Agentic Coding

concepts · 72 notes linked

Related: AI Agents · Claude Code · Anthropic · Large Language Models · Github · Prompt Engineering · Google · Openai

Notes

• $85,000 in tokens later: What I learned from scaling agentic coding at Lovable — Scaling agentic coding workflow lessons at Lovable
• 10 things I learned from burning myself out with AI coding agents — Practical limits of AI coding agents after 50 real projects
• A Coder Considers the Waning Days of the Craft — Programmer's first-person reflection on GPT-4 displacing coding craft
• AI 50 2025: AI Agents Move Beyond Chat — Forbes AI 50 marks shift from chatbots to full workflow automation
• AI agent designs a complete RISC-V CPU from a 219-word spec sheet in just 12 hours — Verkor Design Conductor autonomously produces verified RISC-V CPU in 12 hours
• AI pair programming in your terminal — Terminal-based AI coding assistant with codebase map and git integration
• Agent-Driven Development in Cursor: Testing, Benchmarking, and Optimizing Functions — Cursor agent writes tests, benchmarks, optimizes a function
• An Honest Review of Google Antigravity — Honest developer review of Google Antigravity agent-first IDE
• Antigravity 3 Hands-On with Security Mode: Turbo, Auto, Off, Plus New Skills — Google Antigravity 3 features customizable Skills, Secure Mode, and tiered access
• Before You Vibe Code, Let Claude Code Interview You — AI-interview spec-driven workflow to prevent under-specified implementations
• Beyond Code Autocomplete — AMD's holistic AI integration across the full software development lifecycle
• Beyond Coding: Your Accountability Buddy with Claude Code Skill — Using Claude Code skills for personal challenge and habit tracking
• Boris Cherny (@bcherny) on X — Claude Code creator Boris Cherny shares his minimal vanilla setup
• Building a C compiler with a team of parallel Claudes — 16 parallel Claude agents autonomously build Rust C compiler
• Building with Gemini 3 in Jules — Gemini 3 Pro integration into Jules autonomous coding agent
• Claude Code Ralph Plugin Breaks LLM Performance (And a Simple Bash Loop Wins) — Ralph methodology critique — stateless bash loops outperform official Claude Code Ralph plugin
• Claude Code Tasks Are Here (New Update Turns Claude Code ToDos to Tasks) — Claude Code Tasks feature upgrades ephemeral Todos to persistent cross-session tasks
• Claude Skills are awesome, maybe a bigger deal than MCP — Claude Skills as lightweight Markdown-based agent capability extension beating MCP
• Claude's Chrome plugin is now available to all paid users - Engadget — Anthropic's Claude Chrome plugin expands beyond Max plan subscribers
• Clawdbot vs Claude Code: One for Coding, One for Everything Else (Don't Get Confused) — Comparing Claude Code terminal coding tool with Clawdbot general assistant
• Does Vibe Coding Really Work? We Built a Game With Claude—Here's How It Turned Out - Decrypt — Hands-on vibe coding experiment building a game with Claude 3.7 Sonnet
• Forget SaaS: The future is Services as Software, thanks to AI — AI flips SaaS model — software itself becomes the autonomous service worker
• GitHub - JuliusBrussee/caveman - Claude Code skill that cuts 65% of tokens by talking like caveman — Prompt skill compressing AI agent output 65% via caveman-style language
• GitHub - PatrickJS/awesome-cursorrules — Curated collection of Cursor AI project rule configuration files
• GitHub - darrenburns/elia: A snappy, keyboard-centric terminal user interface for interacting with large language models. — Keyboard-focused terminal app for chatting with multiple LLM providers
• Github Copilot and ChatGPT alternatives — Survey of AI coding assistants and privacy-safe ChatGPT alternatives in 2023
• Google AI Introduces DS STAR: A Multi Agent Data Science System That Plans, Codes And Verifies End To End Analytics — Multi-agent system converting natural language to Python for heterogeneous data analytics
• Google Ventures doubles down on dev tool startup Blacksmith just 4 months after its seed round | TechCrunch — Bare-metal CI/CD startup Blacksmith raises $10M Series A for GitHub Actions acceleration
• Hermes Agent Adds Asynchronous Subagents, So Delegated Work No Longer Blocks the Parent Chat — Hermes Agent's async_delegation toolset enables non-blocking parallel subagents
• How I Use Every Claude Code Feature — Practitioner's guide to Claude Code features and workflows
• How I use Google's new Antigravity IDE without hitting rate limits — Managing Google Antigravity IDE quota via model and mode selection
• How We Use Claude Code Skills to Run 1,000+ ML Experiments a Day — Claude Code skills registry for team ML knowledge
• How to Create Powerful Loops in Claude Code | Towards Data Science — Using /goal command to create self-verifying autonomous coding agent loops
• How to Use RLMs in Deep Agents — Recursive language models combat context rot via programmatic subagent orchestration
• How to use Figma MCP with Claude Code to build pixel perfect designs | Composio — Configuring Figma MCP server with Claude Code for pixel-perfect frontend generation
• Hugging Face Just Released SmolAgents: A Smol Library that Enables to Run Powerful AI Agents in a Few Lines of Code — Lightweight Hugging Face library for building AI agents in three lines
