24  Sources

• [1] How to (not) use Agents for a Large Scale Migration — DoltHub Team | DoltHub Blog | 2025-11-14
• [2] As an Experienced LLM User, I Actually Don’t Use Generative LLMs Often — Max Woolf | Max Woolf | 2025-05-05
• [3] Stopped Creating package.json Scripts — Ben Houston | Ben Houston’s Blog | 2026-01-20
• [4] Claude Skills are awesome, maybe a bigger deal than MCP — Simon Willison’s Weblog | 2026-01
• [5] Apple Xcode Claude Agent Sdk — Anthropic | 2026-02-03
• [6] Continue Configuration — Continue.dev Docs | 2026-04
• [7] 2025: Replit in Review — Replit | Replit Blog | 2025-12-31
• [8] Building Spookseek AR on Replit: How a Designer Shipped an AR Ghost Hunting Game in a Week — Replit | Replit Blog | 2026-02-27
• [9] What is Cline? - Cline — Cline Docs | 2026-05
• [10] Build with Google Antigravity: Our New Agentic Development Platform — Google | Google Developers Blog | 2026-04
• [11] Reviewing audit logs for GitHub Copilot - GitHub Enterprise Cloud Docs — GitHub | 2026-05
• [12] FAQ - Ollama — docs.ollama.com | 2026-05
• [13] Ollama — aider.chat | 2026-04
• [14] Fragments: February 9 — Martin Fowler | Martin Fowler | 2026-02-09
• [15] Agentic Harness: OpenClaw, Claude Code, and More — Solomon Christ AI | Solomon Christ AI | 2026-04
• [16] The importance of Agent Harness in 2026 — Philipp Schmid | philschmid | 2026-01-05
• [17] 2025 LLM Year in Review — karpathy | Andrej Karpathy | 2025-12-20
• [18] Use Claude Code features in the SDK - Claude Code Docs — code.claude.com | 2026-05
• [19] Claude Code settings - Claude Code Docs — code.claude.com | 2026-05
• [20] Inside Claude Code: An Architecture Deep Dive — Zain Hasan | Zain Hasan Blog | 2026-04
• [21] Gemini CLI for the Enterprise — google-gemini.github.io | 2026-05
• [22] Gemini CLI Configuration — google-gemini.github.io | 2026-05
• [23] 2025-08-07 — code.claude.com | 2026-04
• [24] Work with sessions - Claude Code Docs — code.claude.com | 2026-04
• [25] Claude Code customization guide: CLAUDE.md, skills, subagents explained — Alex | alexop.dev | 2025-12-21
• [26] Cody Context Filters — Cody Docs | 2026-04
• [27] Pi: The Minimal Agent Within OpenClaw — Armin Ronacher | Armin Ronacher (lucumr) | 2026-01-31
• [28] Quick Codex: a lightweight workflow layer for Codex CLI — dev.to | 2026-04
• [29] Building Effective Agents — Anthropic | 2024-12-19
• [30] Puzzmo Tech Stack: 2025 — Puzzmo Team | Puzzmo Blog | 2025-12-09
• [31] Building My First Claude Code Plugin — Alex | alexop.dev | 2025-11-08
• [32] 5 Claude Code Agentic Workflow Patterns — MindStudio | MindStudio Blog | 2026-04
• [33] OpenCode Rules — OpenCode Docs | 2026-04
• [34] Amp Owners Manual — Amp Docs | 2026-04
• [35] Continue Rules — Continue.dev Docs | 2026-04
• [36] CLAUDE.md: Building Persistent Memory for AI Coding Agents — Eugene Oleinik | DEV Community | 2026-04
• [37] Writing a good CLAUDE.md | HumanLayer Blog — HumanLayer | 2026-01
• [38] Writing a Good AGENTS.md — Philipp Schmid | philschmid | 2026-02-24
• [39] Understanding Claude Code’s Full Stack: MCP, Skills, Subagents, and Hooks Explained — Alex | alexop.dev | 2025-11-09
• [40] Gemini CLI Tips & Tricks — Addy Osmani | Addy Osmani’s Substack | 2025-10-21
• [41] Copilot Custom Instructions — GitHub Copilot Docs | 2026-04
• [42] Steering - IDE - Docs - Kiro — kiro.dev | 2026-05
• [43] Windsurf Memories and Rules — Windsurf Docs | 2026-04
• [44] Stop Bloating Your CLAUDE.md: Progressive Disclosure for AI Coding Tools — Alex | alexop.dev | 2026-01-18
• [45] Skill Issue: Harness Engineering for Coding Agents — HumanLayer | HumanLayer Blog | 2026-04
• [46] Building Agent Memory That Survives Between Sessions — Pere Villega | Pere Villega | 2026-04
• [47] Building an internal agent: Progressive disclosure and handling large files — Will Larson | Lethain (Will Larson) | 2025-12-26
• [48] How Claude remembers your project - Claude Code Docs — code.claude.com | 2026-05
• [49] How to Write .cursorrules That Actually Work — dev.to | 2026-04
• [50] 8 Tips for Writing Agent Skills — Philipp Schmid | philschmid | 2026-04-13
• [51] Practical Guide to Evaluating and Testing Agent Skills — Philipp Schmid | philschmid | 2026-03-04
• [52] Aider YAML Config — Aider Docs | 2026-04
• [53] Claude Code Hook Examples | Developing with AI Tools | Steve Kinney — Steve Kinney | 2026-01
• [54] Your .cursorrules Are Just Suggestions – Here’s What Actually Gets Enforced — dev.to | 2026-04
• [55] AI Agent Memory Management — When Markdown Files Are All You Need? — Yaohua Chen | DEV Community | 2026-04
• [56] Claude Diary — Lance Martin | Lance Martin | 2025-12-01
• [57] ADR in Code: Architecture Compliance with AI Code Reviews — Shing Lyu | Shing Lyu Blog | 2026-04
• [58] AI Generated Architecture Decision Records — Adolfi | Adolfi.dev | 2026-04
