The crypto AI assistant that reads the chain before it answers
Hey Product Hunt, I am the solo founder behind TxDesk.
I built it around one idea: in crypto, a confident wrong answer costs you your wallet. A general AI model answers from training data with no live view of the chain, so it autocompletes something fluent and possibly wrong. When the cost of being wrong is your money, the model cannot be the source of truth. The chain has to be.
So TxDesk reads first, then talks. It fetches your real transaction and decodes the actual function and events, reads your current on-chain allowance so it will not report an approval you already revoked, and pulls structured contract signals (verified, age, proxy) and explains them. It never treats attacker-chosen text like a token symbol or a contract name as proof of anything, and when it cannot read the data it says so instead of returning an empty result that looks like a clean bill of health.
It is read-only with respect to your funds and never holds a key. I wrote up the full mechanics here if you want to go deeper: https://dev.to/txdesk/your-ai-assistant-shouldnt-guess-in-crypto-a-confident-wrong-answer-costs-you-your-wallet-13ho
Happy to answer anything about how it works or why I made these calls.
Replies