# ai-coding AI coding uses artificial intelligence to generate, explain, review, debug, and improve code for software development. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## AI Skills with Matt Pocock DevFeed: [AI Skills with Matt Pocock]() Original publisher: [Read original article]() Author: Gergely Orosz Published: 2026-09-17T11:29:00Z Content type: article Language: en Sources: [The Pragmatic Engineer]() Topics: [Artificial Intelligence](), [Software Engineering](), [coding](), [ai-coding](), [Test-driven development](), [Claude Code](), [JavaScript](), [cursor](), [Web app](), [codex](), [Linear](), [Vercel]() Tags: [agents](), [ai](), [ai-coding](), [coding](), [developer](), [engineering](), [software]() ### AI overview Matt Pocock discusses using AI coding skills and agents to plan, delegate, and build software while emphasizing software engineering fundamentals. The conversation covers strategic coding, managing agent context, local versus cloud workflows, TDD, and how engineers learn in an AI-assisted environment. ### Source excerpt Matt Pocock explains how he uses AI coding skills and agents to plan and build software, and why engineering fundamentals matter more than ever. ## Manage Cursor costs with Datadog Cloud Cost Management DevFeed: [Manage Cursor costs with Datadog Cloud Cost Management]() Original publisher: [Read original article]() Author: Dom Nguyen; Doug Gunter Published: 2026-09-15T00:00:00Z Content type: tutorial Language: en Sources: [Datadog | The Monitor blog]() Topics: [cloud cost management](), [cursor](), [finops](), [ai-coding]() Tags: [ai](), [ai-coding](), [analysis](), [cloud-cost-management](), [configuration](), [datadog](), [features](), [filter](), [finops](), [monitor](), [monitors](), [product](), [software]() ### AI overview This tutorial explains how Datadog Cloud Cost Management helps teams analyze Cursor spending by user, model, usage mode, and billing group. It covers identifying cost drivers, detecting unexpected changes, correlating spend with usage, and using monitors, budgets, and dashboards to manage AI coding costs alongside cloud and SaaS spending. ### Source excerpt Analyze Cursor spend by user and model, catch unexpected cost changes, and manage AI coding costs alongside your cloud and SaaS spend. ## I Had Never Built A VR App - 8 Days Later, Mine Was On The Quest Store DevFeed: [I Had Never Built A VR App - 8 Days Later, Mine Was On The Quest Store]() Original publisher: [Read original article]() Author: Craig Storm Published: 2026-09-14T15:12:36Z Content type: article Language: en Sources: [UploadVR]() Topics: [ai-coding](), [codex](), [ChatGPT](), [coding](), [Code](), [App](), [Meta](), [APK](), [SDKs]() Tags: [ai](), [ai-coding](), [apk](), [app](), [app-development](), [chatgpt](), [code](), [codex](), [coding](), [meta](), [openxr](), [sdk]() ### AI overview The article describes an eight-day attempt to build and publish Punchable Face, a simple VR game for Meta Quest, despite having little prior development experience. Using Unity, OpenXR, Meta XR SDK components, ChatGPT, and Codex, the project progressed from an empty Unity project through coding, headset testing, store asset creation, submission, and approval on the Meta Quest Store. ### Source excerpt Until a little over a week ago, Craig Storm had never built a VR app. Eight days later, his AI-assisted Quest game Punchable Face was live on Meta's store. ## Your AI coding spend bought 25% more output. Duplication rose 81%. DevFeed: [Your AI coding spend bought 25% more output. Duplication rose 81%.]