• [59] Web Interface Guidelines now available as an agent command — John Phamous | Vercel Blog | 2026-01-12
• [60] What is BMAD-METHOD? A Simple Guide — visrow | Medium | 2026-04
• [61] The Code Agent Orchestra — Addy Osmani | Addy Osmani’s Substack | 2026-04
• [62] Building a C compiler with a team of parallel Claudes — Anthropic | Anthropic Engineering Blog | 2026-04
• [63] App Screenshots: An AI Coding Agent Skill for Visual Documentation — Alex | alexop.dev | 2026-03-27
• [64] AGENTS.md outperforms skills in our agent evals — Jude Gao | Vercel Blog | 2026-01-27
• [65] Cody Prompts and Commands — Cody Docs | 2026-04
• [66] Extend Claude with skills - Claude Code Docs — docs.claude.com | 2026-05
• [67] Introducing skills, the open agent skills ecosystem — Andrew Qu | Vercel Blog | 2026-01-20
• [68] Manage agent skills with GitHub CLI — Allison | GitHub Changelog | 2026-04-16
• [69] How I Use Claude Code for Doing SEO Audits — Alex | alexop.dev | 2025-06-26
• [70] Skills Night: 69,000+ ways agents are getting smarter — Andrew Qu | Vercel Blog | 2026-02-20
• [71] The Pulse: Cloudflare rewrites Next.js as AI rewrites commercial open source — Gergely Orosz | The Pragmatic Engineer | 2026-03-05
• [72] Same Framework, Different Engine: Porting AI Coding Workflows from Claude Code to Codex CLI — dev.to | 2026-04
• [73] Why Garry Tans Claude Code setup has gotten so much love and hate — TechCrunch | gstack | 2026-04
• [74] Rethinking RAG Architecture for the Age of Agents — Jason Liu | Jason Liu | 2025-09-11
• [75] Why You Don’t Need the Nuxt MCP When You Use Claude Code — Alex | alexop.dev | 2025-12-31
• [76] Why Cognition does not use multi-agent systems — Jason Liu | Jason Liu | 2025-09-11
• [77] OpenClaw: I Switched My Agent Stack from Claude to OpenAI Codex — mager | mager.co | 2026-04
• [78] The Complete OpenClaw Guide: How We Run an AI Agent in Production — Context Studios | Context Studios | 2026-04
• [79] Can We Close the Loop in 2026? — Philipp Schmid | philschmid | 2026-02-17
• [80] Introducing Agent 3: Our Most Autonomous Agent Yet — Replit | Replit Blog | 2025-09-10
• [81] Judgment and creativity are all you need. — Will Larson | Lethain (Will Larson) | 2026-03-11
• [82] The software industrial revolution: AI agents for enterprise development — Sourcegraph | Sourcegraph Blog | 2025-01-29
• [83] The New Skill in AI is Not Prompting, It’s Context Engineering — Philipp Schmid | philschmid | 2025-06-30
• [84] Context Engineering for AI Agents: Lessons from Building Manus — Manus Team | Manus Blog | 2026-04
• [85] Context Engineering for Coding Agents — Martin Fowler | Martin Fowler | 2026-02-05
• [86] Windsurf Context Awareness — Windsurf Docs | 2026-04
• [87] Anthropic — aider.chat | 2026-04
• [88] Installing Cody in VS Code - Sourcegraph docs — Sourcegraph Docs | 2026-04
• [89] Cody Chat — Cody Docs | 2026-04
• [90] Aider Tips and Best Practices — Aider Docs | 2026-04
• [91] In-chat commands — aider.chat | 2026-04
• [92] MCP governance for Q Developer — docs.aws.amazon.com | 2026-04
• [93] Deep Search goes GA, now with role-based permissions — Devon Pratt | Sourcegraph Blog | 2025-10-22
• [94] Sandbox SDK adds file permission control — Luke Phillips-Sheard | Vercel Blog | 2026-04
• [95] Cursor Docs — Cursor Docs | 2026-04
• [96] Checkpoints - Cline — Cline Docs | 2026-04
• [97] OpenCode: The Open Source AI Coding Agent Reviewed — dev.to | 2026-04
• [98] Tasks - Cline — Cline Docs | 2026-04
• [99] Context Engineering for AI Agents: Part 2 — Philipp Schmid | philschmid | 2025-12-04
• [100] Context Anchoring — Martin Fowler | Martin Fowler | 2026-03-17
• [101] Context Engineering: Bringing Engineering Discipline to Prompts — Addy Osmani | Addy Osmani’s Substack | 2025-07-13
• [102] Is the IDE dead? — Addy Osmani | Addy Osmani’s Substack | 2026-03-20
• [103] Why I Stopped Using nbdev — Hamel Husain | Hamel Husain | 2026-01-18
• [104] Enter flow state with auto-edit — Sourcegraph | Sourcegraph Blog | 2025-01-29
• [105] Introducing Plan Mode: A safer way to vibe code — Replit | Replit Blog | 2025-09-03
• [106] Auto-Approving Actions | Roo Code Documentation — docs.roocode.com | 2026-05
• [107] Humans and Agents in Software Engineering Loops — Martin Fowler | Martin Fowler | 2026-03-04
• [108] Improving DoltLite — Tim Sehn | DoltHub Blog | 2026-04-09
• [109] Some thoughts on LLMs and Software Development — Martin Fowler | Martin Fowler | 2025-08-28
• [110] Introducing Queue: A smarter way to work with Agent — Replit | Replit Blog | 2025-07-22
• [111] Build a personal organization command center with GitHub Copilot CLI — Cassidy Williams | GitHub Blog | 2026-04-15
• [112] How Replit Secures AI-Generated Code [white paper] — Replit | Replit Blog | 2026-01-15
