/agent-studio/conversation-process/slots/file-slots#/) ### Custom Data Types Custom data types allow for specialized inputs tailored to your use case. For details, see the [Custom Data Types documentation.](/agent-studio/core-concepts/data-types) ### List Slots Slots can represent either a single value (`[type]`) or a list of values (`List[type]`). When creating or editing a slot, simply check the option **“Data type is expected to be a list.”** List slots are useful for plugins that need an input that behaves like a multi-select (for example, a list of users to add to a calendar event). ![](https://files.readme.io/7db86f523f320dc5c2920bc6bb7a3e268625cf59357a7d041529e6ab37653a68-CleanShot_2026-01-09_at_00.25.34.gif) If your list data type users a resolver strategy, each record will be matched again a valid candidate value. ## Slot Validation Policy Slots can include validation rules to ensure the collected value meets specific criteria. Validation is defined using the [Moveworks DSL language](/agent-studio/core-platform/configuration-languages/moveworks-dsl-reference). #### Example: To refer to the slot, use the identifier `value` in your DSL rules. For a `due_date` slot, ensure the date is today or later: **`DSL`** ```text DSL $PARSE_TIME(value) >= $TIME() ``` ![](https://files.readme.io/3e216d901769e3091fa930659c28d7255d538e9308adfc21891c2fdccc135c39-CleanShot_2025-04-09_at_03.57.34.png) ## Slot Inference Policy The inference policy controls how the AI assistant collects slot values: * **Infer slot value if available**: The Assistant attempts to derive the value from the conversation context. * **Always prompt the user**: The Assistant always prompts the user for the value, ignoring context. #### Example For a `country_code` slot, you might configure: ![](https://files.readme.io/6aece47658e57267f1d017733ac01311b4de9e99fc39bbe8cfb76a38ff70793b-CleanShot_2025-04-09_at_04.00.49.png) \ ## Resolver Strategies Resolver strategies instruct the AI agent how to convert natural language input into a structured data type. For example, converting "the login bug" into a specific `JiraIssue` object with ID `BUG-732`. Resolvers can be: * **Inherited from the data type** — if you selected a custom data type that has resolver strategies configured, those are used automatically * **Defined inline on the slot** — for slot-specific resolution logic that overrides or supplements the data type's resolvers Key resolver concepts: * **Static methods**: Preconfigured option lists (e.g., dropdown of priorities) * **Dynamic methods**: Call an action to retrieve candidates at runtime * **Output cardinality**: Whether the resolver returns a single exact match or a list of candidates for the user to pick from * **Context passing**: [Pass data from earlier slots or activities into a dynamic resolver action](/agent-studio/guides/getting-started/pass-data-to-dynamic-resolvers-with-strategy-mapping) with Strategy Mapping For full configuration details, see [Resolver Strategies](/agent-studio/conversation-process/resolver-strategies). # Configuring Slots Slots are defined in the **Conversational Process Low-code Editor** within Agent Studio. The editor allows you to specify slot names, descriptions, data types, validation policies, inference policies, and resolver strategies. ![](https://files.readme.io/c2a6ce599a0c29c35cfd29e14b93056f08ef6fe2b263b69bcb5725cb4775951c-CleanShot_2025-10-22_at_13.58.142x.png) # How the AI Assistant Handles Slots The AI assistant uses the slot configuration to determine how to prompt users for input. It evaluates the slot’s name, description, data type, and policies to formulate appropriate questions or infer values from context. # Troubleshooting Common Issues * **Ambiguous Slot Names**: If slots like `slot1` or `slot2` are used, the Assistant may misinterpret user input. Always use descriptive, unique names (e.g., `ticket_comment`). * **Validation Failures**: If users report validation errors, check the DSL expression in the validation policy for correctness. * **Inference Issues**: If the Assistant incorrectly infers a value, set the inference policy to "Always explicitly ask for slot" or clarify the description. ## Docs - [File Slots](https://docs.moveworks.com/agent-studio/conversation-process/slots/file-slots.md): Learn how to use the File slot type to receive file attachments from users in plugins. - [Optional Slots](https://docs.moveworks.com/agent-studio/conversation-process/slots/optional-slots.md)