Skip to content
Now Assist AI agents › Enable AI experiences
Release: Australia · Updated: 2025-10-27 · Official documentation · View source

Now Assist AI agents reference

Find more information about user roles, tables, and the different properties that are installed in Now Assist AI agents.

Now Assist AI agents roles

The following roles are installed with Now Assist AI agents with a compatible Now Assist application.

RoleDescription
AI Agent admin [sn_aia.admin]Administrator of the application. A user with the sn_aia_admin role can create, read, update, and delete records.
AI Agent Viewer [sn_aia.viewer]Read-only access to the application. A user with the sn_aia_viewer role has read and report access on all tables.
agent_role_config_adminWith this role, user can access and modify Agent role configurations with AI Agent admin [sn_aia_admin] being the parent role.
agent_role_config_viewerCan view the Agent role configurations with AI Agent Viewer [sn_aia_viewer] being the parent role.

Note: The roles can be assigned manually through the user record directly. For the assigned roles to take effect, logout and login back to the application.

Now Assist AI agents system properties

The following are system properties that define default values and behavior.

PropertyDescription
glide.ai\_record\_activity.validation.feature.enabled

Enables UI validation for agentic AI and skills at the instance level. If this feature is enabled, then any UI validation, such as required fields, must be met before the AI process is completed. The following properties are context-specific gates that determine where validation is done when the feature is enabled:

  • glide.ai_record_activity.ai_detection.nap.enabled: Now Assist panel executions
  • glide.ai_record_activity.ai_detection.skill.enabled: Now Assist skill execution with UI actions or in Virtual Agent
  • glide.ai_record_activity.ai_agent.validation.enabled: agentic AI-initiated record updates with UI actions or in Virtual Agent

If you want to enable these gates of the UI validation feature, you must create the system property and set the value to true. You don't need to enable this feature for individual skills or agentic AI assets.

sn\_aia.agent\_llm\_providerDefines the (large language model) LLM service provider for AI agents.Default value: azure_openai.
sn\_aia.agent\_tool\_supported\_data\_typesDefines a comma-separated list of supported data types for tools that are used by agents for IntegrationHub spoke. Each value corresponds to the name field of records in the Field classes table \[sys\_glide\_object\].
sn\_aia.analytics\_dashboard\_sysidProvides the sys\_id for the AI Agents Analytics dashboard.read\_roles: sn\_aia.admin and sn\_aia.viewer
sn\_aia.continuous\_communicator\_output\_limitDefines the maximum number of continuous outputs that the AI Agent Orchestrator can trigger to show to users. Default value: 3
sn\_aia.continuous\_tool\_execution\_limitDefines the maximum consecutive number of uses for the same tool. Default value: 7
sn\_aia.enable\_usecase\_tool\_execution\_mode\_overrideEnables running agentic workflows fully autonomously, overriding any non-automated tools in the agentic workflow. Default value: false
sn\_aia.ltm.category.auto\_createEnables AI-generated categories if no matching categories exist. Default value: false
sn\_aia.ltm.enable\_long\_term\_memoryEnables long-term memory for AI agents. All previous user interactions are used as context for the LLM. Default value: false
sn\_aia.maximum\_agent\_toolsDefines the maximum number of tools that can be assigned to an AI agent. Default value: 20
sn\_aia.max\_scheduled\_trigger\_query

Defines how many records are processed when a scheduled trigger is detected. Default value: 10

Write_role: admin

sn\_aia.mid\_skill\_switch\_enabledEnables mid-skill switching. Default value: false
sn\_aia.react\_failure\_retry\_max\_limitDefines the maximum number of retries in case of an execution failure. Default value: 3
sn\_nowassist\_va.router\_redirect\_va\_agenticDetermines AI agent discovery in Virtual Agent. If set to NEVER, Virtual Agent continues Q&A without any agentic AI.Default: ROUTER_DECISION
com.glide.cs.dynamic.capability.timeout

Defines the Timeout for AIA Proficiency Descriptor. Default value: 180.

