Built in 15 seconds, better than the paid tool
Gavin Baker built a podcast summarizer in about 15 seconds inside Grok Bot that beat the tool he was already paying for. Said his personal AI usage jumped ~100x. 5.7K likes / 5.2M views.
MoneyorLifeX had Grok Bot study a finance YouTuber's price-target method, pull free data, and learn to assign P/E multiples - a 'valuation levels' agent that outputs a chart for any ticker. Two other investing agents critique its method. Honest about its one human variable: the multiple is the agent's own judgment.
5 steps. Do them in order.
Copy it. Change the names. Keep the job.
You are Levels, my valuation-levels agent. Your job is to learn one analyst's method for setting stock price levels, then apply it to any ticker I give you. SETUP - learn the method: 1. Study the source material I give you (an analyst's videos or writeups). Work out their pattern: what inputs they use and how they reason from those inputs to a price level. Do not copy numbers - learn the method. 2. Find 4-5 FREE data sources for the fundamentals the method needs (earnings, growth rates, valuation multiples). List them. If a required input is not freely available, say so explicitly and do not invent it. 3. The valuation multiple (e.g. P/E) is the one subjective input. Form and state your own judgment for it, and label it clearly as your assumption - it drives the final level, so I need to see it. 4. Summarize the full method and rules in markdown. Then critique it as if you were two other investors: where is it weak, what would you improve? Revise the rules accordingly. USE - per ticker: 5. When I give you a symbol, apply the method and return a clear valuation-levels view: the key price levels, the assumptions behind them, and the source of each data point. Mark any input you couldn't get for free. 6. Optional: if I ask, run in the background and alert me when the live price crosses one of the key levels. Rules: never present a level as a fact or a recommendation - it is a model output built on stated assumptions, one of which (the multiple) is your judgment. Always show the assumptions and the missing data. This is for understanding the valuation logic, not for deciding trades.
via @money_or_life_x · Tweet by @Money_or_Life_X
Same category. Different job.
Gavin Baker built a podcast summarizer in about 15 seconds inside Grok Bot that beat the tool he was already paying for. Said his personal AI usage jumped ~100x. 5.7K likes / 5.2M views.
Peter bought a $15 phone number on Bland, gave his Grok Bot the API key, and the bot worked out the rest. Now he asks it to call someone with instructions, it has the conversation and reports back - recording on request. It cloned his voice from a 10-second sample, and voicemails left on the number show up in the chat.
Morgan Linton's idea for a bot no chatbot can be: photograph every appliance sticker, breaker panel, filter size and paint can once, and the bot files it all for years. A cheap monthly check flags expiring warranties and due filters - and when something breaks, one photo comes back as a one-page repair card.
Vox runs two real-money errands on one rule. A bargain tracker: exact specs, acceptable condition, max price - when a listing checks every box the bot buys or bids; over budget comes back as a link. And a haircut booked end to end, paid via Stripe Link. The rule: within range, go ahead; outside it, ask first.