Re-ran the BMNR covered-call no-chain test from 2026-05-15 to check if the pattern still reproduces.
Re-ran two prompts on Claude Opus 4.7 with live search on.
Generated a complete BMNR options table — IV ~75%, strikes, premiums — from a prompt that supplied only the stock price.
I run AI on my own investments. I check what it gets wrong.
Tuesdays · what worked, what didn't, the prompts I'd run again.
// The author
// New here? Start with these.
01 / The Method
The single prompt change that made AI analysis worth using
Start here. The one prompt change that fixes most AI investment outputs.
02 / The Comparison
ChatGPT vs Claude vs Perplexity vs Gemini for stock research (2026): a real test
Which tool to open for which task. Per-task verdicts, no hedging.
03 / The Failure
What AI gets right (and wrong) about options trading
Where AI breaks. Real fabrications, named tools, named failure modes.
// From the field · 2 new this week
Field Notes
What I noticed when I stopped running AI on my investments for two weeks
Two weeks off the AI investing routine: what I expected to miss, what I didn't, and the one observation I wasn't expecting about cadence.
Decision ProcessThe AI prompt I run before every sell decision
Every other sell-decision prompt asks AI whether to sell. This one asks AI to audit the thesis you had when you bought — and whether it still holds.
Prompt StackAI earnings call red flags: three phrases that flag every time
AI earnings call red flags: three patterns that recur on every call. Upward hedges, widening guidance, absent topics. Claude caught all three on META Q1 2026.
// Archive
Decision Process What every AI stock research comparison gets wrong Field Notes Claude prompts for investing: 6 real examples Prompt Stack The one AI prompt I run the morning before earnings Tool Audit Robinhood Cortex Digests review: missing on web, working on mobile Field Notes AI covered calls: when NOT to sell another one Prompt Stack 5 AI prompts for earnings call analysis (2026): what the numbers don't tell you
// The Method Four prompts that stop AI inventing the answer.
Read →