# Cloud and systems Published articles for Cloud and systems. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## EC2's formally verified "isolation engine" provides mathematical assurance of virtual-machine isolation DevFeed: [EC2's formally verified "isolation engine" provides mathematical assurance of virtual-machine isolation]() Original publisher: [Read original article]() Author: Dominic Mulligan; Nathan Chong Published: 2026-06-10T15:00:00Z Content type: article Language: en Sources: [Amazon Science homepage]() Topics: [Amazon EC2](), [Rust formal verification]() Tags: [amazon-web-services-aws](), [autocorrode-library](), [automated-reasoning](), [aws-graviton5-security](), [cloud-and-systems](), [confidentiality-integrity-proofs](), [ec2-virtual-machine-security](), [formal-verification](), [formally-verified-hypervisor](), [isabelle-hol-proof-assistant](), [kernel](), [memory-safety-verification](), [nitro-isolation-engine](), [nitro-system](), [provable-security](), [rust](), [rust-formal-verification](), [security](), [security-privacy-and-abuse-prevention]() ### AI overview Amazon describes formally verifying the Nitro Isolation Engine, a separation-kernel component that enforces isolation between EC2 virtual machines. The verification uses Isabelle/HOL and is deployed as an always-on feature for Graviton5 users. ### Source excerpt Splitting the "separation kernel" off from the rest of the Nitro security system and using only a subset of the Rust programming language to code it enabled its formal verification. ## Graviton5's improved design increases speed and energy efficiency -- beyond Moore's law DevFeed: [Graviton5's improved design increases speed and energy efficiency -- beyond Moore's law]() Original publisher: [Read original article]() Author: Ali Saidi Published: 2026-06-10T15:00:00Z Content type: article Language: en Sources: [Amazon Science homepage]() Topics: [cpu](), [Amazon EC2]() Tags: [amazon-elastic-compute](), [architecture](), [cache](), [chip-design](), [cloud-and-systems](), [cpu](), [design](), [energy-efficiency](), [formal-verification](), [graviton](), [hardware](), [memory](), [performance](), [speed]() ### AI overview Amazon describes Graviton5 CPU and M9g/M9gd EC2 instances, highlighting more cores, faster memory and interconnects, improved branch prediction, and expanded cache capacity. ### Source excerpt A new chiplet architecture, custom die-to-die connectivity, and support for DDR5-8800 memory and the latest PCIe gen6 interconnects improve performance by 25% for general-purpose and agentic AI workloads. ## Bridging intent and execution in agentic systems DevFeed: [Bridging intent and execution in agentic systems]() Original publisher: [Read original article]() Author: Gaurav Gupta; Vatshank Chaturvedi Published: 2026-06-08T17:00:00Z Content type: article Language: en Sources: [Amazon Science homepage]() Topics: [Agent Harness](), [AI Agent](), [systems](), [Large Language Model](), [Terminal](), [cloud-infrastructure](), [Open Source](), [Code]() Tags: [agent](), [agentic](), [agentic-ai](), [ai](), [ai-agent](), [benchmarks](), [cloud-and-systems](), [code](), [conversational-ai](), [infrastructure](), [llm](), [software](), [tools]() ### AI overview The article argues that performance in agentic systems is fundamentally a systems problem involving the interaction between a large language model and its harness. It defines the intent-execution gap between model intentions and harness actions, shows that reducing this gap can improve benchmark results without task-specific tuning, and emphasizes the effects of tools, execution graphs, infrastructure, timeouts, and resource constraints. It also introduces Simple Strands Agent (SSA), a lightweight customizable harness, and argues that model-harness codesign is important because model families differ in tool use and feedback interpretation. ### Source excerpt The harnesses that mediate between models and tools in agentic systems are becoming their own performance bottleneck, but a few simple design principles can fix what ails them. ## How flat is replacing fat in AWS data center networks DevFeed: [How flat is replacing fat in AWS data center networks]() Original publisher: [Read original article]() Author: Giacomo Bernardi; Ratul Mahajan; Seshadhri Comandur Published: 2026-05-28T10:30:00Z Content type: article Language: en Sources: [Amazon Science homepage]() Topics: [networking](), [Network architectures]() Tags: [aws](), [aws-data-center-network-architecture](), [cloud-and-systems](), [data-center](), [fat-tree-network-replacement](), [flat-network-topology](), [network-design](), [networking](), [networks](), [quasi-random-network-topology](), [resilience](), [routing]() ### AI overview The article describes AWS's scalable flat data-center network, using quasi-random topology and ShuffleBoxes to replace conventional fat-tree designs. ### Source excerpt "Quasi-random" network topologies and new passive optical components called ShuffleBoxes make more-efficient flat networks as practical as traditional "fat-tree" networks.