Write_role: admin.

sn\_aia.enable\_follow\_upEnables users to continue the conversation with follow-ups after the agentic workflow execution is complete.Default value: true.
sn\_aia.follow\_up\_messageDefines a follow-up message sent after execution is completed.Default Value: How otherwise can I help you?
sn\_aia.allow\_context\_sharingEnables the sharing of short-term memory, allowing context to persist across execution within the same conversation.Default Value: true
sn\_aia.agent\_strategy\_choice\_enabledEnables to show the LLM reasoning strategy in the agent setup screen.Default Value: false
sn\_aia.context\_sharing\_strategyThis property defines the strategy to use for storing short-term memory for an execution.Default Value: summarise
sn\_aia.enable\_agent\_tool\_input\_value\_overridesEnables you to override the agent tool description.Default Value: true.
sn\_aia.follow\_up\_qna\_failure\_limitDefines the limit to exit execution if the number of consecutive questions and answers aren’t available in the follow-up.Default value: 1.
sn\_aia.ltm.use\_memory\_for\_ai\_agentEnables long-term memory for AI agent interactions. When enabled, stored user memories are utilized in AI agent interactions.Default value: true.
sn\_aia.quick\_mode\_failure\_retry\_max\_limitDefines maximum limit for retries in case of a failure in Quick Mode execution.Default value: 3.
sn\_aia.user\_context\_data

Defines a comma-separated list of user context data to be used with AI Agents. The list is used to pick the data available from knowledge graph API: getUserContext.

List of available user information:

  • profile
  • manager
  • reportees
  • assets

The user information can also be customized by overriding the method getUserContext via UserContextUtil.

If customized, the property must define the comma separated list of keys generated by the customized getUserContext method.

Default value: profile.

sn\_aia.external\_agents.enabledSet to `true` to enable external agent features
sn\_aia.external\_agents.parallel\_conversations.enabledEnables or disables multiple simultaneous conversations per user
sn\_mcp\_client.cursor.max\_iterations

Specifies the maximum number of cursor-based pagination iterations to perform when fetching MCP tools. Helps prevent excessive looping or API calls during data retrieval.

Note: Set this value to 0 to disable pagination iteration limits.

mcp\_guardian\_check

Enables guardian check for MCP Client when the value is set to true.The default value is false.

Note: To enable guardian check for MCP Client, verify that you enable Now Assist guardian on AI Agent Studio > Settings page.

com.glide.agentic\_processes\_view.enabledEnables the in-product experience for agentic workflows in the AI Workflows panel. Verify that this is set to `true` if you plan on using UI actions to run agentic workflows.
sys\_generative\_ai\_prompt\_configReferences a config record via the generative AI Config field.
System propertyDescription
sn\_aia.enable\_episodic\_memory

Enables episodic memory. When enabled, episodic memories from past interactions are collected and stored in sn_aia_memory and utilized in future interactions to enhance the overall experienceDefault value: true.

.

sn\_aia.enable\_memory\_limitMaximum number of episodic memories to inject into prompt when an agent is invoked. Note: The maximum number of values allowed is less than or equal to 5.
sn\_aia.use\_episodic\_memory\_for\_ai\_agentEnables episodic memory injection for AI agent interactions. When enabled, stored user memories are utilized in AI agent interactions.Default value: true.

Properties on the Agent Properties table

The following properties are on the Agent Properties [sn_aia_property] table. These properties affect different AI agent behaviors.

NameDescriptionDefault value
alert.assist\_spike\_hours\_to\_checkTime interval, in hours, between running the scheduled job that checks for spikes in assist usage3
alert.assist\_spike\_usage\_percentage\_thresholdPercentage increase required from previous job results to trigger the spike in assist usage notification0.5 \(50%\)
alert.assist\_spike\_usage\_thresholdMinimum number of assists to trigger the spike in assist usage notification5000
alert.consecutive\_error\_countConsecutive number of latency errors to trigger the latency notification3
alert.llm\_latency\_thresholdTime taken, in seconds, for the LLM to respond before sending a latency error10
alert.tool\_latency\_thresholdTime taken, in seconds, for a tool to finish executing before sending a latency error300
enable\_agent\_tool\_input\_value\_overridesDetermines whether tool input values can be overriden by the AI agent or other tools for use by another toolfalse
execution\_task.latency\_thresholdsDetermines thresholds on LLM and tool execution times and response tokens/character counts for tool calling
{
  "llm": {
    "timeBoundaries": [
      5000,
      10000
    ],
    "tokenLimit": 500
  },
  "tool": {
    "timeBoundaries": [
      200000,
      300000
    ],
    "outputCharLimit": 10000
  }
}
follow\_up\_behaviourActions to take by the agentic workflow after it has finished executing. Each record applies to only one agentic workflow.no\_followup\_close\_conversation
mcp\_guardian\_checkDetermines whether Now Assist Guardian runs on MCP tool executionsfalse
show\_citationsDetermines whether agentic AI-generated responses in Now Assist panel or Now Assist in Virtual Agent add citations for their outputfalse
kill\_switch.modeControls how the feature responds to a detected breachwarn\_onlyOther values include: - off - enforce
kill\_switch.consecutive\_windows\_durationThe total look back span.4320
kill\_switch.max\_fires\_per\_windowFires per record that mark it as breaching.5
kill\_switch.min\_distinct\_recordsBreaching records needed for the window to count as runaway.25
kill\_switch.window\_sizeLength of one observation window.1440

