What we learned building two fail-closed verification tools for the agent economy
ERC-8004 gives AI agents an on-chain identity, but identity is not trust. A few recent posts here made that point well, including one showing that a naive average of reputation scores can crown the wrong agent as "best." That matches something we ran into ourselves, from a different angle, while building two small open-source tools. We did not set out to build a trust layer for agents. We built…
Building two fail-closed verification tools for the agent economy revealed a crucial lesson: never claim clean when you haven't actually checked. The first tool, which verified a sanctions-list claim, refused to declare clean if the list was missing, stale, or below a minimum version number. The second tool, which checked payment receipts, reported a payment as invalid if it did not fully check out.
Both tools emphasized the importance of honesty in verification processes. The authors tested their tools extensively by planting deliberate bugs in the code and ensuring that every single fault caused a test failure. Despite their tools not solving agent trust, the authors believe that testing one's own verification process is essential.
They have not yet resolved an issue with the verification of independently-verified impact claims, where the field for "who verified this" is left open. The authors invite anyone building on top of ERC-8004 or x402 to share their experiences and challenges.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
