awsJul 6, 2026

AWS Weekly Roundup: Claude Sonnet 5 on AWS, Amazon WorkSpaces for AI agents, AWS service availability updates, and more (July 6, 2026) | Amazon Web Services (opens in new tab)

The July 6, 2026 AWS roundup highlights new infrastructure, AI, observability, and developer productivity capabilities. Major announcements include Claude Sonnet 5 on AWS, generally available WorkSpaces for AI agents, faster SageMaker inference scaling, and log-query alarms in CloudWatch. It also details AWS service lifecycle changes and upcoming community events. ## Featured AWS Launches - **Claude Sonnet 5 on AWS** - Anthropic’s latest Sonnet model is available for coding, agentic workflows, and professional tasks. - It can navigate large codebases, use tools accurately, and preserve state across long-running tasks. - **Amazon WorkSpaces for AI agents** - AI agents can securely operate desktop applications in managed WorkSpaces environments. - Organizations can use existing applications without modernization or custom integrations. - **OpenSearch log analytics optimization** - A new engine provides up to four times better price-performance in internal benchmarks. - It combines log aggregation with OpenSearch’s full-text search capabilities. - **Faster SageMaker AI inference scaling** - Container image caching can reduce generative AI scale-out time by up to half. - SageMaker supports up to two times faster end-to-end scaling during demand increases. - **CloudWatch alarms from log queries** - Users can create alarms directly from log query results and define thresholds in one workflow. - This removes the need to create metric filters or custom metrics first. ## Additional Infrastructure and Developer Updates - **EC2 C9g and C9gd instances** - Powered by AWS Graviton5 processors. - Offer up to 25% more compute performance than Graviton4 instances, five times more cache, faster memory, and optional local NVMe storage. - **CloudFormation Express mode** - Provides deployment confirmation within seconds. - Helps developers and AI agents iterate more quickly, at no additional cost in commercial Regions. - **Amazon EKS version rollbacks** - Kubernetes upgrades can be reversed within seven days. - Rollbacks avoid rebuilding clusters and reduce the risk of failed upgrades. - **ACME support in AWS Certificate Manager** - Automates issuance and renewal of public TLS certificates using the standard ACME protocol. ## AWS Service Availability Changes AWS updated its lifecycle guidance on June 30, 2026, including alternatives and migration support. - **Moving to maintenance for new customers from July 30** - Amazon Bedrock Agents becomes Bedrock Agents Classic. - Amazon Cognito Sync, Amazon Kendra, Amazon Q Business, Simple AD, and several other services and features will no longer accept new customers. - A number of SageMaker AI features are affected, including Clarify, Debugger, Ground Truth, Model Monitor, and Studio Lab. - AWS IoT Device Defender Detect changes on August 31, 2026. - **Entering sunset** - Amazon WorkSpaces PCoIP and Pool. - AWS Managed Services Advanced. - AWS re:Post Private. - SageMaker AI Profiler. - **End of support** - Amazon Chime SDK Carrier Voice Focus. - SageMaker AI Ground Truth Plus. ## Upcoming AWS Events - AWS Summits will take place throughout the second half of 2026. - AWS Community Day Belo Horizonte is scheduled for August 22. - The AWS Builder Center offers community discussions, technical content, and information about upcoming virtual and in-person events. Organizations using affected AWS services should review the relevant lifecycle documentation and contact AWS Support to plan migrations before availability or support deadlines.

claude-sonnetk8sawsamazon-sagemaker+4

githubApr 17, 2026

Building an emoji list generator with the GitHub Copilot CLI (opens in new tab)

