Coding with AI

Gen Digital used Amazon Bedrock AgentCore Web Search to build the AI-curated news engine for Norton Revamp.

Gen built Norton Revamp with AgentCore Web Search to ground AI news, content ideas, and goals in cited, real-time web sources.

Key Takeaways

  • Gen Digital launched Norton Revamp in March 2026, a generative AI platform that helps professionals turn ideas into authentic social media content and manage their online reputation.
  • Its core AI-curated News Engine uses Amazon Bedrock AgentCore Web Search to ground personalized news feeds, content suggestions, and goal roadmaps in current, cited web results.
  • The team chose managed Web Search over custom crawlers, third-party APIs, and static knowledge bases because it has no infrastructure overhead, stays within AWS with zero data egress, and returns source URLs and publication dates.
  • The event-driven architecture combines Amazon Nova, Nova Lite, Bedrock, Stability AI, and AWS services to retrieve, rank, generate, and refine content, while AI-assisted development helped a small team build the platform rapidly.

Meta description: Gen launched Norton Revamp in March 2026, using Web Search on Amazon Bedrock AgentCore for cited, real-time AI reputation content for professionals.

Gen Digital used Amazon Bedrock AgentCore Web Search to build the AI-curated news engine for Norton Revamp.

Tags: Amazon Bedrock AgentCore Web Search, Norton Revamp, generative AI, real-time grounding, AWS

Featured image: Abstract illustration of a glowing search icon feeding a networked document stream, with friendly geometric shapes and no real people, logos, or text.

Gen launched Norton Revamp in March 2026, a generative AI-powered professional reputation management platform built by a small group of engineers. The story is useful for professionals who publish career-focused content and for builders who need to see how Web Search on Amazon Bedrock AgentCore can attach current, cited web results to AI-generated recommendations. The Gen team built the platform to help customers turn ideas into engaging social media posts.

Why live sources matter

A professional’s online presence now often arrives before a résumé does. Recruiters may check LinkedIn before returning a call, and clients may review digital presence before booking a first meeting. For a person building a reputation as a generative AI thought leader, reacting to today’s breakthroughs matters more than repeating last week’s headlines. As AI-generated noise floods feeds, audiences reward authenticity and timeliness.

What the News Engine does

Unlike chatbots that rely on static knowledge bases, Norton Revamp centers on an AI-curated News Engine, powered by AgentCore Web Search, that grounds every content suggestion, goal recommendation, and news feed item in current, cited web knowledge.

The engine supports three features. A personalized news feed surfaces the latest articles and trending topics tied to each user’s goal. A cyber security expert can receive today’s threat intelligence, while a marketing leader can see this week’s industry shifts. Unlike a static Really Simple Syndication aggregator, the feed is a goal-aware discovery engine that refreshes with every session.

Users receive AI-generated content ideas tailored to trending topics, written in their own authentic voice, with optional AI-generated visuals from Stability AI. A three-step coaching flow, Analyze, Refine, Post, guides users from initial ideas to published content on LinkedIn and X. A feedback loop lets the AI get sharper with every iteration.

Gen Digital used Amazon Bedrock AgentCore Web Search to build the AI-curated news engine for Norton Revamp.

Users define a goal, and the AI builds a personalized roadmap with weekly themes and milestones. AgentCore Web Search feeds real-time trend data into goal generation, so weekly themes reflect current industry movements. The system learns from the past four weeks of activity and refreshes recommendations as users grow.

Why managed search was chosen

Before choosing AgentCore Web Search, the team evaluated custom web crawlers, third-party news APIs, and static content databases. Crawlers require ongoing maintenance and lag real time. Third-party news APIs added vendor contracts, API key management, and data leaving the AWS environment. Static knowledge bases were perpetually stale.

Web Search on Amazon Bedrock AgentCore is fully managed, has zero infrastructure overhead, operates entirely within AWS with zero data egress, and returns cited sources with URLs and publication dates. This makes personalized, real-time news feeds viable at scale. It is available as a managed connector on the AgentCore Gateway, a capability of Amazon Bedrock AgentCore, and follows the Model Context Protocol (MCP). The agent sends a natural-language query, and Web Search returns relevant snippets, source URLs, titles, and publication dates that the model uses to produce grounded responses.

