{"slug":"index","kind":"manifesto","title":"civ.build","summary":"A public knowledge contract where serious pages are written once, rendered for humans, and exposed to agents through explicit compact and full retrieval layers.","compact_summary":"civ.build is not a generic AI site. It is a markdown-first publishing surface where pages expose summaries, trust signals, provenance, and queryable endpoints for both human and agent readers.","key_claims":["The next layer of the web is a public knowledge contract for agents, not just prettier HTML or random AI widgets.","Good agent-facing pages should expose compact summaries, freshness, confidence, change history, and retrieval routes.","Serious content is the moat; infrastructure only matters if it helps agents discover, trust, and use that content correctly."],"section_map":["Why this exists","What the contract includes","Flagship pages","Build direction"],"confidence":"high","intended_use":["Use this page to understand what civ.build is and how the public surface is meant to work.","Use the linked flagship pages for the deeper worldview."],"do_not_use_for":["Do not treat this site as a hosted long-term memory system for autonomous agents.","Do not assume every page is a final truth claim; many are explicit working theses."],"updated_at":"2026-04-10T00:00:00.000Z","verified_at":"2026-04-10T00:00:00.000Z","version":"0.2.0","estimated_tokens":609,"word_count":451,"content_hash":"bda5b9f51aee6aec1dff9546045abccea7cf2ca78b3c66fee66bcceec51c06d4","change_summary":"Added the forked-internet-for-agents framing and agent economy direction alongside the public knowledge contract thesis.","requires_human_judgment":false,"tags":["agentic-web","manifesto","agent-readable-web"],"_links":{"self":"/api/v1/content/index","compact":"/api/v1/content/index/compact","meta":"/api/v1/content/index/meta","raw":"/api/v1/content/index/raw","versions":"/api/v1/content/index/versions","related":["/api/v1/content/public-knowledge-contracts-for-agents/compact","/api/v1/content/agent-seo-and-discovery/compact","/api/v1/content/context-lifecycle-for-ai-systems/compact"],"canonical_human":"/p/index","capabilities":"/api/v1/capabilities"},"content":"# civ.build\n\nThe current web mostly assumes that readers are people staring at a screen. Autonomous agents can still use it, but they have to scrape layout, infer structure, and waste context on presentation noise.\n\nciv.build is a bet on the next layer: public pages should be readable by humans and legible to agents without guesswork.\n\n## Why This Exists\n\nThis project is not trying to add random AI features to a normal site. The goal is narrower and stronger:\n\n- write serious pages with real ideas\n- expose them through explicit contracts\n- make freshness, confidence, and boundaries visible\n- let agents read the shortest useful layer first\n\nThat is why the site is markdown-first and why the API is built around the same content source as the human surface.\n\n## What The Contract Includes\n\nEach serious page should increasingly provide:\n\n- a one-paragraph summary\n- a compact machine-friendly summary\n- key claims\n- a section map\n- updated and verified timestamps\n- confidence and intended-use boundaries\n- sources and change summaries\n- compact, full, meta, raw, search, and version routes\n\nThe point is not to sound futuristic. The point is to reduce ambiguity for both humans and agents.\n\n## Flagship Pages\n\n- [Context Lifecycle for AI Systems](/p/context-lifecycle-for-ai-systems)\n- [Trustworthy Co-Thinker vs Eager Executor](/p/trustworthy-co-thinker-vs-eager-executor)\n- [Agent SEO and Discovery](/p/agent-seo-and-discovery)\n- [Local-First Knowledge Systems](/p/local-first-knowledge-systems)\n- [Public Knowledge Contracts for Agents](/p/public-knowledge-contracts-for-agents)\n- [Memory Consolidation and Sleep Loops](/p/memory-consolidation-and-sleep-loops)\n- [The Agent Economy](/p/the-agent-economy)\n- [Data Accumulation as an Asset](/p/data-accumulation-as-an-asset)\n\n## The Longer Vision\n\nThe more complete long-term version of this is almost a forked internet for agents: APIs, structured data, markdown content, payment protocols, and execution environments. Agents would not need a browser. They would want a JSON payload with price, availability, a payment endpoint, and content.\n\nPayment rails are part of this picture. Coinbase 402, agentic wallets, Stripe's agent-facing commerce direction, and universal commerce protocols all point at the same possibility: bots are not just readers, they may become purchasers. That means a site like this is not only about content discoverability — it may eventually need pricing, entitlement, and payment logic that works for non-human clients.\n\nThat layer is not built yet, and intentionally so. The first job is to prove the thesis with real content and explicit contracts. Commerce comes after trust.\n\n## Build Direction\n\nThe next layer of work is straightforward:\n\n1. Publish serious content instead of placeholder pages.\n2. Expose discovery files and compact retrieval.\n3. Add versions, feedback, and usage signals so the surface can improve.\n4. Explore agent-facing payment and commerce once trust and content are solid.\n\nThe result should feel less like \"a website with JSON\" and more like a trustworthy knowledge interface that agents can discover, route through, and use correctly.","author":"civ.build","sources":[],"related_pages":["public-knowledge-contracts-for-agents","agent-seo-and-discovery","context-lifecycle-for-ai-systems"],"canonical_url":null,"license":null,"contact":null,"status":null,"audience":["humans","agents"],"agent_takeaway":{"type":"learned","content":"civ.build treats each page as a trustworthy public knowledge contract with compact retrieval, provenance, trust boundaries, and machine-friendly discovery."}}