Tag
A tweet highlights the challenges of vibe coding and promotes a free 50-page guide on transitioning to agentic engineering, covering a new AI-driven software development life cycle.
Augment's Cosmos platform enables AI agents to handle the full software development lifecycle, dramatically reducing code review time from hours to minutes by automating routine checks and focusing humans on design decisions.
Shubham Saboo announced a free 50-page guide on shifting from vibe coding to agentic engineering, covering the AI agents-based software development life cycle.
Loom is an open-source delivery harness for coding agents that turns agents like Claude Code and Codex into repeatable software delivery systems by adding durable state, verification, and repair workflows.
A former Google engineer reveals that the so-called AI-generated code within the company in 2024 was mostly autocomplete. The real 'vibe coding' was limited due to technical silos and a strong review culture, and the conflict between efficiency and responsibility persisted until 2026.
Launches hands-on labs and a series on Agentic Engineering, starting with Agent Skills, covering planning, context engineering, multi-agent systems, and long-running agents.
The author shares their experience building a ReAct agent system and introduces the GLM-5 technical report released by Zhipu AI, which achieves breakthroughs in agentic, reasoning, and coding capabilities.
Simon Willison reflects on how vibe coding and agentic engineering are converging in his own workflow, raising concerns about code review responsibilities as AI coding agents like Claude Code become increasingly reliable. He explores the ethical tension between trusting AI-generated code in production and maintaining software engineering standards.
OpenAI's Codex CLI v0.128.0 introduces the /goal command, enabling the coding agent to iteratively work towards a defined goal until completion or token exhaustion.
Simon Willison shares an example of using Claude Code to add a new 'beats' content type to his blog-to-newsletter tool, demonstrating effective agentic engineering patterns and prompt design for delegating coding tasks to AI agents.
GLM-5 introduces DSA for cost reduction, asynchronous reinforcement learning for alignment, and enhanced coding capabilities, achieving state-of-the-art performance on benchmarks and real-world software engineering tasks.
A comprehensive best-practice guide for Claude Code covering subagents, commands, skills, and orchestration workflows to transition from vibe coding to agentic engineering.
A developer shares insights on how to maximize AI agent capabilities, arguing that simpler setups and understanding core principles are more effective than complex harnesses and libraries.
Andrej Karpathy discusses the December 2024 shift where LLMs reached new reliability, coining 'vibe coding' for floor-raising and 'agentic engineering' for ceiling-raising, and argues that verifiability is key to AI's jagged capabilities.