Key Tables You Must Know for Now Assist Token Configuration
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
05-25-2026 09:36 AM - edited 05-25-2026 09:37 AM
Building Custom Now Assist Skills in ServiceNow? Token Limits Are Your Hidden Bottleneck.
Perfect prompt engineering means nothing if your responses are getting truncated.
While implementing custom Now Assist Skill Kit solutions, I kept hitting the same wall default token configurations silently breaking real-world GenAI workflows.
Key Backend Tables to Know:
Purpose | Table |
Now Assist skills | sys_one_extend_capability |
Request Token Config | sys_generative_ai_model_config |
Response Token config | sys_generative_ai_config |
This impacts critical use cases like:
. Incident Summarization
· Problem RCA
· HRSD Case Analysis
· AI Agent Workflows
· Multi-record Context Prompts
The real lesson?
GenAI success in ServiceNow isn’t just about what you prompt. it’s about how the model is configured to respond.
Master these 5 pillars:
- Token Optimization
- Context Management
- Response Chunking
- Model Configuration
- Governance & Observability
As Now Assist adoption accelerates, token management is becoming a core skill for every ServiceNow AI engineer not an afterthought.
Have you hit token limits in your GenAI implementations? Drop your experience below
- 1,409 Views
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Thursday
If you are configuring token limits for custom Now Assist skills, the main thing is to distinguish between request token limits, response token limits, and skill configuration.
The following tables are mentioned in the Community discussion:
sys_one_extend_capability stores capability definitions.
sys_generative_ai_model_config relates to generative AI model configuration.
sys_generative_ai_config relates to generative AI configuration.
I would recommend the following checks:
Open the relevant Now Assist skill in Now Assist Skill Kit.
Review its prompt and input context to identify how much data is being sent to the model.
Check the configured model and its supported token limits.
Review the request and response configuration for the selected model.
Test with larger records to identify whether truncation happens in the input or generated response.
You can also monitor overall Now Assist consumption through Admin > Subscription Management > Subscriptions > Now Assist usage.
One important point: avoid directly updating the three backend tables to change token limits. Their exact configuration behavior can vary by release and model provider. Use the supported configuration interface wherever available.
ServiceNow references: