{"slug":"architecture/WORKBENCH_DOCTRINE","title":"Workbench Doctrine","section":"architecture","sectionLabel":"Architecture","status":"unclassified","type":"document","path":"architecture/WORKBENCH_DOCTRINE.mdx","bytes":7273,"description":null,"updated":null,"source":"integratewise/Integratewise-docs-wiki","content":"\n> **Status:** Canonical architecture doctrine\n> **Date:** July 12, 2026\n> **Authority:** Nirmal (Founder)\n> **Supersedes:** All prior Workbench product doctrine\n> **Canonical Reference:** [CANONICAL_PLATFORM_ARCHITECTURE.md](./CANONICAL_PLATFORM_ARCHITECTURE.md)\n\n> The Workbench is the primary operating surface of IntegrateWise.\n\nPeople do not work inside applications.\nAI does not work inside applications.\nGovernance does not happen inside applications.\n\nEverything operates through governed **Work** that projects continuity from the Adaptive Spine.\n\nApplications become capabilities rather than destinations.\n\nWork is never the system of record.\nWork never owns canonical truth.\nWork projects governed context into the appropriate experience.\n\n---\n\n## Core Doctrine\n\n> **Truth you own. AI you rent. Approval in between.**\n\nThe organization owns its operational truth in the Adaptive Spine. The Twin provides rented intelligence — reasoning, drafting, retrieval, and proposals — but never gets a direct Act button. Every consequential execution is gated by human approval and by Governance.\n\n---\n\n## L1 Target\n\nThe human product is a single L1 Workbench.\n\nIntelligence is a silent partner inside L1. Governance appears when policy requires it. L2/L3 are panel states inside L1, not separate product boundaries.\n\n## Product grammar\n\n```text\nCONTEXT LENS\n→ ENTITY COLLECTION\n→ ENTITY 360\n→ ACTIVITY\n→ CONTEXTUAL INTELLIGENCE\n→ ACTION\n→ GOVERNANCE WHEN REQUIRED\n→ EXECUTION STATE\n→ CONTINUITY\n```\n\n---\n\n## The Four-Button OODA Grammar\n\nThe User Workbench interaction model is exactly four canonical buttons, mapped directly to the OODA loop. These are the universal interaction grammar across **every Workbench** — not domain-specific action button chaos.\n\n| OODA    | Canonical Action   | Button                    | System Meaning                                                                                |\n| ------- | ------------------ | ------------------------- | --------------------------------------------------------------------------------------------- |\n| Observe | Capture truth      | **Store in Spine**        | Persist context, evidence, decision, note, or artifact into canonical Digital Memory.         |\n| Orient  | Understand context | **Ask Your Twin**         | Query the Twin using current workspace + Continuity Bridge + Spine context.                   |\n| Decide  | Delegate intent    | **Assign Your Twin**      | Give the Twin an objective to plan, reason, draft, or prepare an action.                      |\n| Act     | Govern execution   | **Approve Twin's Action** | Human approval authorizes Hermes / capability execution. Twin never gets a direct Act button. |\n\n### The Critical Authority Boundary\n\n```\nSTORE\nUser ────────────────► Spine\n\nASK\nSpine + Context ─────► Twin ─────► Insight\n\nASSIGN\nUser ────────────────► Twin ─────► Proposal\n\nAPPROVE\nHuman ───────────────► Governance ─────► Hermes ─────► Capability\n```\n\nThe fourth button is deliberately **Approve Twin's Action** — not Run Twin, not Execute, not Automate. That is what preserves the doctrine:\n\n> **Truth you own. AI you rent. Approval in between.**\n\n`Store → Ask → Assign → Approve` is the OODA loop made executable on every Workbench.\n\n---\n\n## Workbench UI\n\n```\n┌──────────────────────────────────────────────────────────────────┐\n│ ACCOUNT SUCCESS                                      Acme Corp   │\n│ Context: Renewal · Q3 · At Risk                                  │\n├──────────────────────────────────────────────────────────────────┤\n│                                                                  │\n│                        WORKBENCH                                 │\n│                                                                  │\n│   [ Store in Spine ]   [ Ask Your Twin ]                         │\n│        OBSERVE              ORIENT                                │\n│                                                                  │\n│   [ Assign Your Twin ] [ Approve Twin's Action ]                 │\n│         DECIDE                 ACT                                │\n│                                                                  │\n├──────────────────────────────────────────────────────────────────┤\n│ OODA  ● Observe ─── ○ Orient ─── ○ Decide ─── ○ Act             │\n└──────────────────────────────────────────────────────────────────┘\n```\n\n---\n\n## Projection Principle\n\nEvery projection is a view over the same governed platform.\n\nNo projection owns data.\nNo projection owns truth.\nEvery projection reads from the same governed platform.\nDifferent projections expose different perspectives over the same organizational continuity.\n\n---\n\n## Context Lens Doctrine\n\n```text\nSAME ENTITY\n+\nDIFFERENT CONTEXT LENS\n=\nDIFFERENT OPERATIONAL EMPHASIS\n```\n\nContext Lenses include Account Success, Revenue Operations, Sales Operations, Finance, Marketing, HR/People, Product and Engineering, Business Operations, IT Administration, Services, and Procurement. These are role, department, industry, and capability clusters, not separate product boundaries unless separately authorized.\n\n---\n\n## Twin Inside L1\n\nTwin is a silent partner inside L1, not a separate product interface.\n\nThe Twin works alongside the user with durable memory, session continuity, and governed context. Users **Observe** by storing truth in the Spine, **Orient** by asking their Twin, **Decide** by assigning their Twin, and **Act** by approving the Twin's proposed action.\n\nProposals accumulate as a badge count on \"Approve Twin's Action.\" The user pulls them when ready. No pop-ups, no chat window, no \"How can I help?\" greeting.\n\n---\n\n## Constitutional Principles\n\n1. The human product is L1.\n2. Every projection is a projection.\n3. No projection owns canonical truth.\n4. Every projection consumes governed context.\n5. Context Lenses share one Adaptive Spine.\n6. Governance protects all projections equally.\n7. Applications remain replaceable; the Work remains consistent.\n8. The OODA Grammar (Store → Ask → Assign → Approve) is universal across every Workbench.\n\n---\n\n## Doctrine Replacement\n\nThis replaces prior multi-Workbench product doctrine, separate Human/Twin/Governance/Knowledge/Domain Workbench product boundaries, and any frontend doctrine that treated role-specific surfaces as separate products.\n\nThe L1 Workbench canon is:\n\n- `CANONICAL_PLATFORM_ARCHITECTURE.md`\n- `PRODUCT_ARCHITECTURE.md`\n- `WORKBENCH_DOCTRINE.md`\n"}