I built a Qwen 3.8 Max agent that decides which ERC-8004 agents to trust, and teaches itself to say 'not enough data'

Описание и применение

AgentCredit использует Qwen 3.8 Max для анализа отзывов ERC‑8004, вычисляет надёжный рейтинг и записывает решение в смарт‑контракт, обеспечивая прозрачную проверку доверия.

Задача

ERC‑8004’s reputation registry provides raw feedback but no standard trust score, leading to misleading summary numbers that can approve or disapprove agents incorrectly.

Результат

AgentCredit successfully filters out unreliable feedback, applies strict evidence thresholds, and records trustworthy verdicts onchain, enabling reliable trust checks for ERC‑8004 agents.

Рабочий процесс

• 1. Qwen 3.8 Max plans and calls tools to confirm agent existence, read and classify feedback, compute score, compare to threshold, and optionally record verdict onchain.
• 2. The AgentCredit contract stores the verdict, coverage figure, and evidence hash.
• 3. Anyone can verify the record or gate actions via a single contract call.

Доказательства

ERC‑8004’s Reputation Registry lets anyone leave feedback for an agent: a number, plus tags saying what it is.

Источник

The job isn’t “ask an AI for a number”. The job is to read the individual entries, work out what each one means, and refuse to score what can’t be interpreted.

Источник

In my first version, the score was built from the registry’s summary number. When I asked about agent #16, which has exactly one rating of 85 from a single client, Qwen answered APPROVE (with caution).

Источник