Normalized claim
Quantified impact: 1.5% increase
Scaled to handle 1,500% more calls.
Intact Financial accelerates call auditing with Amazon Transcribe (Call Quality suite)
Use case typeCustomer support automationUpdated Jun 13, 2026
Intact Financial Corporation (Intact), the largest property and casualty insurer in Canada, built an automated Call Quality (CQ) suite to analyze customer service calls at scale. The solution transcribes recorded calls, extracts insights with additional machine learning models, and provides a dashboard and search tool for quality analysts. The system supports English and Canadian French, runs on a serverless AWS architecture, and is used to improve customer service, agent coaching, and operational efficiency.
- Organization
- Intact Financial Corporation
- Industry
- Insurance
- Location
- Canada
- Published
- May 2026
Reported outcomes
4-6x
timeTime & speed
+1.5%quantified impact4-6 hourstime−10%time+65%quantified impact−6%accuracy
Strategic outcomes
Scale & capacityScaled call auditing to handle far more volumeSpeed & agilityAccelerated call auditing workflowsCost efficiencyImproved auditor productivityCustomer experience & trustImproved customer service analysis at scale
Why do we believe this?Outcome claims, sources, and evidence checks
Normalized claim
Time: 4-6 hours increase
Processed up to 20,000 calls within 4–6 hours, a 15x improvement in audit speed.
Normalized claim
Time: 4-6 x increase
Processed up to 20,000 calls within 4–6 hours, a 15x improvement in audit speed.
Normalized claim
Time: 10% decrease
Reduced average handling time by 10%.
Normalized claim
Quantified impact: 65% increase
Quality auditors became 65% more efficient.
Normalized claim
Accuracy: 6% decrease
Improved English transcription accuracy by about 6% lower word error rate.
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- Intact Financial Corporation
- Provider
- AWS
- Maturity
- Scaled Production
- Linked source
- AWS Customer Story
Intact Financial Corporation (Intact), the largest property and casualty insurer in Canada, built an automated Call Quality (CQ) suite to analyze customer service calls at scale
Customer identity supportedSource describes one deploymentMaturity supported
Primary read
Use case focus
Showing 3 of 4
- 1Call center analytics
- 2Quality assurance automation
- 3Speech to text
- Manual call auditing was time-consuming and expensive.
- Analysts reviewed less than 2% of overall call volume.
- The company needed multilingual speech-to-text support for English and Canadian French to uncover customer experience insights at scale.
- Intact Lab built the CQ suite using Amazon Transcribe and Amazon S3 on AWS.
- Recorded calls are ingested from Amazon S3, transcribed with Amazon Transcribe, and then analyzed with additional ML models for call components, sentiment, intent, outcome, and review prioritization.
- The solution includes a CQ dashboard and search tool for analysts, and later added PII redaction and AI-powered summarization.
Technologies
- Scaled to handle 1,500% more calls.
- Processed up to 20,000 calls within 4–6 hours, a 15x improvement in audit speed.
- Reduced average handling time by 10%.
- Quality auditors became 65% more efficient.
- Improved English transcription accuracy by about 6% lower word error rate.
Architecture
A secure serverless AWS architecture where recorded calls are stored in Amazon S3, sent to Amazon Transcribe for speech-to-text conversion, and then processed by additional ML models for sentiment, intent, outcome, and review routing. Analysts access a CQ dashboard and search tool for call-quality insights; later enhancements added PII redaction and AI-powered summarization.
Sources & evidence1
Evidence: Medium65/100Evidence strength
- Customer explicitly identified
- Deployment status explicitly supported
- Primary source available
- Quantified outcome available
- Technical implementation details available
Type: Customer StoryPublished: May 27, 2026Publisher: AWSEvidence: PrimaryConfidence: High
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
Browse the catalog
Was this useful?
Community
Comments
Loading comments...