Cassidy Williams describes building an AI-powered emoji list generator during GitHub’s Rubber Duck Thursdays livestream. The terminal application converts bullet points into relevant emojis, then copies the formatted Markdown list to the clipboard with a keyboard shortcut. The project demonstrates how GitHub Copilot CLI and SDK can quickly turn a small idea into a functional open-source tool. ## The Emoji List Generator - Runs directly in the terminal. - Accepts pasted or typed bullet points. - Uses AI to replace each bullet with a relevant emoji. - Generates the result when the user presses `Ctrl + S`. - Copies the completed list to the clipboard. - Exits with `Ctrl + C`. ## Technologies Used - `@opentui/core` provides the terminal user interface. - `@github/copilot-sdk` supplies the AI functionality. - `clipboardy` handles clipboard access. ## Building the Project with Copilot CLI - Development began in Copilot CLI’s plan mode using Claude Sonnet 4.6. - A natural-language prompt described the desired Markdown emoji generator and requested integration with the Copilot SDK. - Copilot asked clarifying questions about the technology stack and libraries. - It then produced a `plan.md` file for review. - The implementation was completed with Claude Opus 4.7 only a few minutes later. ## Copilot CLI Features Demonstrated The livestream project combined several Copilot CLI capabilities: - Plan mode for outlining the implementation. - Autopilot mode for carrying out development tasks. - A multi-model workflow using different Claude models. - The `allow-all` tools flag for permissive tool access. - The GitHub MCP server for GitHub-related integrations. The finished Emoji List Generator is available as a free, open-source project, alongside documentation for the GitHub Copilot CLI and SDK.

claude-sonnetgithub-copilot-cliclaude-opusgithub-copilot-sdk+4

awsFeb 23, 2026

AWS Weekly Roundup: Claude Sonnet 4.6 in Amazon Bedrock, Kiro in GovCloud Regions, new Agent Plugins, and more (February 23, 2026) | Amazon Web Services (opens in new tab)

AWS’s February 23, 2026 roundup highlights continued investment in AI-assisted development, cloud infrastructure, and production-grade agents. Major launches include Claude Sonnet 4.6 in Amazon Bedrock, Kiro for GovCloud, customizable SageMaker deployments for Nova models, and new EC2 and Aurora capabilities. The post also points developers toward agent tooling, operational best practices, community resources, and upcoming events. ## Developer Conferences and AI Collaboration - AWS teams discussed “renascent software,” where humans and AI work together as co-developers through Kiro. - Developer Week sessions focused on: - Agent memory - Multi-agent architectures - Meta-tooling - Hooks - Production deployment of AI agents - At dev/nexus in Atlanta, AWS speakers will cover AI agents with Spring and MCP, along with AI-assisted Java modernization. ## Major AWS Launches - **Claude Sonnet 4.6 in Amazon Bedrock** - Provides near-Opus 4.6 intelligence at lower cost. - Targets coding, agent workloads, and professional knowledge work. - Designed for fast, high-quality task completion at scale. - **Amazon EC2 Hpc8a instances** - Powered by 5th Gen AMD EPYC processors. - Deliver up to 40% higher performance, increased memory bandwidth, and 300 Gbps Elastic Fabric Adapter networking. - Intended for simulations, engineering, and tightly coupled HPC workloads. - **Custom Amazon Nova models with SageMaker Inference** - Supports configuration of instance types, auto-scaling policies, and concurrency. - Enables deployments to be tuned for specific performance and cost requirements. - **Nested virtualization on EC2** - Allows KVM or Hyper-V virtual machines to run inside virtual EC2 instances. - Supports mobile emulators, automotive hardware simulation, and Windows Subsystem for Linux environments. - **Aurora encryption by default** - New database clusters automatically use server-side encryption with AWS-owned keys. - Encryption is transparent, fully managed, and has no additional cost or performance impact. - **Kiro in AWS GovCloud** - Brings Kiro’s agentic development capabilities to teams working on government missions. - Supports regulated environments requiring stringent security controls. ## Agent Tools and Operational Reliability - AWS introduced open-source **Agent Plugins for AWS** that add AWS-specific skills to coding agents. - The `deploy-on-aws` plugin can generate: - Architecture recommendations - Cost estimates - Infrastructure-as-code - AWS also highlighted automated reasoning research led by Byron Cook, applying formal verification techniques to AI-generated code and critical agent decisions. - Recommended practices for AWS DevOps Agent focus on configuring Agent Spaces to balance broad investigation capabilities with operational efficiency. - AWS reports that DevOps Agent has handled thousands of escalations and achieved an estimated root-cause identification rate above 86% within Amazon. ## Community Projects and Resources - Community content includes: - A practical guide to AWS for developers entering their first job. - An AI agent that automates job searching. - A Kiro Power integrating 25 MCP tools, 10 steering guides, and structured development guidance. - AWS encourages developers to use the AWS Builder Center to exchange knowledge and discover community content. ## Upcoming Events and Hackathons - 2026 AWS Summits are scheduled for Paris, London, and Bengaluru. - The six-week Amazon Nova AI Hackathon runs through March 16, with $40,000 in prizes across areas such as agentic AI, multimodal applications, UI automation, and voice. - Upcoming AWS Community Days include events in Ahmedabad, Tokyo, Chennai, Slovakia, and Pune. Developers interested in AI-assisted coding, agent operations, or high-performance cloud workloads should explore the new Bedrock, Kiro, SageMaker, and Agent Plugin capabilities, while using AWS events and community forums for practical guidance.

