Notes from the build.

Every recommendation Vestya makes is written into a record that cannot be edited or deleted — stamped with the exact model version and prompt that produced it. Here is how that works and why we built it.

You can talk a language model out of a rule it was merely told to follow. Vestya's hard limits run as ordinary code before any model reviews a trade. Here is each rule, and the one that isn't live yet.

Any trade of $5,000 or more waits for your explicit yes — as does every stock trade and everything in real-money mode. That threshold is a design decision, not a preference setting.

It will be wrong sometimes. What matters is what the system does about it: a risk reviewer that can only shrink trades, receipts rendered by code rather than a model, and a record you can read afterwards.

The full path a Vestya recommendation travels — from your message, through a specialist's proposal, a rule engine, a risk review, and your approval, into a permanent record. Step by step, nothing skipped.

A plain-English definition: software that uses AI models to research and propose investment decisions. What that does and doesn't mean, what to ask before trusting one, and where the limits are.

Practicing with money that isn't real: how paper trading works, what it can genuinely teach you, and the three important things it cannot.

A percentage-of-assets fee grows with your balance whether or not the service improves. The arithmetic of what 0.25% actually costs at different balances, laid out plainly.

The honest answer is: not on faith. Trust claims are cheap — checkable mechanisms are not. The four questions worth asking of any AI investing product, and how Vestya answers them.