Call center ai · Production

Netsertive builds scalable AI call insights assistant using Amazon Bedrock and Amazon Nova

The problem

Netsertive needed to unlock business intelligence from customer call tracking data at scale, but manual call review processes took hours or even days for high-volume customers, making real-time actionable insights impractical.

Workflow diagram · grounded in source
1
Incoming call routed to Lead API
trigger
“When a call comes in, it's immediately routed to the Lead API. This process captures both the live call transcript and important metadata about the caller.”
2
Transcript forwarded to Bedrock
integration
“The captured transcript is forwarded to Amazon Bedrock for analysis. The system currently uses a standardized base prompt for all customers, and the architecture is designed to allow for customer-specific prompt customization as an added…”
3
Nova Micro analyzes transcript
ai_action
“Amazon Nova Micro processes the transcript and returns a structured JSON response. This response includes multiple analysis components: sentiment analysis of the conversation, a concise call summary, identified key terms, overall call th…”
4
Results stored in Aurora
integration
“All analysis results are systematically stored in an Amazon Aurora database with their associated key metrics.”
5
Scheduled aggregate run
trigger
“The aggregate analysis process automatically initiates on both weekly and monthly schedules.”
6
Trend analysis across calls
ai_action
“This aggregate analysis uses both Amazon Bedrock and Amazon Nova Micro, applying a specialized prompt designed specifically for trend analysis.”
7
Reports generated through UI
output
“The processed aggregate data from both workflows is transformed into comprehensive reports displaying trend analysis and comparative metrics through the UI.”
Reported outcome

Netsertive's Call Insights AI feature using Amazon Nova Micro on Amazon Bedrock now takes minutes to create actionable insights, replacing manual review processes that previously took hours or even days.

Reported metrics
Time to create call insightsonly takes minutes to create actionable insights
Model evaluation periodapproximately 1 week
Time from development to beta launchapproximately 30 days
Amazon Nova Micro generation speedover 200 tokens per second
Reported stack
Amazon BedrockAmazon Nova Micro
Source
https://aws.amazon.com/blogs/machine-learning/how-netsertive-built-a-scalable-ai-assistant-to-extract-meaningful-insights-from-real-time-data-using-amazon-bedrock-and-amazon-nova?tag=soumet-20
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Netsertive's Call Insights AI feature using Amazon Nova Micro on Amazon Bedrock now takes minutes to create actionable insights, replacing manual review processes that previously took hours or even days.

What tools did this team use?

Amazon Bedrock, Amazon Nova Micro.

What results were reported?

Time to create call insights: only takes minutes to create actionable insights; Model evaluation period: approximately 1 week; Time from development to beta launch: approximately 30 days; Amazon Nova Micro generation speed: over 200 tokens per second (source-reported, not independently verified).

How is this call center ai AI workflow structured?

Incoming call routed to Lead API → Transcript forwarded to Bedrock → Nova Micro analyzes transcript → Results stored in Aurora → Scheduled aggregate run → Trend analysis across calls → Reports generated through UI.

Related call center ai cases