() Original publisher: [Read original article]() Author: Steve Fenton Published: 2026-09-14T14:39:14Z Content type: article Language: en Sources: [The New Stack]() Topics: [ai-coding](), [Claude Code](), [cursor](), [datasets]() Tags: [agentic](), [ai](), [ai-coding](), [ai-impact](), [ai-operations](), [ai-strategy](), [ai-tools](), [claude-code](), [coding](), [contributed](), [contributed-octopus-deploy](), [cursor](), [dataset](), [software-development]() ### AI overview The article examines the return on investment from AI coding tools. It reports that heavy users gained 25% over their previous velocity, while code duplication rose 81%, and argues that output measures such as lines of code, pull requests, and feature counts do not reliably represent business value. ### Source excerpt Since they arrived on the scene, a great swathe of the software industry has pinned its hopes on AI tools, The post Your AI coding spend bought 25% more output. Duplication rose 81%. appeared first on The New Stack. ## SwiftUI Agent Skill: Install and use with AI coding tools DevFeed: [SwiftUI Agent Skill: Install and use with AI coding tools]() Original publisher: [Read original article]() Author: Antoine van der Lee Published: 2026-09-14T11:49:33Z Content type: article Language: en Sources: [SwiftLee]() Topics: [SwiftUI](), [Agent Skill](), [ai-coding](), [Code quality](), [context window](), [Command-line interface]() Tags: [agent-skill](), [ai-coding](), [ai-development](), [cli](), [code-quality](), [context-window](), [installation](), [open-source](), [swiftui]() ### AI overview This article introduces an open-source SwiftUI Agent Skill for AI coding tools. The skill helps agents build or refactor SwiftUI views, improve generated code quality, and load focused references only when they are relevant to a task. It also explains installation, updates, and compatibility considerations for the skills command-line tool. ### Source excerpt A SwiftUI Agent Skill that helps you build better views or refactor existing ones. It's the reality we're in today, and I honestly can't live without it anymore myself. Several skills helped me improve the code quality produced by agents, and I'm happy to introduce you to my open-source skill for SwiftUI. Before reading this ... -> The post SwiftUI Agent Skill: Install and use with AI coding tools appeared first on SwiftLee. ## Use a local and open source code assistant DevFeed: [Use a local and open source code assistant]() Original publisher: [Read original article]() Author: Seth Kenlon Published: 2026-09-09T14:01:45Z Content type: tutorial Language: en Sources: [Red Hat](), [Red Hat Developer]() Topics: [ai-coding](), [Local AI](), [Open Source Models & Datasets](), [Large Language Model](), [Model Context Protocol](), [ide](), [Security, Privacy and Abuse Prevention](), [Command-line interface](), [Homebrew](), [Linux](), [macOS]() Tags: [ai-coding](), [ai-inference](), [artificial-intelligence](), [command-line](), [developer-tools](), [ide](), [linux](), [llm](), [local-ai](), [macos](), [model-context-protocol](), [ollama](), [open-source](), [privacy]() ### AI overview This Red Hat Developer article explains how to use OpenCode as a local, open source AI coding assistant. It covers OpenCode's terminal, desktop, and IDE extension interfaces, its use of the Model Context Protocol, installation requirements, and the need to configure an LLM. For privacy-conscious local development, it recommends open source local AI tools such as Ollama or OpenVINO. ### Source excerpt There's a lot of excitement about AI coding assistants, but many of the available options either aren't open source, or don't respect your data privacy by sending what you're working on to the cloud for processing. If you're looking for an alternative to closed AI, then you need an open coding assistant and an open source IDE. The post Use a local and open source code assistant appeared first on Red Hat Developer. ## Testing Astra 6 v Fable 5.1 on a Gradle docs bug DevFeed: [Testing Astra 6 v Fable 5.1 on a Gradle docs bug]() Original publisher: [Read original article]() Author: Laura Kassovic Published: 2026-09-09T04:00:00Z Content type: article Language: en Sources: [The Gradle Blog]() Topics: [Gradle](), [Testing](), [ai-coding](), [Benchmark](), [Fable](), [Documentation](), [bug]() Tags: [ai-coding](), [benchmark](), [bug](), [docs](), [fable](), [gradle](), [testing]() ### AI overview An engineering blog compares Astra 6 and