The following properties are used to detect and avoid infinite recursion or execution loops. If you reach the max executions that match the query within the time window, any new executions matching the query will abort. You can adjust these values if you want to lower the threshold for detecting recursion.

recursive\_check.create\_max\_executionsMaximum number of matching executions creating records50
recursive\_check.create\_time\_windowTime window, in minutes, for checking for matching executions creating records15
recursive\_check.query\_for\_create\_recordQuery for the fields of execution plans to create records to check if executions are repeatingobjective=\{objective\}^agent=\{agent\}^ORusecase=\{usecase\}
recursive\_check.query\_for\_update\_recordQuery for the fields of execution plans to update records to check if executions are repeatingrelated\_task\_record=\{related\_task\_record\}^objective=\{objective\}^agent=\{agent\}^ORusecase=\{usecase\}
recursive\_check.update\_max\_executionsMaximum number of matching executions updating a record5
recursive\_check.update\_time\_windowTime window, in minutes, for checking for matching execution updates15

Now Assist AI agents tables installed

The following tables are installed so Now Assist AI agents works as expected:

TableDescription
Agentic workflows \[sn\_aia\_usecase\]List of configured agentic workflows.
AI Agents \[sn\_aia\_agent\]List of configured AI agents.
Tools \[sn\_aia\_tool\]List of tools used by an AI agent.
Strategies \[sn\_aia\_strategy\]List of strategies used by an AI agent.
Teams \[sn\_aia\_team\]Team that is a group of listed agents.
Team members \[sn\_aia\_team\_member\]List of teams mapped to an agent.
Agent Tools \[sn\_aia\_agent\_tool\_m2m\]List of tools mapped to an AI agent.
AIA Trigger Configurations \[sn\_aia\_trigger\_configuration\]List of triggers created for an agentic workflow.
Execution Tasks \[sn\_aia\_execution\_task\]List of tasks by execution plan ID.
Messages \[/sn\_aia\_message\]List of messages recorded in AI agent conversations to and from the human users.
Tools Executions \[sn\_aia\_tools\_execution\]List of tools executed by the plan ID.Note: The records in the Tools Executions table expire and is set to unavailable after a period of 13 months.
Execution Plans \[sn\_aia\_execution\_plan\]List of plan executions by conversation ID.
Agent Tools \[sn\_aia\_agent\_tool\_m2m\]List of tools and maximum automatic executions.
AI Agent configs \[sn\_aia\_agent\_config\]List of active AI agents configured for the proficiency that they’ll be used in.
Agent properties \[sn\_aia\_property\]Various properties that affect AI agent behavior.
Gen AI Metadata M2M \[sn\_aia\_gen\_ai\_m2m\]List of Gen AI metadata and the maximum automatic executions.Maintains the mapping between sn\_aia\_execution\_task and Gen AI log metadata. If two large language model \(LLM\) calls are made to the sn\_aia\_execution\_task, then the sn\_aia\_gen\_ai\_m2m table has two records.
Report metrics \[sn\_aia\_report\_metric\]List of the report metrics.
Agent Access Role Configurations \[sys\_agent\_access\_role\_configuration\]List of agent access roles. You can also create agent access roles from this table.
generative AI Configurations \[sys\_generative\_ai\_config\]Record that points to the actual model.
Invocation Sources \[sn\_aia\_invocation\_source\]Functions as a registry of entry points and helps track and define the different contexts or surfaces from which an AI agent can be invoked or triggered.
TableDescription
GAF record group [sn_gaf_record_group]Stores the output of the grouping skill. Each record represents a cluster of related records. You can open each record group record to discover which records were included within the cluster.
GAF record group detail [sn_gaf_record_group_detail]Contains the individual records that belong to each group GAF record group. You can also find if a record is marked to act as a representative of the cluster on these records.
GAF action strategy result [sn_gaf_action_strategy_result]Holds the results of the Action Strategy skill, which selects representative records from each group for downstream processing.
GAF action mapper results [sn_gaf_action_mapper_result]Stores the output of the Mapper skill, which maps new records to existing clusters.
GAF action reducer results [sn_gaf_action_reducer_result]Stores the result of the Action Reducer skill. The results include insights for entire clusters. For example, how to resolve incidents similar to those gathered in a cluster.