Use Case Intelligence RSS Search use cases Search
AWS Software / SaaS Global

Gen

Fraud Detection · Risk Management

When creating Norton Genie, Gen faced several development obstacles. Its team wanted to develop a prototype within weeks instead of months, an incredibly quick turnaround.

Read the original story Explore all use cases
A study conducted by the Social Market Foundation found that one in five people were victims of scams between 2021 and 2023.
By using serverless architecture, AWS side response times are less than 1 second, and the application is scalable with little to no patching and maintenance required by Gen.
Norton Genie can differentiate between over 10 types of scams and identify locale-specific scams.
reduction in engineering effort 30%

Reported impact

Business outcome

Gen continues to improve Norton Genie. By September 2024, it plans to migrate its conversational AI technology to Amazon Lex , a fully managed AI service with advanced natural language models to design, build, test, and deploy conversational interfaces in applications. Key reported metrics include scam detection accuracy 90%; reduction in engineering effort 30%; second and less end-to-end response time (excluding LLM calls) 1.

  • Productivity Improvement
  • Risk Reduction
  • Scalability

Solution

Learn how Gen, a leader in cybersecurity and the company behind brands such as Norton, Avast, and LifeLock, quickly developed a minimum viable product for Norton Genie, an AI scam detection application, using AWS. A study conducted by the Social Market Foundation found that one in five people were victims of scams between 2021 and 2023. With scams being a several-billion-dollar threat vector, Gen wanted to build a solution to protect consumers. The company chose to go further than classic phishing protection and URL-based blockers and created Norton Genie , a generative artificial intelligence (AI) product that customers use to scan emails, images, and web links for immediate vulnerability assessment. Gen chose to build a serverless architecture on Amazon Web Services (AWS). Source data enters the Gen workflow through its application services, stored or indexed in Amazon DynamoDB, processed with AWS Lambda, coordinated by AWS Step Functions.

Data flow

Source data enters the Gen workflow through its application services, stored or indexed in Amazon DynamoDB, processed with AWS Lambda, coordinated by AWS Step Functions.

Solution architecture

3 components · 3 layers
  1. Compute
    • AWS Lambda Runs event-driven compute for real-time processing without server management.
  2. Storage
    • Amazon DynamoDB Stores operational application data with low-latency access.
  3. Orchestration
    • AWS Step Functions Coordinates multi-step application or data workflows.

Architecture clues

  • Because AWS Step Functions can be separated by task, such as cleaning text, scam detection, and efficacy, multiple teams at Gen can work together in parallel, making changes to any component of the pipeline without impac
  • By using serverless architecture, AWS side response times are less than 1 second, and the application is scalable with little to no patching and maintenance required by Gen.
  • Customers submit text or images to the application, which extracts the text and runs it through an optical character recognition pipeline.
  • Gen uses AWS Lambda , which is a serverless, event-driven compute service to run code for virtually any type of application or backend service without provisioning or managing servers, as a communication mechanism to cal
  • To glue all these steps together, Gen uses AWS Step Functions , a visual workflow orchestration service.
  • “It has the flexibility, scalability, and auditability we need.” The company uses several other serverless services, including Amazon DynamoDB —a serverless, NoSQL, fully managed database service with single-digit millis

Evidence from the source

A study conducted by the Social Market Foundation found that one in five people were victims of scams between 2021 and 2023.
By using serverless architecture, AWS side response times are less than 1 second, and the application is scalable with little to no patching and maintenance required by Gen.
Customers submit text or images to the application, which extracts the text and runs it through an optical character recognition pipeline.
Norton Genie can differentiate between over 10 types of scams and identify locale-specific scams.
Norton Genie is available on Android, iOS, and the web.
When creating Norton Genie, Gen faced several development obstacles. Its team wanted to develop a prototype within weeks instead of months, an incredibly quick turnaround.
Transparency Evidence & methodology 95/100 reference value · 87% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value95/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth20/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact25/25
    4 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence87%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    6 direct source quotes retained.
  • Date provenance8/10
    The publication date comes from publisher-controlled metadata.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. AWS

    Gen customer story

    First-party
    https://aws.amazon.com/solutions/case-studies/gen-digital-video-case-study/
    Source type
    Vendor-published customer story
    Published
    Sep 16, 2024
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
Databricks Apr 23, 2026 Elliptic Software / SaaS Global Elliptic's clients—compliance teams at crypto exchanges, banks, payment providers, and institutional custody platforms—face rising alert volumes and stringent regulation, and analysts must document each decision by… 2x faster resolution of high-risk screenings Fraud DetectionRisk Management Agent Bricks / Mosaic AI · Databricks Foundation Model APIs · Databricks Model Serving OpenAI Oct 28, 2025 Doppel Software / SaaS North America Doppel needed to detect, classify, and stop phishing, impersonation, and other social-engineering threats at internet speed, long before human analysts could keep up with the volume and variation created by generative… 3x threat handling capacity Fraud DetectionRisk Management GPT-5 · LLM-driven pipeline · o4-mini OpenAI Sep 9, 2025 SafetyKit Software / SaaS North America SafetyKit needed to review huge volumes of risky multimodal content for fraud, prohibited activity, and compliance violations with higher nuance and lower cost than legacy moderation systems or manual review could… 10+ point performance gains on hardest vision tasks with GPT-5 Fraud DetectionRisk Management Computer Using Agent · GPT-4.1 · GPT-5