It’s time for another bi-weekly review. With AI compressing the scale of time so extremely that even a single day can feel long, why do I still review on a two-week cadence? I thought about it, and there’s no real reason — this scale just feels comfortable.
These two weeks, I kept meeting up with friends (and freeloaded quite a few meals, ha), attended a few seminars, continued advancing through the AI PM course and some online classes, reported back to my parents, and went through the move-in process for the studio. Looking ahead to May, a batch of hardware SKUs I’d ordered earlier will start arriving. Most importantly, there’s a small toy robot — I think it’ll be a fun theme, and something my daughter can play with as field testing. Another important thing is building a “real” Agent that can help me run development work in parallel, actually scaling a version of myself. And finally, an old classmate asked me to build a multi-broker trading system. I do invest, but building an order-placing tool was something I’d never considered before; after diving in this week, I found it quite interesting — and I have to plant a flag to wrap this project up in May!
1. AI Voice Input Tool: OmniTypist
Kept polishing the AI dictation experience on macOS / iOS, letting users quickly enter text by speaking, or select text and ask AI to refine it with one click. During this period I shipped several releases, ran iOS TestFlight testing, fixed speech-recognition stability, and wrote a Traditional Chinese user manual.
2. AI Reading Companion: Lectio
Started building a learning assistant that understands what you’re currently reading and talks with you by voice. It can read the content in your browser and help you understand articles, documents, or web pages through voice Q&A. During this period I completed the first macOS prototype, voice input/output, OCR screen understanding, a settings UI, and a local voice playback engine.
3. Multi-Broker Trading System: MatrixTradingSystem
Pushed an order-placing UI prototype toward a genuinely usable desktop trading system. During this period I completed the core architecture, the desktop app framework, the trading data model, the order/modify/cancel flow design, error prompts, audit logging, and initial integration and validation with some broker APIs.
This project is still in progress, with a way to go before it’s a complete product. Next I need to integrate more brokers, including the five major ones not yet done, plus plenty of risk control, accounting, testing, deployment, and live-trading validation features still being planned and developed.
🚩 Flag: wrap up by end of May.
4. Personal Site & Portfolio Rebuild
Reorganized chenfu.ai, shifting the site from a plain résumé display to a clearer presentation of what I’m building now: edge intelligence, secure networking, AI tools, and productization experiments. I also added bilingual content, project pages, and SEO.
5. Product Proposals & Market Exploration
Put together several product proposals and technical documents — including an AI trend-tracking tool, an AI Maker platform, voice assistant architecture, and OCR technology selection — so these ideas don’t just stay in my head but become material that can be discussed, validated, and collaborated on.
More next week: hardware arriving, unboxing the robot, and pushing the Trading Agent forward. The sense of time keeps compressing, but the direction keeps getting clearer.
Comments & Feedback