Scry lets you talk to any EVM smart contract in plain English. Point it at an address on six chains and ask "what does this do?" or "can I withdraw my funds?" The hard part is not the chat. It is getting a usable interface for a contract when the ABI is hidden behind a proxy, or when there is no verified source at all. Here is how the resolution pipeline works.
The easy case, and why it is rare
If a contract is verified on a block explorer, you fetch its ABI and you are done. The ABI tells you every function, its inputs, and its outputs, and you can build a chat interface on top of it. With the unified Etherscan V2 API, one key covers all the chains Scry supports, which simplifies the fetch considerably.
The trouble is that "verified with a clean ABI" is the minority case for the contracts people actually want to inspect. Two things break it constantly: proxies and unverified bytecode.
Problem 1: the proxy hides the real interface
