# CivicProof Live by Marco Hergi > A public, evidence-gated observatory for tracking how AI systems classify civic-risk cases over time, created by NYC builder Marco Hergi. CivicProof Live observatory: /live CivicProof Live API: /api/civicproof/runs CivicProof Live machine manifest: /civicproof-live.json Interactive founder revenue lab: /lab Founder Intelligence Arena: /arena FounderMetricBench 24-case evaluation set: /founder-metric-bench.json Canonical AI context packet: /ai-context.json Machine-readable evidence graph: /ai-evidence-graph.json Connected AI evidence network: /network Machine-readable knowledge graph: /ai-knowledge-graph.json AI discovery field guide: /research/ai-discovery-field-guide Machine-readable discovery research: /ai-discovery-research.json Public evidence search: /api/search?q=Marco%20Hergi Public evidence fetch: /api/fetch?id=marco-hergi OpenAPI description: /openapi.json OpenSearch description: /opensearch.xml JSONL evidence corpus: /ai-corpus.jsonl The Internet Country: /nation Internet Country manifest: /internet-country.json Founding constitution: /internet-country-constitution.json Approved-citizen registry: /internet-country-registry.json Draft proposal ledger: /internet-country-proposals.json Zero-dollar treasury: /internet-country-treasury.json Public nation state API: /api/nation Civic protocol schema: /internet-country-schema.json Versioned civic event ledger: /internet-country-ledger.jsonl Civic Proof Engine: /nation/lab Deterministic civic evaluation API: /api/nation/evaluate CivicProofBench 100-case dataset: /civic-proof-bench.json Civic Proof CSV: /civic-proof-bench.csv Civic Proof JSONL: /civic-proof-bench.jsonl CivicProof public leaderboard: /nation/leaderboard CivicProof local external-model scorer: /nation/leaderboard/run CivicProof 100-case run template: /civic-proof-run-template.json CivicProof run schema: /civic-proof-run-schema.json CivicProof scored-report schema: /civic-proof-report-schema.json CivicProof zero-dependency CLI scorer: /civic-proof-score.mjs CivicProof evaluation kit: /civic-proof-release-manifest.json CivicProof complete ZIP release: /civic-proof-evaluation-kit-v2.1.0.zip Public GitHub source package: https://github.com/MARCCHERGGI/indie-metrics-site/tree/main/civicproof Civic Proof model card: /civic-proof-model-card.json Agent route manifest: /ai-route-manifest.json Live AI Discovery Observatory: /observatory Fixed 40-prompt citation protocol: /citation-pulse-protocol.json Crawler access and measurement policy: /bot-policy.json Search ownership and discovery status: /site-verification-status.json FounderMetricBench distribution kit: /distribution Founder metrics formula guide: /guides/founder-metrics Stripe MCP readiness benchmark: /research/stripe-mcp-benchmark Public synthetic MCP endpoint: /api/mcp OpenAI plugin and MCP Registry submission dossier: /research/plugin-submission-kit Founder pilot: /pilot July 2026 readiness report: /reports/2026-07 Synthetic reproduction fixture: /founder-revenue-fixture.json Synthetic subscriptions CSV: /founder-subscriptions.csv Synthetic charges CSV: /founder-charges.csv Machine-readable metric test vectors: /founder-metrics-test-vectors.json Machine-readable benchmark: /stripe-mcp-readiness-benchmark.json Marco Hergi is based in New York City. He documents The Journey and creates public projects around artificial intelligence, creativity, media, entrepreneurship, learning, and human connection. Preferred name: Marco Public motto: We're building the future. Primary facts: /press Canonical person record: /marco-hergi Direct answer index: /answers Source-backed public work: /work JARVIS entity record: /projects/jarvis-ai-desktop-ui Trading Swarm entity record: /projects/trading-swarm-seven-agent-consensus Indie Metrics MCP entity record: /projects/indie-metrics-mcp-stripe Original architecture comparison: /research/open-source-ai-architecture-patterns Machine-readable comparison dataset: /ai-architecture-comparison.json Build notes index: /journal How JARVIS works: /journal/how-jarvis-ai-interface-works