{ "abstract": "The dominant interface for artificial intelligence collapses exploration, commitment, execution, and review into one conversation. This is convenient for short tasks and cognitively expensive for serious projects. A casual thought can look like a directive. A model proposal can be remembered as a user decision. A worker result can replace an accepted artifact. The user must reconstruct current state across chats, providers, files, devices, and tools. Glyph Desk is a human-centered project environment built around three permanent synchronized lenses over one durable Project Core: - Chat: understand, explore, question, and evaluate; - Plan: decide, constrain, structure, and authorize; - Make: execute, inspect, verify, refresh, and deliver. The machine unifies state. The interface separates responsibility. Conversation must cross a boundary before becoming intent. Intent must cross another boundary before becoming consequential action. Accepted and working results remain separate. Models and providers rent scoped project context; the user owns the Project Core. ZEKE can continuously reduce the gap between Plan and working result only within explicit authority, budget, and evidence gates. Glyph Desk is not differentiated by three columns. It is differentiated by the contracts underneath them.", "author": "Hayden Lindley", "category": "Operational Systems", "claims": { "claims": [ { "claim_id": "P22-C01", "evidence_refs": [ "P22-S01", "P22-S02" ], "limitations": [ "Unified production implementation remains to be verified." ], "public": true, "scope": "Master product architecture.", "statement": "Glyph Desk defines Chat, Plan, and Make as persistent synchronized lenses over one Project Core with explicit promotion and authority boundaries.", "status": "SPECIFIED" }, { "claim_id": "P22-C02", "evidence_refs": [ "P22-S01", "P22-S03", "P22-S05" ], "limitations": [ "Connector implementations and migration require evidence." ], "public": true, "scope": "Non-destructive/provider-independent contract.", "statement": "Accepted and working results remain separate and providers operate through scoped bindings rather than owning project state.", "status": "SPECIFIED" }, { "claim_id": "P22-C03", "evidence_refs": [ "P22-S01", "P22-S04" ], "limitations": [ "No accepted user study is published." ], "public": true, "scope": "Multi-session comparative study.", "statement": "Chat–Plan–Make reduces cognitive load and project errors compared with ordinary provider chats.", "status": "AWAITING_LOCAL_RUN" } ], "disclosure_note": "Claims marked non-public in the authored ledger are omitted from this public artifact.", "paper": "p22-glyph-desk", "version": "0.1.0", "withheld_claim_count": 0 }, "date": "2026-07-27", "diagrams": { "diagrams": [ { "brief": "Blue Chat, green Plan, amber Make around one Project Core, with explicit transition gates.", "format": "svg", "id": "P22-F01", "path": "/diagrams/p22-glyph-desk/P22-F01.svg", "status": "source-generated conceptual architecture", "title": "Three lenses, one core" }, { "brief": "Accepted immutable reference, evolving working result, candidates, evidence, and promotion.", "format": "svg", "id": "P22-F02", "path": "/diagrams/p22-glyph-desk/P22-F02.svg", "status": "source-generated conceptual architecture", "title": "Non-destructive result model" }, { "brief": "Multiple AI/tool providers connect through scoped bindings to one Project Core.", "format": "svg", "id": "P22-F03", "path": "/diagrams/p22-glyph-desk/P22-F03.svg", "status": "source-generated conceptual architecture", "title": "Provider bindings" }, { "brief": "Capture → interpretation → Plan → Work Order → Return → Verification → Acceptance → Receipt → Home/Library projection.", "format": "svg", "id": "P22-F04", "path": "/diagrams/p22-glyph-desk/P22-F04.svg", "status": "source-generated conceptual architecture", "title": "End-to-end accepted act" } ], "paper": "p22-glyph-desk" }, "evidence_state": "SPECIFIED", "id": "p22-glyph-desk", "institution": "Glyphd Labs", "integrity": { "claim_ledger_sha256": "9f81117c7d6ea9788fa1e2df5fa7f9585440218094dcc7fcf6599fd23a9c5d7c", "paper_mdx_sha256": "c9c436924a91a122bc78d7dbe263beed92231a39c2f4d47bf34d39118441799d" }, "public_disclosure_boundary": "This edition publishes the public-safe product architecture and interaction contracts. It excludes private project data, connector secrets, unpublished commercial details, internal provider agreements, and patent-claim drafting. It does not claim that a unified production Glyph Desk has already passed the full accepted-act gate.", "publication_class": "public-safe working paper", "publication_url": "https://www.glyphd.com/papers/p22-glyph-desk", "revisions": { "paper": "p22-glyph-desk", "revisions": [ { "date": "2026-07-27", "summary": "First synthesized public-safe institute edition compiled from the Glyphd project corpus.", "version": "0.1.0" } ] }, "schema_version": "1.0.0", "slug": "p22-glyph-desk", "sources": { "notes": "Internal source paths are provenance references. Public publication must expose only approved public-safe excerpts or archived public artifacts.", "paper": "p22-glyph-desk", "sources": [ { "date": "2026-07-12", "id": "P22-S01", "path": "GLYPH-DESK-MASTER-SPEC.v1.md", "title": "Glyph Desk Master Specification v1" }, { "date": "2026-07-13", "id": "P22-S02", "path": "CHAT-PLAN-MAKE_Approval_Package_v1.pdf", "title": "Chat–Plan–Make Approval Package" }, { "date": "2026-07-18", "id": "P22-S03", "path": "ZEKE-V1-CANON-RECOVERY-AND-GAP-AUDIT-v0.1.md", "title": "Glyphd V1 Canon Recovery and Gap Audit" }, { "date": "2026-07-18", "id": "P22-S04", "path": "GLYPHD-V1-MASTER-SPEC-LOCKS-AND-EXPERIMENT-PLAN-v0.1.md", "title": "Glyphd V1 Master-Spec Locks and Experiment Plan" }, { "date": "2026-07-20", "id": "P22-S05", "path": "Pasted text.txt", "title": "Native Accepted Act build directives" } ], "version": "0.1.0" }, "subtitle": "A human-centered AI project environment with one durable Project Core and three role-separated lenses", "title": "Chat · Plan · Make", "version": "0.1.0" }