ForestSharing insights on learning, data-driven innovation, AI thinking and my life
My company's internal AI agent builder training was fantastic. But after the demos ended, I started thinking about who these tools actually serve, what they're genuinely good at, and where the gaps still hide. A practitioner's reality check on enterprise AI democratization.
A practical look at how AI is transforming government public services - from tax compliance and fraud detection to taxpayer experience. Real use cases, real ROI numbers, and what IT teams should know about this fast-moving space.
Configurable AI agent platforms from Microsoft, Google, and AWS promise no-code agent building. But the gap between drag-and-drop demos and production-grade agents is wider than the marketing suggests. A deep dive from chatbots to autonomous agents.
Claude Code's new agent teams feature lets multiple AI instances work as a coordinated team — with a lead, shared tasks, and direct messaging. I tested it on an RFP review and the results were surprisingly good. Here's how it works, what it costs, and when you should (and shouldn't) use it.
How I moved from spending a euro per blog post on Gemini 3 Pro to a hybrid Gemini 2.5 Flash + Replicate FLUX setup that costs almost nothing — without sacrificing quality where it matters.
I checked Google Search Console and the numbers were embarrassing. Broken hreflang, wasted crawl budget, a sitemap Google refused to read — here are the 12 SEO issues I found in my Next.js blog and how I fixed each one, explained for humans.
ChatGPT可以帮我做装备抉择，Claude Code可以帮我把工作效率拉满。但它们永远算不出，那个独自骑着单车穿过上海深夜街道的瞬间，到底值多少算力。
Leave a message, say hello!