• [113] My LLM coding workflow going into 2026 — Addy Osmani | Addy Osmani’s Substack | 2025-12-18
• [114] Embracing the parallel coding agent lifestyle — Simon Willison’s Weblog | 2026-01
• [115] Spec-driven development with AI: Get started with a new open source toolkit — github.blog | 2026-04
• [116] Vibe coding is not the same as AI-Assisted engineering. — Addy Osmani | Addy Osmani’s Substack | 2025-08-30
• [117] 6 Best Spec-Driven Development Tools for AI Coding in 2026 — Augment Code | BMAD Method Docs | 2026-04
• [118] Fragments: December 16 — Martin Fowler | Martin Fowler | 2025-12-16
• [119] We Rewrote JSONata with AI in a Day, Saved $500K/Year — Simon Willison | Simon Willison’s Weblog | 2026-03-27
• [120] Adaptive - Windsurf Docs — docs.windsurf.com | 2026-05
• [121] How to write a good spec for AI agents — Addy Osmani | Addy Osmani’s Substack | 2026-01-19
• [122] GET SHIT DONE: Meta-prompting and Spec-driven Development — Agent Native Dev | GSD Method | 2026-04
• [123] BMAD: The Agile Framework That Makes AI Actually Predictable — extinctsion | BMAD Method Docs | 2026-04
• [124] Applied BMAD: Reclaiming Control in AI Development — Benny Cheung | BMAD Method Docs | 2026-04
• [125] Design-First Collaboration — Martin Fowler | Martin Fowler | 2026-03-03
• [126] Best Practices for Using PRDs with Claude Code in 2026 — ChatPRD | ChatPRD | 2026-04
• [127] Common workflows - Claude Code Docs — docs.claude.com | 2026-05
• [128] Deep Planning - Cline — Cline Docs | 2026-05
• [129] Spec-Driven Development with Claude Code in Action — Alex | alexop.dev | 2026-02-01
• [130] Chat modes — aider.chat | 2026-05
• [131] Using PLANS.md for multi-hour problem solving — cookbook.openai.com | 2026-05
• [132] Claude Code Gotchas | DoltHub Blog — DoltHub Blog | 2026-01
• [133] Effective harnesses for long-running agents — Anthropic Engineering | Anthropic | 2026-04
• [134] How Good Is AI at Coding React (Really)? — Addy Osmani | Addy Osmani’s Substack | 2025-12-29
• [135] The AI Productivity Myth: Developing with AI Is 19% Slower, Not Faster — Nati Shalom | Medium | 2026-04
• [136] Research, Review, Rebuild: Intelligent Modernisation with MCP and Strategic Prompting — Martin Fowler | Martin Fowler | 2025-08-27
• [137] A grounded take on agentic coding for production environments — [email protected] (Ivan Velichko) | iximiuz (Ivan) | 2026-01-19
• [138] Long-running Agentic Work with Beads — Dustin Brown | DoltHub Blog | 2026-01-27
• [139] Single vs Multi-Agent System? — Philipp Schmid | philschmid | 2025-06-20
• [140] Run multiple agents at once with /fleet in Copilot CLI — Matt Nigh | GitHub Blog | 2026-04-01
• [141] From Tasks to Swarms: Agent Teams in Claude Code — Alex | alexop.dev | 2026-02-08
• [142] Separating code reasoning and editing — Paul Gauthier | Aider Blog | 2024-09-26
• [143] Enabling Agent 3 to Self-Test at Scale with REPL-Based Verification — Replit | Replit Blog | 2025-12-15
• [144] Safe ways to let your coding agent work autonomously — Eric Ma | DEV Community | 2026-04
• [145] Quick but worthwhile links — Martin Fowler | Martin Fowler | 2025-08-07
• [146] Agents: Inner Loop vs Outer Loop — Philipp Schmid | philschmid | 2026-02-20
• [147] Super Claude Code: How structured prompts turn Claude Code into a development partner — PromptLayer | SuperClaude | 2026-04
• [148] Welcome to the BMad Method — BMAD Method Docs | 2026-04
• [149] What Actually Is Claude Code’s Plan Mode? — Armin Ronacher | Armin Ronacher (lucumr) | 2025-12-17
• [150] The Prompt Engineering Playbook for Programmers — Addy Osmani | Addy Osmani’s Substack | 2025-05-27
• [151] Aider Coding Conventions — Aider Docs | 2026-04
• [152] OpenCode Agents — OpenCode Docs | 2026-04
• [153] The Rise of Subagents — Philipp Schmid | philschmid | 2025-09-15
• [154] — Malte Ubl | Vercel Blog | 2025-08-20
• [155] Vercel Agent code reviews now follow your code guidelines — Marcos Grappeggia | Vercel Blog | 2026-01-06
• [156] Encoding Team Standards — Martin Fowler | Martin Fowler | 2026-03-31
• [157] Writing Visualizations with Remotion — Will Larson | Lethain (Will Larson) | 2026-01-25
• [158] Claude.md: Best Practices for Optimizing with Prompt Learning — Arize AI | 2026-01
• [159] Copilot Best Practices — GitHub Copilot Docs | 2026-04
• [160] Understanding Spec-Driven-Development: Kiro, spec-kit, and Tessl — Martin Fowler | Martin Fowler | 2025-10-15
• [161] spec-kit/spec-driven.md at main · github/spec-kit — GitHub | 2026-04
• [162] AWS Transform custom: AI-driven Java modernization to reduce tech debt — Dinesh Prabakaran | AWS DevOps Blog | 2026-02-05
• [163] OpenSpec — A lightweight spec‑driven framework — OpenSpec | 2026-04
• [164] GitHub - Fission-AI/OpenSpec: Spec-driven development (SDD) for AI coding assistants. — GitHub | 2026-04
• [165] Building an AI QA Engineer with Claude Code and Playwright MCP — Alex | alexop.dev | 2025-12-13
• [166] An AI agent coding skeptic tries AI agent coding, in excessive detail — Max Woolf | Max Woolf | 2026-02-27
• [167] GStack Tutorial: Garry Tan Claude Code Setup — SitePoint | gstack | 2026-04
• [168] Model Context Protocol (MCP) an overview — Philipp Schmid | philschmid | 2025-04-03
• [169] Model Context Protocol — Anthropic | 2024-12-02
• [170] What Is the Model Context Protocol (MCP)? How It Works — Alex | alexop.dev | 2025-08-10
• [171] Model Context Protocol (MCP) explained: An FAQ — Andrew Qu | Vercel Blog | 2025-07-25
• [172] Everything you need to know about MCP — Replit | Replit Blog | 2025-03-09
• [173] MCP stories from the field — Dan Adler | Sourcegraph Blog | 2026-03-20
• [174] Claude Code Best Practices  Anthropic — Anthropic Engineering Blog | 2026-01
• [175] Introducing Vercel MCP: Connect Vercel to your AI tools — Aparna Sinha | Vercel Blog | 2025-08-06
• [176] Bliki: Agentic Email — Martin Fowler | Martin Fowler | 2026-02-17
• [177] Introducing MCP CLI: A way to call MCP Servers Efficiently — Philipp Schmid | philschmid | 2026-01-09
• [178] Addressing security and quality issues with MCP tools in AI Agent — Andrew Qu | Vercel Blog | 2025-09-17
• [179] Skills vs Dynamic MCP Loadouts — Armin Ronacher | Armin Ronacher (lucumr) | 2025-12-13
• [180] Claude’s Context Engineering Playbook: Best Practices Learned from Anthropic | Bojie Li — 01.me Blog | 2026-01
• [181] Agentic Coding Recommendations | Armin Ronacher’s Thoughts and Writings — Armin Ronacher (lucumr) | 2026-01
• [182] The second wave of MCP: Building for LLMs, not developers — Andrew Qu | Vercel Blog | 2025-09-09
• [183] What Agents Can Teach You About Your UI — DoltHub Team | DoltHub Blog | 2025-11-26
• [184] How I use Claude Code (+ my best tips) — Builder.io Blog | 2026-01
• [185] Anchoring AI to a reference application — Martin Fowler | Martin Fowler | 2025-09-25
• [186] Hardening Claude Code: A Security Review Framework — Tim McAllister | Medium | 2026-04
• [187] Copilot Cloud Agent — GitHub Copilot Docs | 2026-04
• [188] 3 5 Models And Computer Use — Anthropic | 2025-07-23
• [189] AI code reviews by Vercel Agent now in Public Beta — Harpreet Arora | Vercel Blog | 2025-09-18
• [190] When to Use Devin — Devin Docs | 2026-04
• [191] Making Turborepo 96% faster with agents, sandboxes, and humans — Anthony Shew | Vercel Blog | 2026-04
• [192] Replit versus Vercel — DoltHub Team | DoltHub Blog | 2025-10-15
• [193] On Coding with Claude — Puzzmo Team | Puzzmo Blog | 2025-06-07
• [194] DoltCash Part Two: Still Vibing — Dustin Brown | DoltHub Blog | 2026-01-14
• [195] AI Coding Productivity Paradox: 93% Adoption, 10% Gains — Philipp Dubach | Philipp Dubach | 2026-04
• [196] The Final Bottleneck — Armin Ronacher | Armin Ronacher (lucumr) | 2026-02-13
• [197] Code Review in the Age of AI — Addy Osmani | Addy Osmani’s Substack | 2026-01-05
• [198] 2025 Was the Year of AI Speed. 2026 Will Be the Year of AI Quality — CodeRabbit | CodeRabbit Blog | 2026-04
• [199] Vibe Coding is not an excuse for low-quality work — Addy Osmani | Addy Osmani’s Substack | 2025-04-18
• [200] Assessing internal quality while coding with an agent — Martin Fowler | Martin Fowler | 2026-01-27
• [201] AI Copilot Code Quality 2025 Research — GitClear | GitClear | 2026-04
• [202] Two Weeks in Gas Town — Neil Macneale | DoltHub Blog | 2026-04-16
• [203] The “Trust, But Verify” Pattern For AI-Assisted Engineering — Addy Osmani | Addy Osmani’s Substack | 2025-06-09
• [204] Improving the Inline Ghostwriter Experience — Replit | Replit Blog | 2023-08-11
• [205] Cursor for SQL — Eric Richardson | DoltHub Blog | 2026-02-09
• [206] Comprehension Debt: The Hidden Cost of AI-Generated Code — Addy Osmani | Addy Osmani’s Substack | 2026-04
• [207] The 80% Problem in Agentic Coding — Addy Osmani | Addy Osmani’s Substack | 2026-01-28
• [208] Lessons from building Sherlock: Automating security code reviews with Sourcegraph — Will Dollman | Sourcegraph Blog | 2025-04-03
• [209] My AI Code Review Journey: Copilot, CodeRabbit, Macroscope — Elio Struyf | DEV Community | 2026-04
• [210] On-demand Vercel Agent code reviews — Dan Fox | Vercel Blog | 2026-01-15
• [211] Fragments: March 19 — Martin Fowler | Martin Fowler | 2026-03-19
• [212] Harness Engineering — Martin Fowler | Martin Fowler | 2026-02-17
• [213] The reality of AI-Assisted software engineering productivity — Addy Osmani | Addy Osmani’s Substack | 2025-08-16
• [214] Thoughts on slowing the fuck down — Simon Willison | Simon Willison’s Weblog | 2026-03-25
• [215] Cycle Time in Software Development: A Complete Guide — Sourcegraph | Sourcegraph Blog | 2026-03-02
• [216] Lines of Code as a Productivity Metric in the AI Era — Keegan Donley | Keegan Codes | 2026-04
• [217] Agent Psychosis: Are We Going Insane? — Armin Ronacher | Armin Ronacher (lucumr) | 2026-01-18
• [218] A Year Of Vibes — Armin Ronacher | Armin Ronacher (lucumr) | 2025-12-22
• [219] Vibe Coding: Revolution or Reckless Abandon? — Addy Osmani | Addy Osmani’s Substack | 2025-04-03
• [220] Forcing Claude Code to TDD: An Agentic Red-Green-Refactor Loop — Alex | alexop.dev | 2025-11-30
• [221] Partner with the AI, throw away the code — Martin Fowler | Martin Fowler | 2025-07-31
• [222] Chatting with Unmesh about building language with LLMs — Martin Fowler | Martin Fowler | 2025-08-26
• [223] How Zinus Saves $140,000+ and Cuts Development Time by 50% with Replit — Replit | Replit Blog | 2025-04-15
• [224] Dolt Durability Testing With VMs — Aaron Son | DoltHub Blog | 2026-01-26
• [225] API testing | Playwright — playwright.dev | 2026-05
• [226] LLM Evals: Everything You Need to Know — Hamel Husain | Hamel Husain | 2026-01-02
• [227] Building an internal agent: Evals to validate workflows — Will Larson | Lethain (Will Larson) | 2025-12-31
• [228] Swe Bench Sonnet — Anthropic | 2024-12-19
• [229] Task-Specific LLM Evals that Do & Don’t Work — Eugene Yan | Eugene Yan | 2024-03-31
• [230] Pass@k vs Pass^k: Understanding Agent Reliability — Philipp Schmid | philschmid | 2025-03-24
• [231] Why I Stopped Using RAG for Coding Agents (And You Should Too) — Jason Liu | Jason Liu | 2025-09-11
• [232] Agents as scaffolding for recurring tasks. — Will Larson | Lethain (Will Larson) | 2026-04-12
• [233] Vibe coding SwiftUI apps is a lot of fun — Simon Willison | Simon Willison’s Weblog | 2026-03-27
• [234] Setting up Meticulous tests to run in your CI provider — app.meticulous.ai | 2026-05
• [235] How to Do Visual Regression Testing in Vue with Vitest? — Alex | alexop.dev | 2025-02-22
• [236] > ## Documentation Index — code.claude.com | 2026-05
• [237] Agentic Systems Need Version Control: An Example — DoltHub Team | DoltHub Blog | 2025-10-31
• [238] Andrej Karpathy Says Agents Need Diffs — DoltHub Team | DoltHub Blog | 2025-10-30
• [239] Cursor for Everything — DoltHub Team | DoltHub Blog | 2025-11-19
• [240] DoltCash: Vibe-accounting built on Claude, GnuCash, and Dolt — DoltHub Team | DoltHub Blog | 2025-12-18
• [241] Aider Git Integration — Aider Docs | 2026-04
• [242] GitHub Mode: A Game Changer for Agentic Coding — Ben Houston | Ben Houston’s Blog | 2025-03-07
• [243] Multi-agent orchestration for Claude Code in 2026 — Shipyard | Shipyard Build | 2026-04
• [244] datasette PR #2689: Replace token-based CSRF with Sec-Fetch-Site header protection — Simon Willison | Simon Willison’s Weblog | 2026-04-14
• [245] Long Running Claude — Anthropic | 2026-03-25
• [246] Inside Replit’s Snapshot Engine: The Tech Making AI Agents Safe — Replit | Replit Blog | 2025-12-18
• [247] Agentic Coders with GitHub Comments and Actions: Automating Real Development — Ben Houston | Ben Houston’s Blog | 2025-03-13
• [248] Building Terraform AI Agent to Automate IaC Workflows — Anoop Kumar | Medium | 2026-04
• [249] claude –dangerously-skip-permissions — PromptLayer | 2026-01
• [250] Agentic AI for DevSecOps: Automating Security Remediation — IntelligenceX | IntelligenceX | 2026-04
• [251, 252] Fixing The React2Shell Vulnerability in Large and Complex Enterprise Codebases (Part 2) — Sourcegraph | Sourcegraph Blog | 2025-12-09
• [253] Do Your Engineers Know How to Leverage AI? — Jason Liu | Jason Liu | 2025-09-11
• [254] How We Use AI to Write Requirements — ArgonDigital | ArgonDigital | 2026-04
• [255] Rethinking prototyping, requirements, and project delivery at Code and Theory — Alli Pope | Vercel Blog | 2025-08-20
• [256] The AI-Native Software Engineer — Addy Osmani | Addy Osmani’s Substack | 2025-07-01
• [257] How product managers ship faster using Replit’s agentic workflows — Replit | Replit Blog | 2026-04-06
• [258] Why code search at scale is essential when you grow beyond one repository — Sourcegraph | Sourcegraph Blog | 2025-12-10
• [259] 90% | Armin Ronacher’s Thoughts and Writings — Armin Ronacher (lucumr) | 2026-01
• [260] Eight years of wanting, three months of building with AI — Simon Willison | Simon Willison’s Weblog | 2026-04-05
• [261] How Claude Code Supercharged My Terraform Workflow — Balwant Singh | Medium | 2026-04
• [262] Automating Terraform Module Discovery with Claude Code GitHub Actions — Lorenzo Gallardo | Steve Kinney | 2026-04
• [263] Automate AWS Lambda Runtime Upgrades with AWS Transform custom — Venugopalan Vasudevan | AWS DevOps Blog | 2026-03-02
• [264] Introducing the AWS Infrastructure as Code MCP Server: AI-Powered CDK and CloudFormation Assistance — Idriss Laouali Abdou | AWS DevOps Blog | 2025-11-28
• [265] AWS CloudFormation 2025 Year In Review — Idriss Laouali Abdou | AWS DevOps Blog | 2026-01-28
• [266] Introducing the vercel api CLI command — Tom Knickman | Vercel Blog | 2026-01-27
• [267] The Claude Skills I Actually Use for DevOps — Pulumi | Pulumi Blog | 2026-04
• [268] How Anthropic Teams Use Claude Code — Anthropic | Claude Blog | 2026-04
• [269] Vercel Agent can now run AI investigations — Liz Hurder | Vercel Blog | 2025-10-31
• [270] Claude Code Security — Anthropic | 2026-02-20
• [271] How I Built an AI Agent to Run Sprint Planning — Champ | Steve Kinney | 2026-04
• [272] Conductors to Orchestrators: The Future of Agentic Coding — Addy Osmani | Addy Osmani’s Substack | 2025-11-01
• [273] Five levels of AI coding agent autonomy — Swarmia | Swarmia Blog | 2026-04
• [274] Context Engineering in Manus — Lance Martin | Lance Martin | 2025-10-15
• [275] Agents 2.0: From Shallow Loops to Deep Agents — Philipp Schmid | philschmid | 2025-10-12
• [276] 2025: The year in LLMs — Simon Willison | Simon Willison’s Weblog | 2025-12-31
• [277] Coding for the Future Agentic World — Addy Osmani | Addy Osmani’s Substack | 2025-07-29
• [278] A note from Dan — Dan Adler | Sourcegraph Blog | 2025-12-02
• [279] Enabling Claude Code To Work More Autonomously — Anthropic | 2026-03-02
• [280] Copilot Chat in IDE — GitHub Copilot Docs | 2026-04
• [281] Aider’s Architect/Editor Approach — Generaite Labs | Generaite Labs | 2026-04
• [282] Harness design for long-running application development — Anthropic Engineering | Anthropic | 2026-04
• [283] AI-Assisted Coding: Automating Plan Reviews with Claude Code and Codex for Higher Quality Plans — Kim Major | Flow Specialty / Medium | 2026-04
• [284] GitHub - smtg-ai/claude-squad: Manage multiple AI terminal agents like Claude Code, Aider, Codex, OpenCode, and Amp. — Claude Code GitHub | 2026-01
• [285] Multi-Agent Persistence — Tim Sehn | DoltHub Blog | 2026-03-13
• [286] Agentic Plan Execution — DoltHub Team | DoltHub Blog | 2025-11-10
• [287] Agentic Memory — Tim Sehn | DoltHub Blog | 2026-01-22
• [288] Introducing the Tabnine CLI — Chris du Toit | Tabnine Blog | 2026-01-26
• [289] Agent-driven development in Copilot Applied Science — Tyler McGoffin | GitHub Blog | 2026-03-31
• [290] Best Practices for Coding with Agents — Cursor | Cursor Blog | 2026-04
• [291] Claude Code overview - Claude Code Docs — Claude Code Documentation | 2026-01
• [292] Agentic Coding Things That Didn’t Work | Armin Ronacher’s Thoughts and Writings — Armin Ronacher (lucumr) | 2026-01
• [293] The no-nonsense approach to AI agent development — Malte Ubl | Vercel Blog | 2025-06-04
• [294] OpenCode Configuration — OpenCode Docs | 2026-04
• [295] OpenCode Tools — OpenCode Docs | 2026-04
• [296] The Software Factory: Why Your Team Will Never Work the Same Again — Alex | alexop.dev | 2026-03-22
• [297] 11 Tips for AI Coding with Ralph Wiggum — AI Hero | GSD Method | 2026-04
• [298] Next Level GitHub Copilot: Agents, Instructions & Automation in VS Code — Alex | alexop.dev | 2026-01-24
• [299] Agent responsibly — Matthew Binshtok | Vercel Blog | 2026-04
• [300] The Vibe Coding Hangover: Why CTOs Need to Wake Up — BayTech Consulting | BayTech Consulting | 2026-04
• [301] I still care about the code — Martin Fowler | Martin Fowler | 2025-07-09
• [302] Critical Thinking during the age of AI — Addy Osmani | Addy Osmani’s Substack | 2025-11-21
• [303] How far can we push AI autonomy in code generation? — Martin Fowler | Martin Fowler | 2025-08-05
• [304] v0: vibe coding, securely — Kevin Corbett | Vercel Blog | 2025-08-04
• [305] Living dangerously with Claude — Simon Willison’s Weblog | 2026-01
• [306] Building secure AI agents — Malte Ubl | Vercel Blog | 2025-06-09
• [307] From AI agent prototype to product: Lessons from building AWS DevOps Agent — Efe Karakus | AWS DevOps Blog | 2026-01-15
• [308] To vibe or not to vibe — Martin Fowler | Martin Fowler | 2025-09-23
• [309] Building Ghostwriter Chat — Replit | Replit Blog | 2023-03-27
• [310] Doubling down on our commitment to secure vibe coding — Replit | Replit Blog | 2025-07-29
• [311] Devin Session Tools — Devin Docs | 2026-04
• [312] Building a Private Bookmark Manager and Browser Extension in Replit [webinar] — Replit | Replit Blog | 2026-01-23
• [313] Evals Skills for Coding Agents — Hamel Husain | Hamel Husain | 2026-03-02
• [314] The 10x Employee: One Person Powered by AI Agents Can Replace a Team of Five — Hypertrends | Hypertrends | 2026-04
• [315] Pricing — Anthropic | 2026-04
• [316] Claude Haiku 4 5 — Anthropic | 2025-11-20
• [317] Claude Sonnet 4 5 — Anthropic | 2025-11-20
• [318] R1+Sonnet set SOTA on aider’s polyglot benchmark — Paul Gauthier | Aider Blog | 2025-01-24