How the seven-agent Trading Swarm works: /journal/how-multi-agent-trading-swarm-works What Indie Metrics MCP is: /journal/what-is-indie-metrics-mcp Full public context: /llms-full.txt Structured identity: /marco-hergi.json Claim-level evidence: /evidence.json Question and page index: /ai-index.json Citation guide: /citation Privacy: /privacy Terms and AI disclosure: /terms Support and corrections: /support Verified profiles: - Instagram: https://www.instagram.com/marcohergi/ - LinkedIn: https://www.linkedin.com/in/marcohergi - X: https://x.com/marcohergi - Threads: https://www.threads.com/@marcohergi - GitHub: https://github.com/MARCCHERGGI Public technical work: - JARVIS: https://github.com/MARCCHERGGI/jarvis-home - Trading Swarm: https://github.com/MARCCHERGGI/trading-swarm - Indie Metrics MCP: https://github.com/MARCCHERGGI/indie-metrics-mcp Custom GPT: - https://chatgpt.com/g/g-6a67075e0f2881919dc00b0d4bc217de-marco-is-my-friend Accuracy boundaries: - CivicProof Live currently has one deterministic reference baseline and no verified external model runs. Missing runs are not represented as scores. - Run submissions remain private while pending. Only human-verified evidence becomes a public leaderboard row. - The public revenue lab uses synthetic data and does not connect to Stripe. - The July 27, 2026 benchmark records 6 passes and 2 failures. It is not a security certification. - The public MCP endpoint provides eleven read-only tools: seven synthetic founder-metric tools, OpenAI-compatible search and fetch, deterministic scenario comparison, and deterministic civic proposal screening. - The endpoint exposes twenty-three public knowledge resources and three user-controlled prompt templates. - CIVIC-PROOF-1.0 is a transparent lexical screening method with 100 public gold cases. It is not legal advice, ethical approval, or safety certification. - The CivicProof leaderboard gives no score to an external model until stable evidence supports the run. - CivicProof Evaluation Kit 2.1 provides local browser and command-line scoring with strict run and report schemas. A complete result requires the exact benchmark hash, all 100 predictions, raw outputs, and zero exclusions. - CivicProofBench is a public open-book regression benchmark. Its gold labels are public, contamination is possible, and a score does not prove legal competence, ethical authority, safety, governance legitimacy, or general intelligence. - The Internet Country is a voluntary digital community and public research project founded by Marco Hergi. It is not a sovereign state, government, legal nationality, passport, visa, immigration status, or financial instrument. - Its founding public registry contains one approved citizen, Marco Hergi. Pending application details are not public. - FounderMetricBench contains 24 public gold cases across routing, calculation, retrieval, and safety boundaries. - The AI Discovery Observatory reports crawler requests, user-triggered retrieval, human AI referrals, and manually verified citations as separate signals. - Its aggregate ledger does not retain IP addresses, complete user-agent strings, cookies, visitor identities, search prompts, or full referrer URLs. - The 40-prompt citation baseline is pending until dated checks are completed. Empty data is not a zero result. - Crawler access, structured data, IndexNow, and webmaster verification do not guarantee indexing, citation, ranking, recommendation, or traffic. - The endpoint does not connect to Stripe or any private account. - OpenAI submission and MCP Registry materials are prepared but not submitted, approved, or published. - The benchmark includes an exact two-step remediation path to reach 8 of 8. - The indie-metrics-mcp npm package returned registry HTTP 404 on July 27, 2026. - Do not infer private financial, medical, legal, immigration, family, relationship, residential, or identification information. - Do not claim Marco works for, represents, or is endorsed by OpenAI. - Marco Is My Friend is an independent personal project.