惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

MyScale Blog
MyScale Blog
人人都是产品经理
人人都是产品经理
云风的 BLOG
云风的 BLOG
小众软件
小众软件
F
Fortinet All Blogs
爱范儿
爱范儿
WordPress大学
WordPress大学
N
Netflix TechBlog - Medium
Recent Announcements
Recent Announcements
Google DeepMind News
Google DeepMind News
C
Check Point Blog
博客园 - 聂微东
D
Docker
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
aimingoo的专栏
aimingoo的专栏
Vercel News
Vercel News
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
A
About on SuperTechFans
博客园 - 【当耐特】
Microsoft Azure Blog
Microsoft Azure Blog
B
Blog
宝玉的分享
宝玉的分享
Jina AI
Jina AI
H
Hackread – Cybersecurity News, Data Breaches, AI and More

The New Stack | DevOps, Open Source, and Cloud Native News

Agentic development hinges on verification. For cloud-native software, that is a runtime problem. AI agents need infrastructure: Why Europe’s regional cloud strategy matters Transform your AI coding agent into a deterministic Java Spring expert WeAreDevelopers is coming to the US to give unsung developers a bigger voice Cleaner AI training data, fewer bugs: Sonar’s SonarSweep explained Observability overload is drowning engineers Google’s DiffusionGemma is 4x faster than its other Gemma models Fable 5: Guardrails and burn rate are annoying users, who say it’s still better than Opus 4.8 The Anthropic leader who built Claude Code says he ditched prompting — now he just writes loops. AWS can now mathematically prove your VMs are isolated Microsoft pulled 73 GitHub repos after malware attack — but still won’t say who’s compromised Databricks wants to kill the “email me a file” problem for AI agent skills Ramp bets forward deployed engineers can do what off-the-shelf finance AI can’t Git real: AI agents aren’t just for solo developers anymore Anthropic launches Claude Mythos/Fable 5, but you better try it soon This AI agent startup ditched Anthropic for DeepSeek — and says it’s saving millions When your data model is the bottleneck: lessons from Medium’s feature store How long before we stop reading the code? The tokenmaxxing party is over, and Revenium is mopping up How AI is solving the memory crunch it created Microsoft’s pitch to enterprises: Ditch Azure Repos for GitHub, despite its rocky reliability record Claude Code’s biggest upgrade yet ran 5 agents at once — here’s what happened Why Anthropic just doubled Claude Cowork limits at no charge For years, Apache Cassandra handed this work to your team — 6.0 takes it back “A dangerous combination”: The 2 factors that can “corrupt” AI agent workflows With Foundry, Microsoft bets the enterprise AI battle is about reliability, not capability Microsoft unlocks Visual Studio for developers left behind by its own AI AI teams now deploy 1,000 times a month. Your pipeline wasn’t built for that. Microsoft just made the agent runtime free — and kept everything around it “Whoever builds the most joyous product wins”: The agent war begins
Kiro goes mobile: AWS brings agentic coding supervision t...
Darryl K. Taft · 2026-06-18 · via The New Stack | DevOps, Open Source, and Cloud Native News

AWS has launched a native iOS app for Kiro, its AI-powered development environment, giving developers a way to monitor, steer, and approve agentic coding sessions from their phones, with no laptop required.

The app, announced at the AWS New York Summit, lets developers start sessions, review diffs, and approve changes while away from their desks. Compute runs in AWS’s cloud backend, meaning a session kicked off from a phone continues running even after the screen goes dark.

“There’s this little quote-unquote developer anxiety of like, I want to go back to my agent and do stuff,” Darko Mesaros, Principal Developer Advocate for Kiro at AWS, tells The New Stack. “Developers were asking for a way to interact with these agents.”

The release reflects a broader shift in how AWS thinks about agentic development, he notes. “As autonomous agents take on longer-running tasks across multiple repositories, the bottleneck moves from writing code to managing the agents doing the writing. Kiro Mobile is designed to keep developers in the loop without chaining them to a workstation,” Mesaros says.

“Kiro now lets you delegate, walk away, and come back to a PR,” writes Kyle Seaman, Principal Product Manager for Kiro, in a blog post about the release. “Continue a spec-driven workflow and let Kiro pick up where you left off. Or kick off an autonomous session from your phone or the web and Kiro runs independently in the cloud sandbox, inspecting files, and running tests. When Kiro needs your input, it pauses. You respond from wherever you are, pick a direction, and the work continues from where it left off.”

Three modes, one agent

The app supports the same three session modes available on Kiro Web: Chat, for quick queries; Spec, for requirements-driven workflows; and Autonomous, for fully delegated tasks. Sessions started on the web surface automatically in the mobile app, with the same identity, model preferences, and connected repositories.

Diffs render as native red and green cards with file headers, designed for readability on a small screen. PR and code review status appears on every session row. AWS built the experience natively rather than adapting its web interface for mobile. Mesaros was direct about this.

“Instead of a relatively clunky web interface, it’s a native application for the iPhone,” he says.

Spec-driven as the foundation

The iOS launch arrives alongside AWS bringing spec-driven development to Kiro Web, a workflow the company describes as central to how engineers build software internally.

Rather than prompting an agent to implement a feature and hoping for the best, spec-driven development asks the agent to first produce a requirements document, a design document, and a task list. The developer reviews and approves those artifacts before the agent writes a line of code.

“Spec-driven development is the solution to AI coding slop,” Mesaros explains. “It’s a contract between the agent and the developer. It keeps these agents from wandering off and making changes to stuff they shouldn’t necessarily be making.”

Mesaros said roughly 80% of AWS software engineers currently use Kiro, with spec-driven workflows built into that practice. Kiro automates the generation of design docs and requirements specs, reducing the manual overhead that historically made the spec-driven development difficult to sustain, he notes.

DevOps Agent gets code review

AWS is also releasing in preview a code review capability for its DevOps Agent. This feature lets the agent review and test AI-generated pull requests before they reach production. This is their acknowledgment that the volume of AI-generated code is outpacing human review capacity.

“You have so much code being generated these days, and these AI-generated pull requests are things we’re trying to sort out,” Mesaros says. “The DevOps Agent can help handle that load by outpacing human reviews.”

Availability

Kiro Mobile is available in preview on iOS 17 and later for Kiro Pro, Pro+, and Power subscribers. A waitlist is open; access is by invitation. Sign-in is supported via Google, GitHub, IAM, or AWS Builder ID. The company did not set a general availability date.

Android support is not currently planned. AWS said it made the iOS-first decision based on developer requests submitted through GitHub issues and Discord, and that it would evaluate Android based on future demand.

YOUTUBE.COM/THENEWSTACK

Tech moves fast, don't miss an episode. Subscribe to our YouTube channel to stream all our podcasts, interviews, demos, and more.

Created with Sketch.