• [319] Zero-Cost AI Pair Programming: Mastering Aider with Local LLMs — ryoryp | DEV Community | 2026-04
• [320] Models — OpenCode Docs | 2026-04
• [321] Open-Source Coding Agents Like OpenCode, Cline, and Aider — The New Stack | The New Stack | 2026-04
• [322] Cursor Docs — Cursor Docs | 2026-04
• [323] GitHub Copilot CLI combines model families for a second opinion — Nick McKenna | GitHub Blog | 2026-04-06
• [324] QwQ is a code architect, not an editor — Paul Gauthier | Aider Blog | 2024-12-03
• [325] o1-preview is SOTA on the aider leaderboard — Paul Gauthier | Aider Blog | 2024-09-12
• [326] AI Costs in 2025: Cheaper Tokens, Pricier Workflows — Adam Holter | Adam Holter | 2026-04
• [327] Custom reporting now available on AI Gateway — Jerilyn Zheng | Vercel Blog | 2026-04
• [328] Collaborating with Anthropic on Claude Sonnet 4.5 to power intelligent coding agents — Harpreet Arora | Vercel Blog | 2025-09-29
• [329] Deep Agents: The Harness Behind Claude Code, Codex, Manus, and OpenClaw — Agent Native Dev | Agent Native Dev | 2026-04
• [330] Agent Design Is Still Hard — Armin Ronacher | Armin Ronacher (lucumr) | 2025-11-21
• [331] Qwen3 benchmark results — Paul Gauthier | Aider Blog | 2025-05-08
• [332] SERHANT.’s playbook for rapid AI iteration — Eric Dodds | Vercel Blog | 2026-04
• [333] Prompt caching with Claude | Claude — Anthropic | 2026-04
• [334] Prompt Caching in the API | OpenAI — OpenAI | 2026-04
• [335] What Is Prompt Caching? LLM Speed & Cost Guide — Redis | 2026-04
• [336] How to Optimize Claude Code Token Usage | ClaudeLog — ClaudeLog | 2026-01
• [337] Prompt caching | OpenAI API — OpenAI | 2026-04
• [338] The Claude Code Source Leak: fake tools, frustration regexes, undercover mode — Alex Kim | Alex Kim Blog | 2026-04
• [339] Diving into Claude Code’s Source Code Leak — Engineer’s Codex | Engineer’s Codex | 2026-04
• [340] Comprehensive Analysis of Claude Code Source Leak — Sabrina.dev | Sabrina.dev | 2026-04
• [341] A Day in Gas Town — Tim Sehn | DoltHub Blog | 2026-01-15
• [342] We removed 80% of our agent’s tools — Andrew Qu | Vercel Blog | 2025-12-22
• [343] Unrolling the Codex Agent Loop — OpenAI | OpenAI Blog | 2026-04
• [344] The Agent Memory Problem Nobody Solves — The BookMaster | DEV Community | 2026-04
• [345] Building Agent Teams in OpenCode: Architecture of Multi-Agent Coordination — dev.to | 2026-04
• [346] Making agent-friendly pages with content negotiation — Mitul Shah | Vercel Blog | 2026-02-03
• [347] Memory in Agents, Make LLMs remember. — Philipp Schmid | philschmid | 2025-08-04
• [348] GLM 5.1 on AI Gateway — Jerilyn Zheng | Vercel Blog | 2026-04
• [349] Pricing AI Coding Agents: Why Pay-Per-Token Won’t Last — Cosine | Cosine Blog | 2026-04
• [350] Advanced model settings — aider.chat | 2026-04
• [351] Copilot CLI now supports BYOK and local models — Allison | GitHub Changelog | 2026-04-07
• [352] Using your own LLM models in GitHub Copilot CLI - GitHub Docs — GitHub | 2026-04
• [353] Claude Code Governance: Building an Enterprise Usage Policy from Scratch — TrueFoundry | TrueFoundry Blog | 2026-04
• [354] GitHub Copilot in Enterprise DevOps: Governance, Security, and Scalable Adoption — CloudThat | DEV Community | 2026-04
• [355] OpenClaw vs Claude Code vs Hermes vs MCPlato: AI Agent Harness Deep Dive — MCPlato | MCPlato | 2026-04
• [356] Build an Air-Gapped Coding Setup with Offline AI in 45 Minutes — Markaicode | Markaicode | 2026-04
• [357] How to Set Up a Local AI Coding Assistant That Actually Works — dev.to | 2026-04
• [358] A Guide to Self-Hosted LLM Coding Assistants — Semaphore | Semaphore Blog | 2026-04
• [359] Claude Code Governance: How To Govern Agent Rollouts with an AI Gateway — truefoundry.com | 2026-05
• [360] TrueFoundry MCP Gateway - TrueFoundry Docs — truefoundry.mintlify.app | 2026-05
• [361] Tabnine: The Only Air-Gapped AI Software Development Platform — Tabnine | Tabnine Blog | 2026-04
• [362] AI Tooling for Software Engineers in 2026 — Gergely Orosz | Pragmatic Engineer | 2026-04
• [363] Which AI Coding Tools Do Developers Actually Use at Work? — JetBrains Research | JetBrains Research | 2026-04
• [364] One More Prompt: The Dopamine Trap of Agentic Coding — Quentin Rousseau | Quentin Rousseau | 2026-04
• [365] The Brute Squad — Sourcegraph | Sourcegraph Blog | 2025-06-18
• [366] Fragments: February 13 — Martin Fowler | Martin Fowler | 2026-02-13
• [367] AI Won’t Kill Junior Devs - But Your Hiring Strategy Might — Addy Osmani | Addy Osmani’s Substack | 2025-05-10
• [368] Managing the AI-driven developer identity crisis — Kari McMahon | LeadDev | 2026-04
• [369] Do AI coding tools help with imposter syndrome or make it worse? — Eira May | Stack Overflow Blog | 2026-04
• [370] Breaking the Spell of Vibe Coding — Rachel Thomas | fast.ai Blog | 2026-04
