High agent assist usage when testing under Agent StudioIssue <!-- /*NS Branding Styles*/ --> .ns-kb-css-body-editor-container { p { font-size: 12pt; font-family: Lato; color: var(--now-color--text-primary, #000000); } span { font-size: 12pt; font-family: Lato; color: var(--now-color--text-primary, #000000); } h2 { font-size: 24pt; font-family: Lato; color: var(--now-color--text-primary, black); } h3 { font-size: 18pt; font-family: Lato; color: var(--now-color--text-primary, black); } h4 { font-size: 14pt; font-family: Lato; color: var(--now-color--text-primary, black); } a { font-size: 12pt; font-family: Lato; color: var(--now-color--link-primary, #00718F); } a:hover { font-size: 12pt; color: var(--now-color--link-primary, #024F69); } a:target { font-size: 12pt; color: var(--now-color--link-primary, #032D42); } a:visited { font-size: 12pt; color: var(--now-color--link-primary, #00718f); } ul { font-size: 12pt; font-family: Lato; } li { font-size: 12pt; font-family: Lato; } img { display: ; max-width: ; width: ; height: ; } } The Generative AI Usage Log (sys_gen_ai_usage_log) table shows multiple entries where the Document value (e.g., "Topic: AIA-Agent Invoker") has a consumption count of 25 assists each. This does not occur when using the virtual agent directly. Since the Web Search AI agent is the only one currently in use, these logs are generated by that agent. Is there a way to directly correlate the usage log entries with this specific agent? Additionally, even if they are tied to the Web Search agent, a consumption rate of 25 assists per activity seems unusually high. Can you confirm if this accurately reflects the usage for a single end-to-end activity performed by the agent? Release<!-- /*NS Branding Styles*/ --> .ns-kb-css-body-editor-container { p { font-size: 12pt; font-family: Lato; color: var(--now-color--text-primary, #000000); } span { font-size: 12pt; font-family: Lato; color: var(--now-color--text-primary, #000000); } h2 { font-size: 24pt; font-family: Lato; color: var(--now-color--text-primary, black); } h3 { font-size: 18pt; font-family: Lato; color: var(--now-color--text-primary, black); } h4 { font-size: 14pt; font-family: Lato; color: var(--now-color--text-primary, black); } a { font-size: 12pt; font-family: Lato; color: var(--now-color--link-primary, #00718F); } a:hover { font-size: 12pt; color: var(--now-color--link-primary, #024F69); } a:target { font-size: 12pt; color: var(--now-color--link-primary, #032D42); } a:visited { font-size: 12pt; color: var(--now-color--link-primary, #00718f); } ul { font-size: 12pt; font-family: Lato; } li { font-size: 12pt; font-family: Lato; } img { display: ; max-width: ; width: ; height: ; } } Yokohama, Zurich Resolution<!-- /*NS Branding Styles*/ --> .ns-kb-css-body-editor-container { p { font-size: 12pt; font-family: Lato; color: var(--now-color--text-primary, #000000); } span { font-size: 12pt; font-family: Lato; color: var(--now-color--text-primary, #000000); } h2 { font-size: 24pt; font-family: Lato; color: var(--now-color--text-primary, black); } h3 { font-size: 18pt; font-family: Lato; color: var(--now-color--text-primary, black); } h4 { font-size: 14pt; font-family: Lato; color: var(--now-color--text-primary, black); } a { font-size: 12pt; font-family: Lato; color: var(--now-color--link-primary, #00718F); } a:hover { font-size: 12pt; color: var(--now-color--link-primary, #024F69); } a:target { font-size: 12pt; color: var(--now-color--link-primary, #032D42); } a:visited { font-size: 12pt; color: var(--now-color--link-primary, #00718f); } ul { font-size: 12pt; font-family: Lato; } li { font-size: 12pt; font-family: Lato; } img { display: ; max-width: ; width: ; height: ; } } This is expected behavior when using Agent Studio. According to internal documentation (see screenshot below), the value 25 does not mean 25 assists were consumed. Instead, it represents that 4 actions (in this case, 4 Web Search tool calls) were executed to produce the results. The entries in sys_gen_ai_usage_log showing, for example, Topic: AIA-Agent Invoker with 25 assists are normal for an Agentic workflow—specifically the one orchestrating your Web Search agent—running end-to-end. To clarify: The 25 value is not a direct count of Web Search assists.Rather, it reflects that the entire workflow fell into the “small workflow (0–4 actions)” category, which is predefined to report as 25 assists for licensing and reporting purposes.This value is a static mapping, not a real-time counter of tool calls. When the workflow is triggered via Virtual Agent, the usage is still captured under the same Agent Invoker record in sys_gen_ai_usage_log. However, the assists are attributed to the orchestrating Agentic workflow, not to the individual Web Search agent or child tool. In summary: The 25 assists in sys_gen_ai_usage_log reflect the correct usage for that Agentic workflow execution.The value corresponds to a small workflow (0–4 actions), as defined in the Assist Overview—not 25 separate actions.Individual Web Search calls are not logged separately for consumption; instead, they roll up into the parent Agent Invoker record.