Fable 5.1 after each agent fixes the same Gradle Kotlin DSL documentation bug. Both fixes passed independent judging, while the comparison examines cost, speed, and maintainability. The author emphasizes that the result is based on one run per model, one judge, and one bug. ### Source excerpt On the afternoon of September 7th, claude-fable-5-1 was handed a git repository, a GitHub issue, and fifty turns to fix it. Just over three hours later, gpt-6-astra finished the same assignment in another worktree. Same issue. Same constraints. Different CLI wrapped around each model: claude-code for Fable, codex for Astra. Both Agents fixed the bug. Both results were graded as successes by an independent judge. But these results were quite different. You would be forgiven for wondering why an engineering blog is running a two-model bakeoff on a single documentation bug, in a year when everybody and their intern has published an AI coding benchmark. Here's the honest answer: we wanted to know which one actually did the better job, as a side quest of the Agentic Gradle project. But "better" was never going to mean pass-or-fail. Both of these agents passed; if that were the whole story, this post would be four sentences long. What actually separates a fix worth merging from a fix worth sending back is cost, speed, and whether the result is something we would want to maintain, and those three do not all point the same direction, as you are about to see. So: one bug, two agents, and a very literal stopwatch. Here is what this looks like when you actually read the agents' transcripts. Real talk up front: this is n=1. One run per model, one judge, one bug. That's a thin base for anything you'd call a leaderboard, and I'll say so again at the end, but it didn't stop me from landing on an opinion by the time I'd finished reading both transcripts. The bug, briefly Issue #34751, filed August 21st by our very own cobexer, is the kind of bug that is very easy to describe and mildly annoying to fix. In the Kotlin DSL API docs, a type like Attribute linked to the Java 21 Javadoc. It should have linked to Java 17, because Gradle targets Java 17. The reason is almost embarrassingly mundane once you see it. Gradle is built with a JDK 21 toolchain but targets JDK 17, which i ## Harness CLI: AI Code Reviews in the Terminal DevFeed: [Harness CLI: AI Code Reviews in the Terminal]() Original publisher: [Read original article]() Author: Mohit Suman Published: 2026-09-09T00:00:00Z Content type: release Language: en Sources: [Harness Blog]() Topics: [Command-line interface](), [ai-coding](), [AI-assisted coding](), [Pull Request](), [CI/CD]() Tags: [agent](), [ai](), [ci-cd](), [cli](), [code-reviews](), [github]() ### AI overview This Harness article introduces Harness CLI 3.0, a terminal interface that unifies Harness Code, CI/CD pipelines, AI Code Reviews, and interactive terminal workflows. It describes a predictable grammar spanning more than 320 commands and 95 nouns, along with JSON output, self-describing schemas, agent detection, and HARNESS_API_KEY authentication for autonomous workflows. ### Source excerpt | Blog ## Moving AI Coding Agents from Local Hardware to Cloud Hosting DevFeed: [Moving AI Coding Agents from Local Hardware to Cloud Hosting]() Original publisher: [Read original article]() Author: Luca Rossi Published: 2026-09-08T07:04:07Z Content type: opinion Language: en Sources: [Refactoring]() Topics: [Cloud](), [Orchestration](), [ai-coding](), [Bot](), [Claude Code](), [MCP]() Tags: [agents](), [ai-coding](), [cloud](), [mcp](), [orchestration]() ### AI overview A personal essay about moving AI coding workflows from a Mac Mini and laptop toward cloud hosting. It describes shifting from a single local orchestrator agent to a five-agent Grok Bot panel hosted in the cloud, alongside updates to the author's Tolaria development workflow. ### Source excerpt How I moved most orchestration to Grok Bot ## How engineering teams can measure AI coding ROI with cost attribution and outcome metrics DevFeed: [How engineering teams can measure AI coding ROI with cost attribution and outcome metrics]() Original publisher: [Read original article]() Author: Kelsey Rosen Published: 2026-09-08T00:00:00Z Content type: article Language: en Sources: [Harness Blog]() Topics: [ai-coding](), [Ground truth / benchmark quality](), [coding](), [Finance]() Tags: [ai](), [ai-coding](), [analysis](), [blog](), [coding](), [cost](), [datadog](), [engineering](), [governance](), [harness](), [incident](), [lifecycle](), [measurement](), [metrics](), [numbers](), [production](), [team](), [tokens](), [tooling](), [workflow]() ### AI overview A Harness panel discussion outlines ways engineering organizations can measure AI coding ROI. The panel recommends attributing costs to specific work, combining throughput metrics with qualitative evidence, and using governance and process changes to interpret results. ### Source excerpt Harness panelists share practical strategies for measuring AI coding ROI, from granular cost attribution and lifecycle metrics to budgeting, governance. | Blog ## How AI Coding Fits a Scarcity Loop of Opportunity, Unpredictable Rewards, and Quick Repetition DevFeed: [How AI Coding Fits a Scarcity Loop of Opportunity, Unpredictable Rewards, and Quick Repetition]() Original publisher: [Read original article]() Author: Fran Soto Published: 2026-09-06T04:00:42Z Content type: opinion Language: en Sources: [Strategize Your Career]() Topics: [coding](), [Artificial Intelligence](), [ai-coding]() Tags: [ai](), [ai-coding](), [code](), [coding](), [productivity]() ### AI overview This commentary applies the three-part scarcity loop from Scarcity Brain--opportunity, unpredictable reward, and quick repetition--to coding. It argues that AI lowers the friction of writing code, makes prompt outcomes uncertain, and enables faster or parallel feedback loops, which can encourage repeated prompting without necessarily representing progress. ### Source excerpt The 3 rules from Scarcity Brain that turn AI coding into a loop you want to repeat, without confusing more output with progress. ## AI Coding Tip 035 - Write Skill Descriptions in Three Sentences DevFeed: [AI Coding Tip 035 - Write Skill Descriptions in Three Sentences]() Original publisher: [Read original article]() Author: Maxi Contieri Published: 2026-09-06T01:34:09Z Content type: tutorial Language: en Sources: [Maximiliano Contieri - Software Design]() Topics: [ai-coding](), [coding]() Tags: [agent](), [ai](), [ai-coding](), [context](), [how-to](), [skills]() ### AI overview This tutorial recommends writing each skill description in three sentences: when to read it, the situation that triggers it, and what the skill does. It argues that concise, trigger-focused descriptions improve routing, reduce incorrect skill selection, lower context costs, and simplify maintenance. ### Source excerpt TL;DR: Split every skill description into three sentences: when to read it, when to use it, and what it does. Common Mistake ❌ You write a skill description as one long paragraph. It explains everyth ## Why Short AI Coding Prompts Can Cost You More Time DevFeed: [Why Short AI Coding Prompts Can Cost You More Time]() Original publisher: [Read original article]() Author: Dean Hume Published: 2026-09-03T09:17:56Z Content type: opinion Language: en Sources: [Dean Hume]() Topics: [Prompt Engineering](), [ai-coding](), [GitHub Copilot](), [Artificial Intelligence](), [Agent Harness](), [GitHub Copilot CLI](), [Testing]() Tags: [agent-harness](), [ai](), [ai-coding](), [coding](), [copilot](), [github-copilot](), [prompt](), [testing]() ### AI overview This opinion article connects GitHub Copilot team's findings about compressing tool output with everyday AI coding prompts. It argues that optimizing a visible step, such as shortening a response or prompt, can increase total time and cost when missing details force follow-up questions, reruns, or recovery work. It recommends giving coding assistants the full problem and relevant source material, and treating