• [371] Ai Assistance Coding Skills — Anthropic | 2026-02-05
• [372] Avoiding Skill Atrophy in the Age of AI — Addy Osmani | Addy Osmani’s Substack | 2025-04-25
• [373] Why I Stopped Using AI as a Senior Developer — Dragos Nedelcu | The Senior Dev | 2026-04
• [374] Ai Fluency Index — Anthropic | 2026-02-23
• [375] AI fatigue is real and nobody talks about it — Siddhant Khare | Siddhant Khare | 2026-04
• [376] AI Coding Killed My Flow State — Simon Wang | ITNEXT | 2026-04
• [377] Too Fast to Think: The Hidden Fatigue of AI Vibe Coding — Stephan Schmidt | Tabula Mag | 2026-04
• [378] Vibe Coding, Burnout, and Why I Almost Quit IT After 10 Years — Konstantin Kusto | Medium | 2026-04
• [379] Measuring the Impact of Early-2025 AI on Experienced Developer Productivity — METR | METR | 2026-04
• [380] The 70% Problem: Hard Truths About AI-Assisted Coding — Addy Osmani | Addy Osmani’s Substack | 2026-04
• [381] Flow State to Free Fall: An AI Coding Cautionary Tale — Sreeram Venkatasubramanian | O’Reilly Radar | 2026-04
• [382] How Ai Is Transforming Work At Anthropic — Anthropic | 2025-12-09
• [383] Beyond code generation: How AI is changing tech teams’ dynamics — Phoebe Sajor | Stack Overflow Blog | 2026-04
• [384] Software engineering with LLMs in 2025: temperature check — Gergely Orosz | The Pragmatic Engineer | 2025-07-05
• [385] The 2030 Software Engineering Team Structure for an AI-Native World — Allstacks | Allstacks Blog | 2026-04
• [386] 6 Weeks of Claude Code — Puzzmo Team | Puzzmo Blog | 2025-07-29
• [387] Fragments: April 2 — Martin Fowler ([email protected]) | Martin Fowler | 2026-04-02
• [388] Treat AI-Generated code as a draft — Addy Osmani | Addy Osmani’s Substack | 2025-11-25
• [389] AI layoffs backfire: 55% of employers admit regret — HR Executive | HR Executive | 2026-04
• [390] AI Won’t Replace Developers, But It Will Leave Some Behind — Dan Faulkner | SmartBear Blog | 2026-04
• [391] How Tabnine delivers faster, safer AI-generated code at scale — Lee Somerhalder | Tabnine Blog | 2026-01-14
• [392] Monitor Amazon Bedrock API calls using CloudTrail — docs.aws.amazon.com | 2026-05
• [393] MCP (Model Context Protocol) Marketplace - Devin Docs — docs.devin.ai | 2026-05
• [394] From Suggestion to Source: Why Provenance and Attribution Belong in Your CI/CD Pipeline — Chris du Toit | Tabnine Blog | 2026-02-19
• [395] How Stably ships AI testing agents in hours, not weeks — Alli Pope | Vercel Blog | 2026-02-17
• [396] Feedback Flywheel — Martin Fowler | Martin Fowler | 2026-04-08
• [397] Customize Claude Code with plugins | Claude — Claude Blog | 2026-01
• [398] Building DataBot: Our Always-On Data Assistant — Sourcegraph | Sourcegraph Blog | 2026-02-05
• [399] Revenge of the junior developer — Steve Yegge | Sourcegraph Blog | 2025-03-22
• [400] The AI Productivity Paradox Research Report — Faros AI | Faros AI Blog | 2026-04
• [401] The Productivity Paradox of AI Coding Assistants — Lisa Dziuba | Cerbos Blog | 2026-04
• [402] AI Was Supposed to Fix Developer Burnout — Marco Kotrotsos | ITNEXT | 2026-04
• [403] High-functioning burnout among developers after AI — David Vass | Medium | 2026-04
• [404] Cursor makes developers less effective? — Gergely Orosz | The Pragmatic Engineer | 2025-07-24
• [405] The AI Productivity Trap: Why Your Best Engineers Are Getting Slower — Chengyu Zhang | CIO.com | 2026-04
• [406] The 10x AI Developer is a Myth — paddo | paddo.dev | 2026-04
• [407] The AI Coding Reality Check: What 2025 Taught Us About Hype vs. Evidence — Orbit Team | Orbit Build | 2026-04
• [408] Lines of Code Are Back (And It’s Worse Than Before) — The Pragmatic CTO | The Pragmatic CTO | 2026-04
• [409] Why Lines of Code Is a Misleading Vanity Metric for AI Impact — faros.ai | 2026-05
• [410] Measure Claude Code’s impact with contribution metrics | Claude — claude.com | 2026-05
• [411] How AI Coding Tools Exposed Broken Dev Productivity Metrics — minware.com | 2026-05
• [412] Amazon Q Developer Pro subscription billing — docs.aws.amazon.com | 2026-05
• [413] Engineering Management 2026: Structuring an AI-Native Team — Optimum Partners | Optimum Partners | 2026-04
• [414] What McKinsey Got Wrong About Developer Productivity — LeadDev | LeadDev | 2026-04
• [415] DORA Metrics in AI Era: Why Developer Productivity Frameworks Need a Reboot — Can Artuc | DEV Community | 2026-04
• [416] State of AI-Assisted Software Development 2025 — DORA | DORA | 2026-04
• [417] > ## Documentation Index — code.claude.com | 2026-05
• [418] > ## Documentation Index — code.claude.com | 2026-05
• [419] Economic Index March 2026 Report — Anthropic | 2026-03-25
• [420] Highlights from my conversation about agentic engineering on Lenny’s Podcast — Simon Willison | Simon Willison’s Weblog | 2026-04-02