claude-sonnetai-agentgen-aiamazon-bedrock+4

figmaJun 9, 2025

8 Essential Tips for Using Figma Make | Figma Blog (opens in new tab)

Figma Make works best when users provide clear context, prepare clean design files, and refine complex projects incrementally. Detailed initial prompts reduce revisions, while organized Figma layers and Auto Layout help designs translate into functional prototypes. For ambitious builds, breaking work into focused prompts and separate code folders improves control, maintainability, and debugging. ## Provide Detailed Initial Prompts - Include: - The task Figma Make should perform - Product or flow context - Essential design elements - Expected interactions and behaviors - Device, layout, and visual constraints - Front-loading requirements helps produce a stronger first version with fewer follow-up prompts. - Use precise, measurable instructions instead of vague requests: - “Move this element down 20 pixels” - “Add 16px of space between these buttons” - If repeated adjustments are not working, restart with a new file and use lessons from the first attempt. - Effective project prompts can include an overview, platform, purpose, features, visual direction, technical details, and an explicit first implementation step. ## Clean Up Figma Files Before Importing Them - Figma Make can either create new designs or turn existing Figma frames into interactive prototypes. - Before copying a frame into Figma Make: - Organize the file - Apply appropriate constraints - Use Auto Layout correctly - Name layers according to their purpose - Figma tools such as Suggest Auto Layout and Rename Layers with AI, along with plugins like Clean Document, can help prepare files. - If the result is too large or not responsive, use prompts such as: - “Scale this to the size of my screen and make it responsive.” - “Keep this mobile-sized.” - A well-structured Auto Layout design can enable complex interactions from a single prompt, such as making a CD spin when a music player starts. ## Build Complex Projects Incrementally - Use a detailed first prompt to establish the overall foundation, then make smaller, focused changes. - Smaller requests allow the model to respond more precisely and reduce the risk of unwanted changes elsewhere. - Incremental prompting is useful for: - Building complex interfaces - Creating multi-page flows - Adding individual features - Maintaining the intended visual direction - Ask Figma Make to place separate elements in separate code folders to improve organization, maintainability, and error isolation. - Large projects may require many prompts; one financial dashboard and onboarding flow took more than 150 focused iterations. - Example follow-ups included adding journal post-its, inserting a detailed finance table, and adding a currency-selection checkbox. - Separating 3D landmarks into individual coded files similarly makes it easier to refine components without affecting the wider environment. Use Figma Make as an iterative design-and-development tool: prepare the source file carefully, describe the desired result precisely, and make complex changes one manageable step at a time.

claude-sonnetfigmaprototypinggen-ai+4