Canonical Ontology
Master conceptual model for SpineWorkspace and the IntegrateWise platform
The organizing center is Business Context.
Not AI. Not the Workbench. Not integrations. Not the agent network.
Everything exists to make business context continuously available, projectable, actionable,
governable, executable, and continuous across organizational work.
Spine Fabric is the contextual business-memory and continuity layer making it available to
humans and AI.
1. The Ontology at One Glance
INTEGRATEWISE (integratewise.ai · COMPANY)
└── SPINEWORKSPACE (spineworkspace.com · PRODUCT)
├── BUSINESS CONTEXT — Business Reality · Org Context · Business Memory · Current/Historical State
│ Relationships · Events · Decisions · Evidence · Policies · Commitments
│ Dependencies · Risks · Outcomes
├── SPINE FABRIC — Canonical Spine · Operational Spine · Operational Sandbox · Context Assembly
│ Memory · Continuity · Provenance · Schema · Lineage · Reconciliation · Promotion
├── ORGANIZATION — Org · Business Units · Departments · Teams · People · Roles · Responsibilities
│ Authority · Policies · Goals · Objectives · Standards · Outcomes
├── BUSINESS DOMAINS — Executive · Sales · Marketing · Account Success · TAS · Support/Service
│ Finance · RevOps · BizOps · Product · Engineering · HR · Legal · IT
│ Security/Risk · Procurement · Administration
├── WORK — Objective · Work · Work Graph · Task · Assignment · Decision · Approval
│ Communication · Research · Action · Dependency · Exception · Evidence
│ Execution · Outcome · Continuity
├── PROJECTION — User · Role · Domain · Responsibility · Authority · Permission
│ Industry · Current Work · Relevance · Policy · Context
├── HUMAN WORKBENCH — Personal · Today · My Work · My Queue · Tasks · Inbox · Approvals
│ Communications · Organizational Memory · Knowledge · Work Surfaces · Domain Projections
├── AI WORKSPACE — Twin · Twin Workspace · OODA · Coworker · Triage · Agents
│ Working Memory · Context · Plans · Delegation · Handoffs · Execution State
├── AGENT FABRIC — Twin · Coworker · Triage · Domain · Specialist · Research · Workflow · External Agents
├── CAPABILITY FABRIC — Capability · Registry · Contract · Policy · Inputs · Outputs
│ Evidence Requirements · Execution Binding
├── EXECUTION FABRIC — API · MCP · Spine Tools · Workflow · Pipeline · ADK
│ Agent Runtime · Orchestration · Queue · Worker · Durable Execution
├── GOVERNANCE — Identity · Authority · Permissions · Policy · Risk · Approval · Consent · Evidence · Audit · Accountability
├── CONNECTIVITY — Connector · Provider · API · MCP · OAuth · Credential Ref
│ Webhook · Event · Sync · Schema Ingestion · External Platform
├── MEMORY — Personal · Conversational · Agent · Work · Entity · Organizational Staging · Organizational Published
├── RECONCILIATION — Intent · Execution · Receipt · Actual State · Verification · Reconciliation · Outcome
└── PLATFORM SUBSTRATE — Identity · Configuration · Routing · AI Runtime · Execution Runtime
Communications · Governance Runtime · Infrastructure · Observability
Metering · OmniRoute
2. Dual Hosting / Product Domain Ontology
This is the actual dual-domain model:
| Domain | Represents | Contains |
|---|---|---|
integratewise.ai | IntegrateWise — the company, platform builder, technology provider, corporate authority | Company · Platform · Technology · Solutions · Resources · Documentation · Corporate |
spineworkspace.com | SpineWorkspace — the customer-facing product and work environment | Product · Workspace · Work · Business Domains · Communications · Personal · Twin · Administration |
INTEGRATEWISE (integratewise.ai)
│ builds / operates
▼
SPINEWORKSPACE (spineworkspace.com)
Business domains such as Finance or Sales are inside SpineWorkspace — they are not the
second meaning of dual-domain terminology.
3. Business Context Ontology
| Term | Meaning |
|---|---|
| Business Reality | Complete current + historical state: entities, work, relationships, events, decisions, transactions, commitments, policies, outcomes |
| Business Context | The subset/representation of reality needed to understand or perform particular work |
| Business Memory | Persistent information retained from previous activity |
| Organizational Memory | Governed institutional knowledge surviving sessions and agents — derived from organizational events, decisions, evidence, work outcomes, approved interpretations. NOT raw chat, agent memory, unreviewed extraction, or a bare vector index |
| Continuity | Preservation of coherent work across time, people, systems, teams, sessions, AI actors |
Memory + Current State + Context + Work History = Continuity
4–5. Organization Ontology
The organization is the root business object: identity; structure (business unit → department →
team → function); people (employee, manager, relationship); roles, responsibilities, authority;
goals, objectives, standards, policies; processes, capabilities, outcomes.
