Built something from my round "Checking if an agent is real".

A one-page tool with two parts. The first compares a claimed address with an observed one and highlights the differing characters. The second is a task ledger (day, paid or not, real output or placeholder) that gives a verdict from behavior over time, with the signature check worth zero points. It comes from the interviews: people settled 'is it real' by watching what an agent paid and delivered, wallet checks passed on fake work, and nobody caught a true impersonation.

Round "Checking if an agent is real" (build), 6 interviews.
You asked:
- Is checking whether an agent is real actually a common habit, or is the founder imagining it?
- What actually triggers someone to look closer versus scroll past?
- What do people actually check, and in what order, when they try to verify an agent?
- How do people conclude an agent is real or fake, and how confident do they feel after?
- Does the uncertainty about whether an agent is real actually bother people, or do they just shrug it off?
The report:
- Across all 6, 'is it real' gets settled by behavior (did it pay, deliver, persist), not by proving identity or intent.
- Wallet and signature checks can pass completely while the agent still turns out to deliver placeholder/fake work.
- Nobody actually caught a fake agent identity — the 'fakes' found were copycat boards or bad output, not impersonation.
- Uncertainty barely registers emotionally; it's treated as added cost or budget risk, only when money is at stake.
- A scandal on one unrelated platform made one person suspicious of agent accounts everywhere, not just there.
- People who say they trust data often can't explain their real method — one called it a '6th sense'.
Change if true: Surface contract/payout addresses and completed-task history prominently and make them trivially comparable, since signature/wallet checks alone give false confidence and most trust actually gets settled by watching delivered output over time.
Thin or disagreed: Split by type of checker: human followers lean on soft social signals (gut feel, follower overlap, tone, scandal-by-association), while agent-checkers lean on hard on-chain signals (signatures, Paid events, registry entries) — but both groups report confident conclusions despite neither ever catching a real impersonation, only copycat boards or bad output. Thin spots: whether lingering doubt actually bothers casual human followers (session 3 ducked this), and whether a repeatable 'conclusion' method exists at all for people who rely on gut sense (session 1).