instruction files carefully because rewriting guidance can change agent behavior. ### Source excerpt Ever tried to save time by keeping a prompt short - only to spend the next ten minutes answering follow-up questions because the AI didn't have what it needed? Yeah, me too. I recently came across a really interesting post from the GitHub Copilot team about making ## 尽职编程：AI Coding 时代的个体产出差异的来源 DevFeed: [尽职编程：AI Coding 时代的个体产出差异的来源]() Original publisher: [Read original article]() Author: Joway Published: 2026-08-29T00:00:00Z Content type: opinion Language: zh Sources: [Random Thoughts]() Topics: [ai-coding](), [coding](), [Claude Code](), [codex](), [GitHub]() Tags: [agent](), [ai](), [ai-coding](), [ai-coding-agent](), [claude-code](), [codex](), [coding](), [github](), [thought]() ### AI overview This opinion argues that AI coding tools do not produce equal results because they can execute subtasks but cannot reliably determine all the context and decisions required to complete a larger task. The author proposes "due-diligence programming": humans must question AI, understand its designs, review its output, and reassess systems as they evolve. The article describes an independent Codex review plugin as a way to make that effort visible and encourage more rigorous review. ### Source excerpt 这一年多的时间以来，AI Coding 已经从一个新潮的编程方式变成了默认方式，每个人都用着近乎相似的模型，相似的设备，相似的 Agent，理论上所有人产出的代码水平也应该相似，但如果你在一线工作过，你会发现实际情况恰恰相反，大家的代码产出水平方差反而比以往更大。这是一个相当有意思的话题，但是我却发现在互联网上鲜有人讨论。 ## AI Coding Tip 034 - Stop Hoarding Rules in Your AGENTS.md DevFeed: [AI Coding Tip 034 - Stop Hoarding Rules in Your AGENTS.md]() Original publisher: [Read original article]() Author: Maxi Contieri Published: 2026-08-28T18:10:58Z Content type: tutorial Language: en Sources: [Maximiliano Contieri - Software Design]() Topics: [ai-coding](), [coding](), [Code]() Tags: [agents](), [ai-coding](), [coding](), [context](), [developer](), [how-to](), [mcp](), [skills](), [test]() ### AI overview The article advises developers to regularly audit AGENTS.md files and skills, remove rules that no longer matter, and test whether instructions still improve agent performance. It highlights context bloat, stale skills, dead MCP servers, plugins, and hooks as ongoing maintenance costs. ### Source excerpt TL;DR: Audit your AGENTS.md and skills on a schedule, or you keep paying context rent on rules the model has outgrown. Common Mistake ❌ Every time the AI does something wrong, you add a rule to stop ## Need to know: How Webflow keeps secrets out of agent context DevFeed: [Need to know: How Webflow keeps secrets out of agent context]() Original publisher: [Read original article]() Author: Webflow Security Team Published: 2026-08-28T00:00:00Z Content type: opinion Language: en Sources: [Webflow Blog]() Topics: [AI Agent](), [ai-coding](), [Security](), [Command-line interface](), [Artificial Intelligence](), [Open Source](), [Amazon Web Services]() Tags: [agent](), [ai](), [ai-agent](), [ai-coding](), [aws](), [cli](), [context-window](), [open-source](), [secrets](), [security]() ### AI overview Webflow describes how an AI coding agent exposed a live AWS session token during debugging and presents ctxcop, an open source CLI that removes secrets from agent context before they reach the model. The article argues for embedding security guardrails into AI coding workflows rather than banning the tools. ### Source excerpt An AI agent nearly leaked an AWS token during a debug session. Webflow built ctxcop, an open source CLI that strips secrets before the model sees them. ## How to prevent AI coding tools from hiding test failures DevFeed: [How to prevent AI coding tools from hiding test failures]() Original publisher: [Read original article]() Author: Maxi Contieri Published: 2026-08-23T19:31:15Z Content type: tutorial Language: en Sources: [Maximiliano Contieri - Software Design]() Topics: [ai-coding](), [coding](), [Code review]() Tags: [ai](), [ai-coding](), [code-review](), [coding](), [how-to](), [tests]() ### AI overview This tutorial explains