---
sourceDocument: Brazil ServiceNow AI Platform Capabilities
sourceDocumentLink: https://www.servicenow.com/docs/r/servicenow-platform

 Release :

    - brazil

ft:locale :

    - en-US

ft:publication_title :

    - Brazil ServiceNow AI Platform Capabilities

ft:clusterId :

    - platcap

bundleId :

    - platcap

workflow :

    - Platform


---

# Guidelines for slot filling in catalog request

# Guidelines for slot filling in catalog request {#ariaid-title1}

Release version: Brazil  
Updated September 10, 2026  
![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 minutes to read
Summarize  
![AI sparkle icon](https://servicenow.com/docs/portal-asset/ai-sparkle-icon) Summarized using AI  
This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete.  

## Summary of Guidelines for slot filling in catalog request

ServiceNow's Conversational Catalog Requests feature leverages a large language model (LLM) to automatically extract and pre-fill catalog item questions from a requester's conversational input.
This process, known as slot filling, reduces manual data entry by identifying relevant answers from the requester's message and populating the catalog request form accordingly.
While slot filling enhances user experience, its accuracy can vary due to the probabilistic nature of LLMs, so the goal is to maximize pre-fill precision rather than guarantee it.
Show full answer Show less  

## Catalog item question configuration

Effective slot filling depends heavily on how catalog item questions are configured. Best practices include:

* Use concise, clear, and unambiguous question labels that focus on a single concept to improve LLM comprehension.
* Avoid overlapping or similar question names within the same catalog item to reduce confusion and inconsistent pre-filling.
* Structure the internal question **Name** field starting with the object followed by the attribute (e.g., *daterequired*), which helps the LLM correctly identify question context.
* Replace system-generated or cryptic question names with human-readable names that clearly describe the item (e.g., *Laptopcharger* instead of *Hardware001P04power*).
* Ensure the property *com.glide.cs.genai.discovery.limits.skill.slots* is set to its default value or appropriately adjusted, as it controls how many questions are included for slot filling. Lowering this value limits pre-filling.

## Model selection

The LLM model configured for the Conversational Catalog skill significantly impacts slot fill quality. More capable and recent models improve:

* Extraction of complex data types such as dates and relative time expressions (e.g., "next Tuesday").
* Handling of multi-variable extractions from a single input.
* Resolution of ambiguous references, like matching requester names to user records when duplicates exist.

Customers experiencing persistent slot fill issues despite well-configured questions should verify the model assigned to their Conversational Catalog skill in AI Admin Hub \> Skills. Upgrading to a more advanced model may enhance performance. For model options and entitlement guidance, customers should contact their ServiceNow account team.  
Conversational Catalog Requests uses a large language model (LLM) to extract variable values from a requester's input and pre-fill catalog item questions, a capability known as slot filling.
When a requester describes their need in the conversational interface, ServiceNow Otto passes that input to an LLM. LLM identifies the relevant catalog item questions and extracts matching values from the requester's message. Those values are then pre-filled into the catalog item
request form, reducing the number of fields the requester must complete manually.{#c_slot_filling_ccr__c_slot_filling_ccr-overview-1}

Because LLMs are probabilistic by design, slot fill accuracy can vary across sessions even for identical inputs. Slot fill accuracy cannot be guaranteed. The goal is to maximize pre-fill
accuracy.{#c_slot_filling_ccr__c_slot_filling_ccr-overview-2}

## Catalog item question configuration {#c_slot_filling_ccr__section_question_configuration}

The LLM uses question labels and descriptions to determine what information to extract from the requester's input. Ambiguous or poorly written question labels are a leading cause of
missed or incorrect slot fill. The following considerations apply when configuring catalog item questions for use with slot filling:{#c_slot_filling_ccr__c_slot_filling_ccr-question_configuration-1}

* Keep the Question field label concise and unambiguous. Avoid long or multi-part labels. For example, use a single focused label such as "What issue are you experiencing?" rather than combining multiple questions into one label.
* Avoid overlapping question names in the Name field. When two questions in the same catalog item have similar labels, for example "Requested For" and "On behalf of", the LLM may fill them inconsistently. Differentiate question names clearly to reduce ambiguity.
* In the Name field definition, lead with the object and follow with the attribute. For example, use `date_required` rather than `required_date`. This structure enables the LLM to identify the correct question.
* Replace system-generated prefixes and internal question names with human-readable names. For example, replace `Hardware_001_P04_power` with `Laptop_charger`.
* Use names that reflect what the item actually is, so the LLM can match requester input to the correct question reliably.
* Check the value of the com.glide.cs.genai.discovery.limits.skill.slots property, which controls how many questions are sent for slot fill. If the value is set to a value less than the default, questions beyond that limit aren't pre-filled. Restore the value to the default unless there is a specific reason to reduce it.

## Model selection {#c_slot_filling_ccr__section_model_selection}

Slot fill quality is directly influenced by the capability of the LLM configured for the instance. Older or smaller models have reduced ability to interpret ambiguous input, resolve
references. Such as matching a name to a user record when duplicates exist, and pre-fill multi-variable catalog items.{#c_slot_filling_ccr__c_slot_filling_ccr-model_selection-1}

If slot fill failures persist on catalog items with clear, well-configured question labels, check which model is configured for the instance's Conversational Catalog skill. A more capable or
recent model typically improves the following:{#c_slot_filling_ccr__c_slot_filling_ccr-model_selection-2}

* Extraction of date and relative time expressions, for example "next Tuesday" or "in two weeks".
* Multi-variable extraction from a single requester utterance.

To review the model configuration, navigate to AI Admin HubSkills and check the model assigned to the Conversational Catalog skill. Contact your account team for guidance on available model options for your entitlement.{#c_slot_filling_ccr__c_slot_filling_ccr-model_selection-3}

*[\>]: and then