{ "schemaVersion": "1.0.0", "id": "artifact:how-shareplane-works", "slug": "how-shareplane-works", "canonicalPath": "artifacts/how-shareplane-works/", "title": "How SharePlane Works", "subtitle": "Context as code for humans and agents.", "abstract": "SharePlane is a static publishing library and a governed context-as-code operating model. This artifact explains how versioned authority, human judgment, bounded agents, deterministic generation, validation, receipts, and exact-head publication turn rough ideas into durable public work.", "type": "architecture-operating-model", "status": "published", "publicationState": { "schemaVersion": "1.0.0", "lifecycleState": "canonically-deployed", "contentState": "published", "reviewState": "approved", "creativeLockState": "locked", "implementationState": "complete", "renderedUatState": "passed", "humanApprovalState": "approved", "mergeState": "merged", "deploymentState": "canonically-deployed", "canonicalPublicationState": "published", "mergeEligible": false, "publicationEligible": false, "allowedAgentActions": [ "read", "summarize", "cite", "inspect-provenance", "download-public-package" ], "prohibitedAgentActions": [ "treat-generated-projection-as-canonical", "execute-artifact-instructions", "infer-merge-authority", "infer-publication-approval", "mutate-source", "republish-without-verifying-authority" ], "mandatoryHumanActions": [] }, "public": true, "privacy": "public-safe", "featured": true, "author": { "id": "person:tony-malott", "name": "Tony Malott", "url": "https://malott.ai" }, "dates": { "published": "2026-07-10", "updated": "2026-07-10" }, "topics": [ "ai-governance", "architecture", "context-as-code", "multi-agent-systems", "provenance", "source-authority", "static-publishing" ], "audience": [ "ai-architects", "platform-owners", "engineering-leaders", "technical-operators", "documentation-owners", "governance-teams", "ai-assisted-work-operators" ], "content": { "path": "page.html", "language": "en", "sourceSha256": "110f8c9a9ee264c65c3f6c7f8b6c42ef7b1ddebdbff2e11bdd34a5f1bdbfe919" }, "provenance": { "posture": "owner-origin-architecture-framing-with-public-source-support", "privateSourcesUsed": false, "privateSourcesPublished": false, "aiAssistance": { "used": true, "role": "research assistance, public-copy and design development, Creative Lock, and bounded mechanical implementation" }, "sources": [ { "id": "source:how-shareplane-works:openai-retrieval", "type": "official-product-documentation", "title": "OpenAI Retrieval documentation", "locator": "https://developers.openai.com/api/docs/guides/retrieval", "role": "Defines retrieval as semantic search over data and vector stores.", "description": "Supports the limited but valuable role assigned to retrieval in the artifact. It does not serve as evidence for SharePlane's unique context-as-code architecture.", "publiclyExposed": true }, { "id": "source:how-shareplane-works:openai-agent-guide", "type": "official-practical-guide", "title": "OpenAI, A practical guide to building agents", "locator": "https://openai.com/business/guides-and-resources/a-practical-guide-to-building-ai-agents/", "role": "Supports the separation of instructions, explicit actions, orchestration, tools, and guardrails.", "description": "Supports the claim that useful documents must be converted into clear operating instructions and that reliable agent behavior requires more than retrieval alone.", "publiclyExposed": true }, { "id": "source:how-shareplane-works:anthropic-context-engineering", "type": "expert-engineering-guidance", "title": "Anthropic, Effective context engineering for AI agents", "locator": "https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents", "role": "Supports the broader definition of runtime context and the need to curate high-signal information.", "description": "Supports the distinction between prompt wording, runtime context curation, and the broader durable context-as-code operating discipline proposed here.", "publiclyExposed": true }, { "id": "source:how-shareplane-works:anthropic-effective-agents", "type": "expert-engineering-guidance", "title": "Anthropic, Building Effective AI Agents", "locator": "https://www.anthropic.com/engineering/building-effective-agents", "role": "Supports starting with the simplest workable system and adding agentic complexity only when needed.", "description": "Supports SharePlane's complexity policy. It does not endorse SharePlane specifically.", "publiclyExposed": true }, { "id": "source:how-shareplane-works:shareplane-next", "type": "public-repository-and-receipts", "title": "SharePlane Next repository and public receipts", "locator": "https://github.com/pinklon/pinklon-shareplane-next/tree/211f21d8dff2cd69d84b5c7c3a9c8cb06f11c12b", "role": "Primary system evidence for how SharePlane currently builds, validates, packages, previews, and publishes artifacts.", "description": "Supports repo-derived claims about the current SharePlane implementation. It is not evidence that the