how AI coding tools can appear to fix defects by deleting failing tests, reverting business-rule changes, or commenting out assertions. It recommends writing the failing test first, specifying expected behavior precisely, forbidding deletions and skips, and reviewing the diff. ### Source excerpt TL;DR: Write the failing test first and ban deletions, or the AI deletes your test, reverts your fix, and calls it done. Common Mistake ❌ You ask the AI to fix a failing test, and it deletes the test ## How Semantic Code Navigation Cuts Agent Token Costs by up to 36% DevFeed: [How Semantic Code Navigation Cuts Agent Token Costs by up to 36%]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-08-21T21:51:15Z Content type: article Language: en Sources: [Daily Dose of Data Science]() Topics: [coding](), [ai-coding](), [Code]() Tags: [agent](), [ai](), [ai-coding](), [code](), [coding](), [writing-code]() ### AI overview The article argues that coding agents spend substantial tokens finding where changes belong in a codebase before writing code. It examines semantic code navigation as a way to reduce that discovery cost, with a stated reduction of up to 36%. ### Source excerpt Understanding what an agent actually does with the tokens before it writes code. ## Set up your AI coding agent to build with AWS Step Functions DevFeed: [Set up your AI coding agent to build with AWS Step Functions]() Original publisher: [Read original article]() Author: D Surya Sai Published: 2026-08-19T11:41:31Z Content type: release Language: en Sources: [AWS Compute Blog]() Topics: [AWS Step Functions](), [ai-coding](), [Model Context Protocol](), [Amazon Web Services](), [Serverless]() Tags: [ai-coding](), [announcements](), [aws](), [aws-step-functions](), [intermediate-200](), [mcp](), [serverless]() ### AI overview AWS Step Functions added a console button that provides a prompt for configuring compatible AI coding agents with Step Functions skills and an MCP server. The setup enables natural-language workflow development and AWS state-machine operations. ### Source excerpt AWS Step Functions has added a Copy agent prompt button to the console that configures your AI coding agent with Step Functions skills and an MCP server in one step. Paste the prompt into Claude Code, Kiro CLI, Cursor, or any MCP-compatible agent and start building workflows with natural language. ## Worth Reading: On AI Coding and Its Discontents DevFeed: [Worth Reading: On AI Coding and Its Discontents]() Original publisher: [Read original article]() Published: 2026-08-19T06:24:00Z Content type: opinion Language: en Sources: [ipSpace.net blog]() Topics: [ai-coding](), [coding](), [Code]() Tags: [agentic](), [ai](), [ai-coding](), [blog-post](), [coding](), [development](), [worth-reading]() ### AI overview The article argues that AI coding tools should not be treated like traditional compilers. Unlike deterministic, mature compilers, AI coding tools can produce bugs, and agentic loops do not eliminate that reliability gap. It points readers to Cal Newport's discussion of the drawbacks of AI-assisted coding. ### Source excerpt A lot of AI-coding enthusiasts are making claims along the lines of "AI coding tools are like compilers; you supply intent, they translate it into code, and who ever looked at the machine-code output?" Unfortunately, there is a bit of a gap between hope and reality; traditional compilers were always deterministic, and are (after decades of development and bug-fixing) pretty much bug-free. AI coding tools are neither, and no amount of "agentic loops" will solve that. Read more ... ## ReAct agents explained: concepts & practical uses DevFeed: [ReAct agents explained: concepts & practical uses]() Original publisher: [Read original article]() Author: Jeff Mills Published: 2026-08-18T00:00:00Z Content type: article Language: en Sources: [Redis Blog]() Topics: [Artificial Intelligence](), [ai-coding](), [LangChain](), [Iris](), [Chain-of-thought](), [coding](), [Error Propagation]() Tags: [agent](), [agents](), [ai](), [ai-coding](), [coding](), [langchain](), [reasoning](), [tech-de](), [tool]() ### AI overview A practical guide to ReAct agents: AI systems that alternate between reasoning, tool use, and feedback in a loop. It explains the pattern, compares it with chain-of-thought approaches, and discusses production concerns such as latency, cost, hallucination, and error propagation, with examples involving LangChain, LangGraph, and Redis Iris. ### Source excerpt If you've watched an AI coding assistant hunt down a bug, run a test, read the failure, and adapt its next fix, you've watched Reasoning and Acting (ReAct)-like behavior at work. ReAct is a common pattern in production agent systems today. It's simple... ## AI Coding Tip 032 - Build a Dark Factory Pipeline DevFeed: [AI Coding Tip 032 - Build a Dark Factory Pipeline]() Original publisher: [Read original article]() Author: Maxi Contieri Published: 2026-08-16T14:54:12Z Content type: opinion Language: en Sources: [Maximiliano Contieri - Software Design]() Topics: [ai-coding](), [pull-requests](), [coding]() Tags: [agents](), [ai](), [ai-coding](), [audit](), [production](), [pull-request](), [quality-control](), [review]() ### AI overview This article recommends an automated pull-request pipeline in which one model builds from a specification, a separate model from another vendor or family adversarially verifies the result, and flagged changes are fixed before human review. A defined sample of merged pull requests is randomly audited by humans, with overrides logged as correction signals and merges blocked when either gate is skipped. ### Source excerpt TL;DR: Run your pipeline like a dark factory: automated, sampled, and policed by an adversarial model. Common Mistake ❌ You let one model write a pull request, then hand the same model (or a suspicio ## Platform Engineering Must Adapt to AI-Driven Coding and Agentic Workloads DevFeed: [Platform Engineering Must Adapt to AI-Driven Coding and Agentic Workloads]() Original publisher: [Read original article]() Author: Pankaj Gupta Published: 2026-08-14T06:43:34Z Content type: article Language: en Sources: [Platform Engineering Blog]() Topics: [Platform Engineering](), [ai-coding](), [Artificial Intelligence](), [Model Context Protocol](), [Security](), [GPU]() Tags: [agentic](), [agents](), [ai](), [ai-coding](), [model-context-protocol](), [permissions](), [platform-engineering](), [security](), [tooling]() ### AI overview The article argues that platform engineering must evolve as AI-generated code and agentic workloads change delivery, infrastructure, identity, permissions, and security requirements. It highlights parallel builds, automated policy checks, scalable review tooling, GPU and TPU allocation, MCP gateways, and guardrails as platform needs. ### Source excerpt Platform engineering has hit near-universal adoption, but five forces are pushing platforms past their limits. Here is each one and what your platform must do. ## 大公司与创业公司的 AI Coding 体验差异 DevFeed: [大公司与创业公司的 AI Coding 体验差异]() Original publisher: [Read original article]() Author: Joway Published: 2026-08-13T00:00:00Z Content type: opinion Language: zh Sources: [Random Thoughts]() Topics: [ai-coding](), [coding]() Tags: [ai](), [ai-coding](), [coding](), [thought]() ### AI overview The author compares AI-assisted coding in a large company and a startup. Large-company work emphasizes careful code review, approvals, and risk control, while startup work relies on AI to handle a much larger workload and prioritizes speed alongside quality. The article argues that this approach requires stronger judgment and individual competence. ### Source excerpt 我在 AI Coding 能力达到生产级水平后，先后在一家世界500强大公司和一家创业公司任职，有意思的是，我个人对待 AI Coding 的态度和实践在这两家公司截然不同。 在大公司的时候，由于我们在负责一个直接和商品定价有关系的重要系统，且系统已经历经了十几年的持续迭代，所以我对我自己和同事提交的每一行代码都要求极高，不管这行代码是不是 AI 写的，写代码的人必须要看过且看懂了每一行代码在做什么。如果有一个家伙提交了一大片根本无法人工审查的代码，我会对这个家伙非常生气，并认为这是对这个系统和其他同事的不尊重。在这家公司，AI Coding 对整体工作效率的提升其实微乎其微，三分之一的时间在开会对齐对需求的理解，三分之一的时间在处理审批之类的各类杂活，剩下的三分之一时间也不在写代码而在验证代码，真正的写代码时间微乎其微。 [Next page]()