ai-workflow

Introducing an AI-assisted development workflow that combines OpenSpec (specification and memory management) with Superpowers (design and execution), using TDD and unified context to solve the two biggest pain points in AI development: lack of memory and lack of discipline.

A detailed guide on how to apply Codex to office and knowledge scenarios, covering environment setup, core concepts, five advanced levels, and other practical content.

Karpathy shares a method to fully automate Obsidian note-taking using Claude, turning the AI into a maintainer that reads new sources, structures a wiki, and runs checks for contradictions, eliminating manual effort.

A step-by-step guide on using Claude Cowork to automate knowledge worker tasks, enabling a one-person company to operate efficiently by offloading production work to AI while focusing on decisions.

A practical guide on setting up iterative loops for AI coding agents with defined stop conditions, cloud execution, and notification channels to offload work without constant babysitting.

This article introduces six ways to use Hooks in Claude Code, including permission pop-ups, startup schedule announcements, summary cards, automatic file organization, sedentary reminders, and long task notifications, demonstrating how event-driven automation can improve the efficiency of AI workflows.

The article discusses the challenge of maintaining consistent context across multiple AI models like ChatGPT and Claude, presenting three common approaches: manual context passing, using one primary model, and a unified workspace, recommending a hybrid approach anchored to a single source of truth.

Discovered an English learning guide with over 50k stars on GitHub. The author details how to use AI learning workflows and prompts to efficiently learn English, and personally tested it with good results.

aronprins announces updates to Claude Loop and Codex Loop, adding parallel wave support for faster autonomous coding workflows using Claude Code.

This tutorial introduces the Loop Engineering method, which designs a cycle of automatic execution, checking, and correction, allowing AI to iterate until the result is satisfactory, upgrading a single query into process engineering.

Introduces three AI workflows that will make money in 2026: reverse-engineering overseas case studies, converting long-form articles into viral X threads, and building a faceless AI short video matrix. Emphasizes that systematic workflows and prompt iteration matter more than chasing new tools.

Introduces how to use Obsidian and Claude Code to build a local AI knowledge base, by creating folder structures, writing CLAUDE.md rule files, and step-by-step importing and organizing materials, to achieve long-term portable personal knowledge management.

The article analyzes the problem of AI-generated writing that often appears correct but actually contains errors, and introduces a workflow using Deep Research tools (such as Apodex) to break down problems, find evidence, check risks, and finally write, helping creators improve content quality.

The author introduces how to use the Helio platform to break down the article writing process into five AI steps (research, deepening the outline, creating a title, removing AI flavor, generating cover prompts), enabling automated handoffs. The author only needs to come up with a topic to get a finished product, significantly reducing the middleman's communication work.

Andrej Karpathy shares his straightforward approach to working with AI, emphasizing plain language over complex prompt engineering, and predicts that by 2026 engineers who dismiss LLMs will lose to juniors who use them effectively.

The article introduces three new courses released by OpenAI on June 12, and provides a 7-day practice plan to help users go from basic usage to building AI workflows, ending with a checklist.

The author shares their evolved workflow for using Claude Code, emphasizing more time spent in conversation with the agent and less on reading its output. They outline a process of discussion, plan distillation, parallel execution, and final PR review.

The article argues that the key to AI productivity is not chasing new tools but selecting the right models for each task and combining them with deep business judgment. It emphasizes running multiple models in parallel and using human expertise to correct AI flaws.

Explains how Codex functions as an AI workbench that integrates project context, tasks, plans, goals, and skills into a cohesive workflow, positioning it as more than just a chatbot.

This article discusses the concept of Skills in the AI agent ecosystem, arguing that Skills are more than prompts—they are packaged capabilities that externalize human expertise into reusable workflow units. The author shares design principles and case studies from building popular Skills.