AUTHOR
Baptiste Fernandez
Building AI Native Development community, spotlighting exciting releases and innovations in the space
Articles
Article
Anthropic, OpenAI, or Cursor model for your agent skills? 7 learnings from running 880 evals (including Opus 4.7)
Explore findings from 880 evaluations comparing Anthropic, OpenAI, and Cursor models, highlighting the impact of agent skills on performance and cost efficiency.
Article
Anthropic brings evals to skill-creator. Here’s why that’s a big deal
Anthropic's skill-creator now includes evals, allowing developers to test and validate context files, improving the accuracy and efficiency of AI coding agents.
Article
Level Up Claude Code: 14 Techniques Top Engineers Use
Explore 14 practical techniques used by engineers to maximize output with Claude Code, including planning, enhancing context with Tessl, and using mutable memory with CLAUDE.md.
Article
7 AI Devtools to Watch This December
Explore seven emerging AI development tools that enhance workflows through trust and adaptability, spotlighting innovative approaches that tackle unique challenges in coding and collaboration for developers.
Article
8 Devtools in the Spotlight - Last Month on the Landscape
Explore eight standout AI development tools, each uniquely enhancing workflows through trust and adaptability, as the rapidly evolving landscape prompts developers to rethink their approaches to integration.
Article
Does Developer Delight Matter in a CLI? The Case of Charm’s Crush
What if the real edge in AI dev tools isn’t just model power, but delight? Crush’s playful, glamorous CLI begs the question: how significant is joy and polish over technical capability?
Article
IDE Comparison With Cursor, Windsurf, and Copilot (on GPT-5)
Dive into a hands-on comparison of Cursor, Windsurf, and Copilot with GPT-5, highlighting their strengths in greenfield and brownfield projects through a spec-first development lens.
Article
Stack Overflow's 2025 Report is Out: Trends on AI Native Development
Developers use AI more than ever, but trust it less. ‘Almost right’ code is driving a push toward spec-driven development.
Article
Terminal-Bench: Benchmarking AI Agents on CLI Tasks
Terminal-Bench is a new benchmark testing how well AI agents handle real-world terminal tasks, revealing big performance gaps and sparking a wave of innovation in system-level agent design.
Article
The Most Valuable Developer Skill in 2025? Writing Code Specifications
In 2025, the key skill for developers is writing code specifications, shifting from transient prompts to structured documentation that aligns stakeholders and ensures clarity in AI-driven development.
Article
How claude-task-master “Reduced 90% Errors for My Cursor”
Discover how Taskmaster leverages AI-driven PRDs to decompose projects into focused tasks, boosting reliability, efficiency, cost savings, and developer autonomy.
Article
The Rise of “Visual Vibe Coding” (with New VSCode Extension)
Stagewise brings visual vibe coding to life - click elements, describe changes, and watch AI reshape your frontend. A new paradigm for intent-driven, precision UI development.
Article
The Best Open-Source Model for Agentic Coding? Meet Mistral’s Devstral
Mistral's new Devstral model tops SWE-Bench Verified for open-weight LLMs—compact, agent-optimized, Apache-licensed, and strong enough to rival massive proprietary giants.
Article
GitHub Unveils Copilot Coding Agent at Build 2025
GitHub Copilot evolves: cloud-based agents now handle PRs, iterate from feedback, and fit seamlessly into dev workflows.
Article
GitHub’s MCP Server: You Can Now Talk to Your Repos
GitHub’s new MCP server empowers Copilot to automate dev workflows with real-time repo context - marking a leap from code suggestions to worklfow actions.
Article
Developing Apps by Chat: How Far Can Lovable 2.0 Really Go?
Lovable 2.0 lets you build apps by chatting with an AI. What does this mean for developers?
Article
IDE Free Tier War: Windsurf’s Push to Win Over Developers
In April 2025, Windsurf (formerly Codeium) rolled out significant pricing updates that made waves in the developer community.
Article
When OpenAI Goes Open Source: Codex CLI
Codex blends ChatGPT and other models (you read that right) with hands-on capabilities like code execution, file manipulation, and project iteration.
Article
GPT-4.1 Exposes Frustrations in AI Native Development
Benchmarks are up, but so is developer frustration—model sprawl, version confusion, and prompt chaos are sparking a shift toward smarter abstraction.
Article
Plugins and Platforms: v0’s Marketplace Integrations in AI Native Development
Vercel's v0 now supports third-party integrations via its new Marketplace, letting developers spin up full-stack apps—complete with backend services—directly from AI prompts. This marks a major leap in the shift toward AI-native development.
Article
GPT-4.5 vs o3: Observations in AI-Native Development
GPT-4.5 vs o3-mini: Which model is best for AI-native development? Tessl’s AI Engineering team put them to the test—here’s what we found.