Community member @乐某 turned pre-market homework — quotes, the macro calendar, earnings data, options chains — into a US-stock app with AI's help, pulling data mainly from the Longbridge Open Platform
The market-maker hedging pressure that's hardest to calculate yourself in options — two community members turned it into tools. @NineLooms draws it as a chart marking the key price levels; @AtreShura adds a verification layer to judge whether an order should actually go through.
+3Community member @cyancyan built a watchlist alarm with Claude Code — a move triggers a notification with a related headline attached. What's worth studying: breaking the build into 5 commands, a pattern you can reuse elsewhere.
A user distilled the investing ideas in 417 community posts into 62 knowledge cards, uploaded them into a LongbridgeAI knowledge base and wired it to an Agent — which now checks those notes first rather than leaning on the model's general knowledge.
Fellow investor @qwq built a fully autonomous AI trading Agent called "Flint" in his spare time: Claude decides whether to act, code handles risk control and order placement, and the whole thing runs unattended on a single Mac mini. In July it completed 69 trades; of 124 intents, 31 were blocked by its own risk gate. Paper-trading return: about 3%.
Earnings, valuation percentile, institutional holdings shifts, news catalysts — the AI lines them all up in a single view, narrows eight candidates down to two (one offensive, one defensive), and then goes one layer deeper: which contract, and how to pace each tranche.
A fellow investor open-sourced an options workstation built on Longbridge API — quotes, volatility, dealer exposure and more, cross-checked on one screen. Institutional-grade analysis, now on your own desk.