Organizational lifecycle:
Need → Goal → Objective → Plan → Work → Assign → Execute → Monitor
→ Decide → Complete → Verify → Reconcile → Outcome → Learn → Continuous Improvement
One shared context. Departments and roles are projection and authority dimensions — never
storage partitions:
ONE ORGANIZATION → CANONICAL SPINE
├─ Sales ─┐
├─ CS ────┼── same Work Graph
└─ Finance┘
Cross-team work uses governed projections of the same Work Graph — no duplicated databases,
no departmental copies of truth.
6. Business Domain Ontology
Domains represent where work belongs: Executive, Sales, Marketing, Account Success, Technical
Account Success, Support/Service, Finance, RevOps, Business Operations, Product, Engineering,
HR, Legal, IT, Security/Risk, Procurement, Administration.
Domain sub-structures (Finance → Billing/Invoices/Payments/AR/AP…; Account Success →
Accounts/Health/Renewals/Escalations…; Sales → Leads/Pipeline/Contracts/Forecast…) are Spine
schema content. Never separate domain truth stores.
7–8. Spine Schema & Schema Synthesis
Spine Schema models organizational reality — not provider APIs: Organization, Person, Team,
Role, Responsibility, Authority, Domain, Goal, Objective, Work, Task, Assignment, Project,
Process, Workflow, Entity, Relationship, Event, Decision, Communication, Evidence, Policy,
Capability, Agent, System, State, Outcome, Continuity.
Synthesis pipeline:
Provider Schema → Mechanical Ingestion → Normalized Raw Schema → Primitive/Field Extraction
→ Semantic Synthesis → Canonical Entity Mapping → Canonical Relationships
→ Spine Schema Registry → Spine
The Schema Generator is NOT "generate an API schema." It is:
translate heterogeneous system representations into the organization's canonical semantic model.
9–13. Entity · Relationship · Event · Decision · Evidence
Entities have identity, attributes, relationships, state, history, provenance, permissions,
domain, source references. Examples: Organization, Person, Account, Contract, Opportunity,
Invoice, Ticket, Work, Task, Workflow, Agent, Capability.
Key relationships: Person→belongs_to→Team, Customer→owns→Account, Contract→generates→Invoice,
Work→assigned_to→Person, Work→delegated_to→Agent, Decision→affects→Work.
Events record changes or occurrences (business/user/work/communication/system/agent/
workflow/governance/approval/execution/reconciliation/memory). An event can produce context —
an event does NOT automatically become canonical memory.
Decisions: maker, context, alternatives, selected option, evidence, authority, timestamp,
consequences, work reference, result. Become org memory only via governance/promotion path.
Evidence: source, references, content, provenance, timestamp, freshness, confidence,
lineage, sensitivity. Evidence is not automatically truth — it supports truth claims or decisions.
14–15. Memory Ontology & Memory Authority
Canonical scopes: Personal · Conversational · Agent · Organizational Staging · Organizational Published.
Runtime vocabulary — Session/User/Work/Entity/Organization memory — are scopes, not interchangeable storage systems.
Promotion rule:
Event/Evidence → Context Assembly → Triage → Candidate → Staging → Governance
→ Approve / Reject / Defer → Canonical Promotion → Organizational Memory → Index/Projection
→ Human + Twin Context
Memory informs organizational truth; it does not silently become organizational truth.
16–18. Triage Ontology
Triage is the cognitive intake and classification boundary. It performs intake, classification,
entity linking, duplicate/conflict/ambiguity detection, sensitivity/materiality/freshness/
completeness assessment, memory-scope classification, governance recommendation, staging.
May write: triage item, candidate, classification, entity links, provenance, confidence,
conflict findings, memory scope, governance recommendation, review state, correlation ID,
causation ID.
May NEVER write: canonical entity state, approved organizational memory, authoritative policy,
permissions, authority grants, canonical relationships, promoted outcomes.
State machine — deliberately no AUTO_APPROVE:
Candidate ── Repair / Reject / Defer
└── Pending Approval ── Reject (terminal) | Approve → Promote → Published
Triage classifies. Governance decides. The Pipeline promotes. Spine owns organizational
memory. Twin consumes the governed result.
19. Projection Ontology
Projection translates shared Spine state into a user-specific view across dimensions:
organization, domain, role, responsibility, authority, permissions, current work, context,
relevance, policy, industry, preferences.
Authenticated User → Gateway/TenantGate → Projection Contract
→ Policy-filtered Spine Read Model → Versioned View Manifest → Workbench
20–23. Work · Work Graph · Assignment · Allocation
Work spans users, domains, systems, and AI actors: objective, desired outcome, current state,
owner, participants, assignments, tasks, decisions, communications, dependencies, constraints,
evidence, actions, agent work, workflow state, approvals, exceptions, execution, results,
reconciliation, continuity.
Work Graph: Goal → Objective → Work → {Tasks, Decisions, Communications, Approvals, Research,
Actions, Exceptions, Dependencies, Agent Assignments, Workflows, Outcomes}.
Assignment targets: Human, Twin, Coworker, Domain Agent, Specialist Agent, Workflow, System,
Human+AI — each with assignee, role, authority, capability, scope, priority, deadline, status,
dependency, evidence requirement, expected outcome.
Work Allocation answers "who or what should perform what now?" from capability,
responsibility, authority, risk, complexity, context, urgency, cost, availability, preference,
historical performance, policy → Human / AI / Agent / System / Human+AI.
24–27. Workbench · Regions · Surfaces · Self-Organizing Workspace
Generated from Business Context + Organizational Memory + Role + Responsibility + Domain +
Authority + Current Work + User Preferences + Twin State.
Regions:
| Region | Contents |
|---|---|
| Orientation | Home · Today · My Work · My Queue |
| Personal | Notes · Projects · Calendar · Activity |
| Communication | Email · Chat · Meetings · Calls · Documents |
| Organizational Memory | Decisions · Documents · Policies · Processes · Knowledge · Meeting Memory · Work History |
| Work | Active · Waiting · Approval · Delegated · Blocked · Completed |
| Domain Workspaces | Sales · Finance · Customer Success · … |
Work Surface modes: Grid, Board, Canvas, Timeline, Entity View, Workflow View, Dashboard, Feed,
Calendar. A surface is a representation of Work and Business Context — not the entity itself.
Self-organizing ≠ an LLM randomly rearranging UI. The workspace is contextually projected from
intent, role, responsibility, active work, capabilities, context, changes, governance.
Boundary: personal/reversible adaptation may be automatic; shared/consequential requires governance.
Allowed silently: view order, density, prefetch, cache, notification ranking, capability placement.
Never silent: canonical schema, canonical truth, permissions, authority, governance thresholds,
institutional memory, shared structures, workbench taxonomy.
28–32. Twin · Twin Workspace · Coworker · Agents · Handoffs
Twin lifecycle:
Receive Intent → Access Context → Reason → Plan → Allocate → Delegate
→ Invoke Capabilities → Monitor → Handle Exceptions → Communicate → Report → Maintain Continuity
Twin Workspace = AI operating surface (context, current work, tasks, plans, decisions,
delegation, agent assignments, tool calls, workflow runs, communications, evidence, results,
artifacts, working memory) — not canonical organizational memory.
Coworker = contextual companion at the human's active surface: observation, retrieval,
preparation, communication support, workflow assistance, screen/surface context, Twin sync.
Agent anatomy: identity, purpose, capability, context scope, authority scope, tenant scope,
policy, evidence requirements, work input/output, reconciliation. Types: Twin, Coworker,
Triage, Domain, Specialist, Research, Workflow, External. Handoffs transfer work context —
never ownership of organizational memory. Handoff payload includes request ID, work ID,
capability, context reference, result, status, evidence, actions taken, errors, confidence,
timestamp, attribution, recommended next step. Twin validates before incorporating.
33–34. Context Assembly & AI Boundary
Context Assembly produces minimum sufficient relevant context:
Spine → Context Assembly → Permission → Purpose → Freshness → Relevance filters
→ Operational Context
Never dump the entire Spine into the model.
CANONICAL SPINE ──(never direct)──► CONTEXT ASSEMBLY ──► filters ──► OPERATIONAL SANDBOX
├─ Twin · Coworker
├─ Domain Agents
└─ External Agents
Both human and AI projection paths are governed. The Twin never queries canonical Spine directly.
35–36. Capability & Execution
Capability = businessly meaningful action (retry_payment, approve_discount,
send_customer_message…) containing ID, description, inputs, outputs, required context,
required authority, risk, evidence requirement, policy, available implementations.
Execution mechanisms (API/MCP/Spine Tool/Workflow/Pipeline/ADK/Orchestrator/Provider SDK) are
invisible to the user:
User Intent → Capability → Governance → Execution Binding → Execution
37–40. Governance · Communication · Lifecycle · Reconciliation
Governance decides whether an action may occur; Intelligence decides what might be a good
action.
