{
  "id": 16309182,
  "title": "Building Climate Court: Evidence-First Climate Investigations with Next.js, Optional AI, and Verifiable Reports",
  "url": "https://urgent.news/2026/10/24/building-climate-court-evidence-first-climate-investigations-with",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-24T09:46:57.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/sandeep_chakravartty_219e/building-climate-court-evidence-first-climate-investigations-with-nextjs-optional-ai-and-2cma"
  },
  "original_language": "en",
  "account": "The source material outlines the development of a platform called Climate Court, which aims to improve the transparency and evidence-based verification of corporate sustainability claims. The platform uses a local-first approach, allowing investigations to be conducted without relying on paid API keys or cloud accounts.\n\nThe core workflow of Climate Court involves submitting a climate-related claim, adding supporting material (via pasted text or a text-based PDF), extracting atomic assertions, inspecting evidence classifications and provenance, generating a versioned report, and registering its snapshot hash on a local EVM (Ethereum Virtual Machine). The application also includes a dashboard, investigation workspace, printable reports, JSON exports, version history, and tools for auditing the process.\n\nThe technology stack for Climate Court includes Next.js App Router, React, TypeScript, Tailwind CSS, Lucide, an HTTP backend with server-side route handlers, runtime validation using Zod, local persistence with schema-validated JSON, and optional cloud persistence via Supabase PostgreSQL. An optional AI adapter, based on the Google Gemini SDK, is included, but the AI's role is limited to suggesting ambiguities rather than deciding verdicts or generating source material. The platform also emphasizes the importance of evidence integrity, with evidence coverage being tracked separately from the verdict.",
  "summary": "How we built a local-first investigation platform—and why the most valuable improvements came from testing what happens when things go wrong. Corporate sustainability claims often sound precise: “We reduced our carbon emissions by 40%.” But precision in wording does not necessarily mean precision in evidence. Reduced compared with which year? Does the figure describe absolute emissions or…",
  "key_points": [
    "Climate Court platform verifies corporate sustainability claims",
    "Local-first approach avoids paid APIs and cloud accounts",
    "AI adapter suggests ambiguities, not verdicts or sources"
  ],
  "editors_take": "By prioritizing local-first workflows and verifiable evidence tracking, this platform provides a technical framework for auditing corporate sustainability claims without relying on centralized cloud services or automated AI verdicts.",
  "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."
}