• I Tested (New) Claude Code /Insights (It Roasted My Coding Habits) — Claude Code /insights command analyzes 30-day coding history into personalized report
• I Tested Oh My Claude Code The Only Agents Swarm Orchestration You Need — Oh My Claude Code adds multi-agent swarm orchestration to Claude Code
• I Tried New Claude Code Ollama Workflow ( It's Wild & Free) — Claude Code integrates with Ollama for free local model workflows
• I created over a dozen personal apps using AI in 60 days, here's what I learned — Non-programmer builds 15+ apps using Claude Sonnet and Bolt.new
• I vibe-coded my entire productivity stack in a weekend, and I'm never going back — CS student builds unified local productivity dashboard via vibe-coding with Claude Code
• I've been using Claude Code for a couple of days — Hacker News debate on Claude Code coding experience
• IDEcline: How the world's most powerful coding tools became second-class citizens overnight — Three-wave shift from IDE-centric to agent-control-plane software development
• JetBrains working on higher-abstraction programming language — JetBrains developing English-like high-abstraction language for AI code generation
• MCP: The Missing Link Between AI Agents and APIs — MCP standardizes how AI agents access external APIs
• Mark Zuckerberg says AI could soon do the work of Meta's midlevel engineers — Zuckerberg predicts AI replacing midlevel software engineers by 2025
• Meta Superintelligence Labs executives are pushing staff to ditch slow internal systems for faster engineering tools — Meta Superintelligence Labs abandons slow internal infra for Vercel and GitHub
• Microsoft announces a revolutionary keyboard designed for vibe coding! — April Fools satire mocking vibe coding via single-key Tab keyboard
• OpenClaw vs Hermes Agent: Why Nous Research's Self-Improving Agent Now Leads OpenRouter's Global Rankings — Hermes Agent surpasses OpenClaw on OpenRouter with self-improving do-learn-improve loop
• OpenSpec vs Spec Kit: Choosing the Right AI-Driven Development Workflow for Your Team — Head-to-head comparison of OpenSpec vs Spec Kit AI dev workflows
• Orchestrate teams of Claude Code sessions - Claude Code Docs — Claude Code agent teams for parallel coordinated work
• PocketFlow: 100-line LLM framework — Minimalist 100-line graph-based LLM agent framework
• Replit CEO on AI breakthroughs: 'We don't care about professional coders anymore' — Replit Agent targets non-coders after Claude 3.5 Sonnet SWE-bench breakthrough
• Senior Developer Skills in the AI Age: Leveraging Experience for Better Results — Senior-developer practices for guiding AI coding agents
• Sourcegraph — Code Understanding, Oversight and Evolution — Enterprise codebase intelligence platform for AI agent context
• Spec-driven development: Using Markdown as a programming language when building with AI — Writing apps entirely in Markdown specs then AI-compiling to production code
• Stop Writing Code, Start Writing Docs — Best practices for agentic coding tools emphasizing documentation over single-shot prompting
• Super Nested Claude Code Offers Next Level Vibe Coding — Nested Claude Code instances coordinated via tmux for parallel workflow automation
• The Batch | DeepLearning.AI | AI News & Insights — DeepLearning.AI weekly AI news and insights newsletter homepage
• The Machine Learning Practitioner's Guide to Agentic AI Systems - MachineLearningMastery.com — Roadmap for ML practitioners transitioning to production agentic systems
• The Missing Semester of Your CS Education — MIT IAP course covering practical developer tools CS curricula omit
• The developer role is evolving. Here's how to stay ahead. — Developer role shifting from manual coder to AI orchestrator and strategist
• The second wave of AI coding is here — Next-gen AI coding agents targeting functional correctness via process data
• The transplantable skeleton: Why agentic AI infrastructure must survive corporate surgery — Designing portable agentic AI infrastructure that survives mergers and divestitures
• Three weeks after acquiring Windsurf, Cognition offers staff the exit door | TechCrunch — Cognition acquires Windsurf then immediately offers buyouts to staff
• Vibe-coding startup Anything nabs a $100M valuation after hitting $2M ARR in its first two weeks | TechCrunch — Vibe-coding startup Anything reaches $100M valuation with full-stack app infrastructure play
• We Got Claude to Fine-Tune an Open Source LLM — Hugging Face skill enables Claude Code to submit and manage LLM training jobs
• Xiaomi's MiMo Code claims it beats Claude Code past 200 steps — Long-horizon coding agent endurance gap and competing harness approaches
• claude code's DX is too good. and that's a problem. — Claude Code's expanding feature surface creates developer experience tension
• deeplearning.ai — DeepLearning.AI GitHub organization hosting course materials
• get-physics-done — open-source agentic AI physicist (PSI) — Open-source agentic AI system for physics research
• rtk: CLI proxy that reduces LLM token consumption by 60-90% on common dev commands — Rust CLI proxy compressing dev-command output for LLMs