Category: Amazon Bedrock

Grubhub and Vody are proving that the winners of AI-powered commerce won’t be defined by a single breakthrough feature, they’ll be the retailers who invest early in unified, AI-ready data foundations built on AWS. By modernizing catalog, content, and behavioral data across 400,000+ merchants, they delivered initial model results in just 6–10 weeks and demonstrated measurable improvements in search relevance, conversion, and customer experience, offering a blueprint for retailers preparing to lead the next wave of AI innovation.

You’ve deployed your agents on Amazon Bedrock AgentCore but making them reachable from Claude Desktop, VS Code, Cursor, or GitHub Copilot means building an “experience layer” that handles identity, authorization, discovery, and developer UX. In this post, ASCENDING shares how they turned that recurring integration work into the Jarvis Registry, an open source experience layer that runs inside your AWS environment and connects agents to every IDE and copilot. See how one customer uses it to serve both business users and engineers from the same set of agents, with department-scoped access enforced across every tool.

As enterprises race to ship features faster and reduce technical debt, AI-assisted development has moved from experimental to essential with Gartner predicting 75% of enterprise engineers will use AI code assistants by 2028. OpenAI ChatGPT Codex on Amazon Bedrock brings frontier agentic coding capabilities to AWS customers, enabling developers to offload complex, multistep coding tasks while maintaining the security, governance, and operational controls that enterprise environments demand. Learn how ChatGPT Codex goes beyond simple code completion to reason across entire repositories, generate tests and documentation, and accelerate delivery all through a fully managed, serverless API with zero operator access and pay-per-token pricing.

When AI infrastructure costs consumed 40% of per-interview revenue, InterWiz knew their single-provider architecture couldn’t support profitable growth. By partnering with AWS Advanced Tier Services Partner Emumba to migrate from Azure OpenAI to Amazon Bedrock, InterWiz reduced AI costs by 90%, improved response times by 55%, and maintained 99.9% uptime, all with zero service disruption. Learn how a multi-model architecture on Amazon Bedrock transformed InterWiz’s cost-to-revenue ratio and created lasting competitive advantage.

The AI-Driven App Modernization Platform from Pega and AWS enables enterprises to incrementally transform legacy applications from mainframes to monolithic applications into intelligent, cloud-native workflows using AI-powered discovery, low-code design, and the strangler fig pattern, cutting modernization timelines from years to months without disrupting critical business operations.

DevRev built real-time AI guardrails into its enterprise agent system, powered by Amazon Nova 2 Lite through Amazon Bedrock. The guardrail layer evaluates every user input against default and custom policies in 247ms average latency without degrading the conversational experience. This post explores how DevRev delivers high support ticket automation and cost reduction while keeping content on-policy and safety controls firm.

As cloud-native environments expand, security and operations leaders face mounting pressure to reduce response times while managing growing alert volumes and team capacity. Elastic’s AI-powered features on Amazon Bedrock automate the path from detection to resolution across both security and observability workflows. Learn how conversational agents, automated workflows, and custom AI agents accelerate incident response and root cause analysis on AWS.

As AI agents take actions across systems on behalf of your users, identity and access management must sit at the center of your security strategy. In this post, we show how Auth0 for AI Agents and Amazon Bedrock AgentCore work together to authenticate users, secure agent-to-agent communication, govern tool access, and enforce fine-grained authorization. Learn how to extend your existing identity infrastructure to agentic workloads and replace fragmented security with a consistent, maintainable model.

Agentic AI represents the third major platform shift in enterprise software, transforming how SaaS is built, priced, distributed, and consumed by a hybrid workforce of humans and autonomous agents. Learn how ISVs can capture this growth opportunity by building on Amazon Bedrock AgentCore for production-ready agentic deployments, making their capabilities discoverable through open protocols such as MCP and using AWS Marketplace for outcome-based pricing models that capture the measurable value agents create.

Open-weight large language models are being released by research institutions worldwide, but turning published weights into production inference services remains a challenge—especially under strict data residency requirements. This post shows how Public AI built a scalable inference platform on Amazon EKS and Intel-powered Amazon EC2 instances to serve Switzerland’s Apertus model family, and why this architecture provides a repeatable blueprint for sovereign LLM initiatives.