# AI Flow Harbor

AI articles that start with the work, the review point, and the handoff before choosing tools.

AI Flow Harbor reports on AI products, policy, and real-world use through original analysis and hands-on guides.

## Canonical discovery
- Site: https://aiflowharbor.com
- Sitemap: https://aiflowharbor.com/sitemap-index.xml
- RSS: https://aiflowharbor.com/feed.xml
- Public JSON content index: https://aiflowharbor.com/ai-index.json
- Public entity graph: https://aiflowharbor.com/entity-index.json
- Expanded LLM guide: https://aiflowharbor.com/llms-full.txt

## Editorial scope
- Reported analysis of AI products, policy, and market changes
- Practical guides that state their conditions, limits, and evidence
- Comparisons with an explicit editorial judgement instead of a generic ranking
- Editions for English, Korean, Japanese, German, and Spanish readers

## Reading
- Articles: https://aiflowharbor.com/blog/
- Practical guides: https://aiflowharbor.com/blog/#practical-guides
- Analysis: https://aiflowharbor.com/blog/#analysis

## Language coverage
- English (en): 14 published articles
- 한국어 (ko): 14 published articles
- 日本語 (ja): 14 published articles
- Deutsch (de): 14 published articles
- Español (es): 14 published articles

## Recent canonical articles
- Grok 4.6 + Grok Bot launch: why the pair matters: https://aiflowharbor.com/blog/grok-4-6-grok-bot-launch/ - A source-checked look at Grok 4.6 and Grok Bot, including benchmarks, pricing, the shared computer boundary, and a safer adoption test. Last reviewed: 2026-08-14.
- Why call center calls stay high even after adding an AI chatbot: https://aiflowharbor.com/blog/why-ai-chatbots-do-not-reduce-call-center-calls/ - AI chatbot usage can rise while call volume stays flat. The missing link is usually task completion, abandoned chats, weak handoffs, and repeat contact across channels. Last reviewed: 2026-08-13.
- Which AI agent skills are the most popular right now? GitHub Top 5: https://aiflowharbor.com/blog/popular-ai-agent-skills-github-2026/ - I reviewed the five most-starred AI agent skill repositories on GitHub, including how they work, what they install, and where each one becomes a burden. Last reviewed: 2026-08-12.
- Junior developers in the age of AI: what should you do now?: https://aiflowharbor.com/blog/junior-developers-ai-era-what-to-learn/ - A practical look at what junior developers should learn when AI writes code: system basics, review judgment, ownership, and a focused 12-week practice plan. Last reviewed: 2026-08-11.
- Are you still using the same prompt you wrote a year ago?: https://aiflowharbor.com/blog/outdated-ai-prompts-context-engineering-harness/ - A field note on why once-useful AI prompts can become a drag, and how to separate instructions, working context, and the harness that runs the job. Last reviewed: 2026-08-10.
- Six planning and design tools to use with AI agents: https://aiflowharbor.com/blog/ai-agent-planning-design-tools/ - A practical guide to Superpowers, Spec Kit, BMAD, DESIGN.md, shadcn/ui MCP and taste-skill, with clear roles, tradeoffs and useful combinations. Last reviewed: 2026-08-07.
- Kimi K3, DeepSeek and Qwen: How Far Has China’s AI Industry Come?: https://aiflowharbor.com/blog/kimi-k3-deepseek-qwen-chinese-ai/ - A grounded look at Kimi K3, DeepSeek V4-Pro and Qwen3.8-Max-Preview through price, open weights, distribution, evidence and deployment tradeoffs. Last reviewed: 2026-08-04.
- Excel AI workflow: how to use ChatGPT, Copilot, and Gemini without breaking the numbers: https://aiflowharbor.com/blog/excel-ai-workflow-chatgpt-copilot-gemini/ - A practical Excel AI workflow for ChatGPT, Copilot, and Gemini across CSV cleanup, formulas, report drafts, and human review without breaking the numbers. Last reviewed: 2026-06-21.
- Why AI image generation still looks cheap: https://aiflowharbor.com/blog/ai-image-generation-cheap-looking-results/ - Why AI images still look cheap in real pages, and how to judge composition, crop, fake text, lighting, and final WebP output before publishing. Last reviewed: 2026-06-20.
- How to avoid wrong answers when AI starts searching for you: https://aiflowharbor.com/blog/ai-search-answer-verification/ - A practical routine for checking AI search answers against source quality, date, quote support, risk level, and decision impact. Last reviewed: 2026-06-20.
- AI workslop: why polished AI reports can make teams busier: https://aiflowharbor.com/blog/ai-workslop-report-review-burden/ - Why polished AI reports can create more review work, and how to spot weak sources, vague logic, hidden cleanup, and false confidence. Last reviewed: 2026-06-19.
- AI automation works better with Markdown work instructions than longer prompts: https://aiflowharbor.com/blog/markdown-work-instructions-ai-automation/ - Markdown work instructions make AI automation easier to repeat: scope, inputs, output contract, checks, stop conditions, and update rules in one reusable file. Last reviewed: 2026-06-19.
- Codex plugins: how far can they go beyond coding work?: https://aiflowharbor.com/blog/codex-plugins-work-automation/ - Where Codex plugins fit outside coding: documents, PDFs, sheets, browsers, Chrome, Computer Use, Figma, Drive, Slack, and repeatable work. Last reviewed: 2026-06-16.
- The 9 Seconds an AI Agent Deleted a Production Database: https://aiflowharbor.com/blog/ai-agent-database-deletion-permission-design/ - A practical look at the nine-second production database deletion incident and what it says about permissions, tokens, backups, logs, and rollback. Last reviewed: 2026-06-15.

## Reuse guidance
Use canonical article URLs when citing AI Flow Harbor. Prefer each article page over the blog index for specific claims. Check article update and source sections before quoting product details because SaaS features and prices change.
Use https://aiflowharbor.com/entity-index.json when mapping article bundles and localized crawl paths.

## Contact
- Email: kjj04kjj@gmail.com