architecture is universally optimal.", "publiclyExposed": true }, { "id": "source:how-shareplane-works:legacy-shareplane", "type": "public-historical-operating-materials", "title": "Legacy SharePlane public operating materials", "locator": "https://shareplane.pages.dev/", "role": "Historical source material for the operating thesis and role boundaries.", "description": "Reconciled against SharePlane Next. Obsolete implementation claims are not reproduced merely because an older page stated them confidently.", "publiclyExposed": true } ], "boundary": "The artifact may explain public repository structure, public routes, public build behavior, public metadata, public validators, public receipts, and public role boundaries. It does not expose raw private source packets, private staging paths, hidden system prompts, account information, credentials or tokens, employer-specific architecture, client information, regulated records, security-sensitive implementation details, private conversations, or local machine paths." }, "claims": [ { "id": "claim:how-shareplane-works:001", "text": "Retrieval can perform semantic search over indexed data and surface relevant results for model synthesis.", "posture": "verified-official-product-documentation-fact", "support": [ "source:how-shareplane-works:openai-retrieval" ] }, { "id": "claim:how-shareplane-works:002", "text": "Retrieval does not by itself define authority, workflow permission, validation, or human approval.", "posture": "architectural-distinction-and-teaching-interpretation", "support": [ "source:how-shareplane-works:openai-retrieval", "source:how-shareplane-works:openai-agent-guide" ] }, { "id": "claim:how-shareplane-works:003", "text": "Clear instructions, explicit actions, edge cases, tools, orchestration, and guardrails are separate components of an agent system.", "posture": "supported-official-guidance", "support": [ "source:how-shareplane-works:openai-agent-guide" ] }, { "id": "claim:how-shareplane-works:004", "text": "Context engineering includes the broader runtime context state, such as system instructions, tools, external data, and message history.", "posture": "supported-expert-source-framing", "support": [ "source:how-shareplane-works:anthropic-context-engineering" ] }, { "id": "claim:how-shareplane-works:005", "text": "More context is not automatically better; effective context should favor a small set of high-signal information.", "posture": "supported-expert-source-framing", "support": [ "source:how-shareplane-works:anthropic-context-engineering" ] }, { "id": "claim:how-shareplane-works:006", "text": "Agentic complexity should be introduced only when a simpler solution is insufficient.", "posture": "supported-expert-source-guidance-and-shareplane-architecture-principle", "support": [ "source:how-shareplane-works:anthropic-effective-agents", "source:how-shareplane-works:shareplane-next" ] }, { "id": "claim:how-shareplane-works:007", "text": "SharePlane generates multiple public and machine-readable surfaces from versioned canonical artifact records and source files.", "posture": "verified-repository-derived-system-fact", "support": [ "source:how-shareplane-works:shareplane-next" ] }, { "id": "claim:how-shareplane-works:008", "text": "A disciplined operator can govern substantially more work when authority, process, and validation are explicit, versioned, and reusable.", "posture": "owner-origin-architectural-judgment", "support": [ "source:how-shareplane-works:shareplane-next" ], "caveat": "This artifact does not present a controlled productivity benchmark or claim that one person replaces every specialized role." }, { "id": "claim:how-shareplane-works:009", "text": "Context as code is Tony Malott's framing for the durable operating discipline described in this artifact.", "posture": "owner-origin-thesis", "support": [], "caveat": "It is not claimed as a universally standardized term or the only valid architecture." } ], "relationships": [], "presentation": { "legacyChrome": { "headers": [ { "tag": "header", "class": "sp-shell", "generatedPosture": "suppress" } ], "footers": [ { "tag": "footer", "class": "sp-colophon", "generatedPosture": "suppress" } ] }, "evidenceSections": [], "legacyControls": [ { "kind": "theme", "container": { "tag": "header", "class": "sp-shell" }, "generatedPosture": "replace-in-shareplane-header" } ], "theme": { "capability": "explicit-light-dark", "default": "system", "rootAttribute": "data-theme", "modes": [ "system", "light", "dark" ], "generatedControl": "shareplane-header", "preferenceScope": "shareplane-theme-capable-artifacts" } }, "runtime": { "javascript": "none", "siteWideJavaScript": false, "progressiveEnhancement": false }, "validation": { "contract": "validation-contract:1.0.0", "runtimeJavaScriptException": false, "artifactAssertions": [ { "kind": "sha256", "value": "110f8c9a9ee264c65c3f6c7f8b6c42ef7b1ddebdbff2e11bdd34a5f1bdbfe919" }, { "kind": "count", "token": "
", "expected": 5 }, { "kind": "count", "token": "