Architecture and engineering process

The integration is event-driven. When a user sets or updates a professional goal, Amazon Nova, through Amazon Bedrock, generates targeted search queries from the goal, recent activity, and engagement patterns. The agent sends those queries to AgentCore Web Search, which returns cited results entirely within AWS. The AI Learning System ranks results for relevance, recency, and source credibility. Amazon Nova Lite uses the ranked results as grounding context to generate content suggestions in the user’s authentic voice. Engagement data feeds back into query generation.

The stack uses Amazon Bedrock for content generation, personalization, post analysis in batch mode, and content coaching; Amazon Nova and Nova Lite as primary large language model (LLM) engines for content generation, goal creation, and trend analysis; Web Search on Amazon Bedrock AgentCore for real-time retrieval; Stability AI for image generation; and Claude, through Amazon Bedrock, for complex reasoning tasks. Frontend tools are React, TypeScript, and Tailwind CSS. Backend tools are Node.js, Amazon Elastic Container Service, AWS Lambda, Amazon DynamoDB with multi-table composite key patterns, Amazon API Gateway, Amazon Simple Storage Service, Amazon Simple Queue Service, Amazon EventBridge, Amazon CloudFront, Amazon CloudWatch, and AWS Secrets Manager, managed by Terraform with blue-green deployment for zero-downtime releases.

The pipeline runs four stages. Full Scan pulls up to 1,000 historical posts, stores them in Amazon Simple Storage Service, and runs Amazon Bedrock batch analysis for reputation impact. Daily Scan uses Amazon EventBridge for incremental analysis. Weekly Goal Generation uses AWS Lambda to combine past engagement data with real-time trend data from AgentCore Web Search. Content Coaching uses synchronous Amazon Bedrock calls through Analyze, Refine, Post, grounding each step with search results.

The team treated generative AI as both product and development method. Humans owned architecture decisions, security reviews, business logic, and personalization algorithms, while AI handled code generation, documentation, test scaffolding, refactoring, and UI component creation.

Gen Digital used Amazon Bedrock AgentCore Web Search to build the AI-curated news engine for Norton Revamp.

With Claude, the team produced 10 or more design variants per concept, compressed design-to-prototype time from weeks to hours, and generated 70 percent of UI code with AI. It tested five pricing models in the time previously needed for one, and gamification went through eight iterations before launch. The measurable impact included 3x faster feature implementation, 90 percent faster boilerplate generation, 80 percent faster documentation, 70 percent faster test creation, and 65 percent faster UI component generation. AI output review consumed 20 to 30 percent of team time.

AI helped with personalization algorithms, the Amazon DynamoDB multi-table architecture, which needed experience-based judgment, security implementation, and Amazon Bedrock batch processing optimization. Product generative AI, including Amazon Bedrock, Amazon Nova, and AgentCore Web Search, and development generative AI served different purposes, and the team kept them separate.

Testing, security, and lessons

The platform achieved 85 percent code coverage through automated test generation. Critical test areas included content generation quality, AgentCore Web Search result relevance and freshness validation, engagement tracking accuracy, gamification logic, and news feed relevance to user goals.

For a product carrying the Norton brand, compliance is non-negotiable. Security checks spanned static code analysis, dependency vulnerability scanning, authentication flows, user data encryption, access control logic, generative AI model output validation, and content filtering. The security team reviewed all AI-generated recommendations: AI accelerated identification, and humans made final decisions. The result was 99.9 percent uptime since launch, with real-time monitoring of generative AI content quality and user satisfaction.

Teams considering AgentCore Web Search should invest in query generation, because well-structured queries yield better results than open-ended ones. They should cache strategically, because real-time freshness is the point, but some queries do not need to re-execute every session; the team uses time-to-live values that match freshness requirements. They should build feedback loops, because tracking which search results users engage with improved the News Engine’s relevance over the first 90 days. They should validate source quality, because AgentCore Web Search returns source URLs and publication dates, and a lightweight credibility scoring layer prioritized authoritative sources.

Norton Revamp shows that a small, generative AI-augmented team can deliver enterprise software in months, and that Web Search on Amazon Bedrock AgentCore can serve as the real-time intelligence backbone for products that need to stay current with the world. The launch combines personalized goal setting, AI-driven content suggestions, real-time curated news feeds grounded by AgentCore Web Search, adaptive learning, gamification, and Norton-grade security.

The source post credits Iskander Sanchez-Rola of Gen and the National Cybersecurity Alliance, Lei Gu of Gen, and Aditya Ravikumar of Amazon Web Services (AWS).

Comments (0)

  1. No comments yet. Be the first to share what worked for you.

Leave a comment

Comments are reviewed before they appear. Your email address is not published.