InfoQ

99.99% of engineers aren’t building AI models. They’re building context! The future of DevOps isn't model training - it's testing and benchmarking agent context with the tools you already know. Stop testing models. Start testing context. 🗓️ Full presentation goes live on InfoQ September 30. #AIAgents #ContextAsCode #DevOps #InfoQ

#AICodingAgents can move fast. But… your architecture might not survive the ride! Speed without architectural guardrails can create new problems. Give agents the context they need to meet quality goals - and use them to explore, validate & evolve software architecture. In this #InfoQ article, Pierre Pureur, Kurt Bittner & Todd Miller share practical guidance for making AI Coding Agents work with architecture, not around it. 🔗 Read now: https://bit.ly/46M77Ef #AI #SoftwareArchitecture

An agent that generates the code should not be the only thing deciding whether that code is good enough to merge. Independent verification is one of the decisions inside the InfoQ Certified AI-Assisted Engineering Program. Over five weeks, participants build a harness against a real brownfield codebase. The work covers onboarding an agent with least-privilege permissions, adding sensors and characterization tests, separating generation from review, moving verification into CI, and measuring what changed. Participants leave with a harness they built and five weeks of their own logged results to compare against what they predicted at the start. The program is facilitated by Zichuan Xiong, who has led architecture and delivery work since 2008 and now builds agentic AI systems for software operations, and Premanand Chandrasekaran, who has spent two decades leading engineering teams with a focus on continuous delivery and internal quality. The next cohort starts October 19. Review the program and syllabus: https://bit.ly/4y1weOA #AIAssistedEngineering #SoftwareEngineering #ContinuousDelivery

Can #Claude fix your production outages? Alex Palcuie from Anthropic’s AI Reliability team shares what really happens when LLMs are used during live incident response - and why humans aren’t leaving on-call rotations anytime soon. Learn: • Where LLMs can be “superhuman” • Where they can fail dangerously • 5 real-world incident response patterns used at Anthropic 🔗 Watch now: https://bit.ly/4gpb1Zj #AI #AIOps #SRE #IncidentResponse

Google rewrote giflib - a ~3,000-line C library for handling untrusted images, in Rust with help from Gemini. The Rust version matched C output bit-for-bit across 30M+ GIFs, while 200M differential fuzzing iterations found no behavioral differences. Human review still required❗ 🔗 Details here: https://bit.ly/4yVD5tE #RustLang #MemorySafety #Security #InfoQ

#Cloudflare moved its main blog from WordPress to EmDash - its #opensource TypeScript CMS. A proxy Worker shifted traffic from 1% to 100% in a single day, with automatic fallback to WordPress. Running on Cloudflare Workers, the setup uses dual caching layers and was load-tested to 7,000 RPS. 🔗 Read more: https://bit.ly/4xJPaRz #InfoQ #SoftwareArchitecture #Caching #Migration

Vercel Labs just introduced script - an experimental compiler that turns TypeScript directly into small native executables without Node.js or V8. Early tests show fast startup times and low memory usage, though execution is currently slower than Node. 🔗 Details here: https://bit.ly/4z2rwAU #TypeScript #JavaScript #WebAssembly #Vercel #InfoQ

What bridges the gap between an AI demo and a production agent? The Agent Harness. In this #InfoQ article, Trista Pan compares two ways to build a finance assistant - using a fully managed AWS AgentCore Harness VS. a self-managed LangChain + Envoy AI Gateway setup. Key trade-offs analyzed: operational ownership, portability, and engineering effort. 🔗 Read now: https://bit.ly/3TSx0PK #AI #AIAgents #AgenticAI #SoftwareArchitecture

Generating code with AI is easy. Trusting it in production is the hard part. In this #InfoQ talk, #Roblox Engineering Manager Andrew Swerdlow explains how his team moved from Copilot autocomplete to autonomous, agentic software engineering. Learn how Roblox built “Prompt to Prod” with AI guardrails, runtime sandboxing, automated rollbacks, and new productivity metrics focused on feature velocity and agent quality. 🎬 Watch now 👉 https://bit.ly/4gxkcFW #AI #AgenticAI #SoftwareEngineering #InfoQ

New article on InfoQ🎉 Building an #AI #Agent is easy. Making it production-ready is the hard part. This article is about #AgentHarness and what it takes to move from a prototype to production #AIAgents 👇 https://lnkd.in/gcq56sEY #AI #AIEngineering #AWS #Bedrock #Agentcore #Envoy #AIGateway