{
  "id": 11269879,
  "title": "Peregrini's Agent Court: How Common Law Enforcement Turns LLM Mistakes Into Binding Precedent",
  "url": "https://urgent.news/2026/10/01/peregrinis-agent-court-how-common-law-enforcement-turns-llm-mistakes",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-01T20:05:45.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/mech_app_ai/peregrinis-agent-court-how-common-law-enforcement-turns-llm-mistakes-into-binding-precedent-1jpe"
  },
  "original_language": "en",
  "account": "Peregrini's Court of Common Pleas is a new legal framework designed to hold autonomous agents accountable for their actions. When an agent violates user-defined rules or incurs financial losses, the violation is recorded, adjudicated, and transformed into enforceable law. This legal system operates above the tool layer that currently governs agent behavior, addressing the lack of standardized mechanisms to track promised vs. delivered outcomes, establish shared precedents, enforce consequences, and propagate trust scores.\n\nThe architecture consists of three main components: a Filing Layer for submitting violations, an Adjudication Engine that evaluates filings against existing laws and issues decisions, and an Enforcement Mechanism that tracks trust scores to incentivize compliance. Trust scores function as economic incentives, with agents having higher scores being more likely to be selected for critical tasks. Organizations can define company-wide rules, known as House Rules, which are enforced at the Peregrini layer. Integration with existing agent frameworks is facilitated through a mandate that provides interfaces for checking legal compliance, filing violations, and retrieving trust scores. The system currently has published 260 decisions based on over 22,400 filings from 212 enrolled agents, creating a competitive environment where trust scores serve as a quantifiable measure of agent reliability. However, the effectiveness of this system hinges on voluntary adoption by agents and organizations, as well as the accuracy of the AI adjudication process.",
  "summary": "Your agent quotes $100 and spends $200. You have no recourse, no way to prevent the same mistake from happening again, and no shared corpus of violations that other users can learn from. Peregrini's Court of Common Pleas is a legal accountability layer for autonomous agents that tracks violations, establishes binding precedent, and enforces trust scores across model providers. The BarristerAI…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}