Communication is part of Work and can create evidence, decisions, assignments, approvals,
commitments, work events.
Execution lifecycle — provider success is not enough:
Intent → Plan → Capability → Governance → Execution → Receipt → Verification
→ Reconciliation → Outcome
Reconciliation states: Confirmed · Failed · Unknown · Divergent · Partially Complete · Pending
Reconciliation.
41–42. Operational vs Canonical · Storage Ownership
Operational Spine is the state of the machine. Canonical Spine is the state of the business.
Spine Cache = default agent read surface — not truth, never a write target.
Storage by ownership and authority (physical techs are implementation details):
| Layer | Contents |
|---|---|
| CANONICAL | entities · relationships · lineage · schema · work · governance · audit · published memory |
| RAW / EVIDENCE | files · attachments · raw payloads · immutable evidence |
| DERIVED | embeddings · search index · retrieval index |
| OPERATIONAL | active context · idempotency · runtime state · projection snapshots · sync state |
| CACHE | sessions · hot projections · connector state · invalidations |
43–45. Documentation · Repository · Apps
Canonical document hierarchy: Doctrine → Business Context/Spine Ontology → Org Memory → Spine
Schema → Projection Contract → Work Graph/Allocation → Spine Workbench → Twin/AI Workspace →
Triage → Agent Fabric → Capability Fabric → Execution Fabric → Governance → Connectivity →
Reconciliation → Platform Architecture → Implementation Reality → ADRs → Runbooks → API Contracts.
Apps are surfaces; services/packages/infrastructure implement the ontology. Target service
taxonomy: spine, context, projections, work, twin, triage, coworker, agents, governance,
reconciliation, orchestration. App mapping: web → User Workbench + Twin Workspace; mobile →
Mobile Workbench; portfolio → Executive Projection; one-access(+console) → Identity;
platform → Customer Platform Admin; platform-console → IW Platform Operations.
46–48. Views · Interaction Model · User–Twin Lifecycle
Three views: User ("what do I need to know and do?" → Workbench + Twin) · Operator
("how is the work being executed?" → Platform Console) · System ("how is infrastructure
functioning?"). Users never need the system view.
Interaction model (operational semantics, expressible via clicks/chat/NL/Slack/email/approval
surfaces):
STORE → ASK → DECIDE → APPROVE/REJECT/MODIFY/CONSULT → EXECUTE → VERIFY → RECONCILE → CONTINUE
Canonical User–Twin Lifecycle:
USER → WORKBENCH → INTERACTION → COWORKER CONTEXT GATHERING → TWIN OBSERVE
→ SPINE CONTEXT ASSEMBLY → TWIN ORIENT → CONTEXT PROJECTION → USER REVIEW → USER DECISION
→ TWIN RE-ORIENT → WORK ALLOCATION → AGENT/WORKFLOW/CAPABILITY → GOVERNANCE → EXECUTION
→ SOURCE SYSTEM → RECEIPT → RECONCILIATION → SPINE CONTINUITY → TWIN → USER
49–50. Learning & Auto-Tuning
Learning: Observation → Pattern → Learning → Adaptation → Suggestion → Governance → Action.
The Twin may learn preferences, communication styles, escalation paths, successful workflows,
agent performance, recurring patterns. Learning NEVER overrides permissions, authority, policy,
governance, canonical truth.
Auto-tuning boundary:
Personal and reversible may adapt; shared and consequential requires approval.
51–52. Relationship Graph & Product Loop
ORGANIZATION → owns goals, defines objectives/people/roles/policies → WORK GRAPH realizes
objectives, connects entities, assigns humans/Twin/agents, generates decisions/communications,
requires approvals, invokes capabilities, produces evidence, reaches OUTCOME → RECONCILIATION
→ SPINE → CONTINUITY/MEMORY.
Complete product loop:
BUSINESS PURPOSE → NEED → GOAL/OBJECTIVE → WORK → BUSINESS CONTEXT → SPINE FABRIC
→ CONTEXT ASSEMBLY → PROJECTION → WORKBENCH ↕ TWIN → ALLOCATION → HUMAN/AI/HUMAN+AI
→ GOVERNANCE → CAPABILITY → EXECUTION → SOURCE SYSTEM → ACTUAL STATE → RECONCILIATION
→ OUTCOME → ORGANIZATIONAL MEMORY → LEARNING → NEXT WORK
53. The Architecture in One Sentence
IntegrateWise builds SpineWorkspace, a human–AI work coordination platform centered on Spine
Fabric—the contextual business memory and operational continuity layer through which fragmented
organizational reality is normalized, assembled into relevant Business Context, projected by
role and responsibility into the Spine Workbench, consumed by a user's bounded Twin through an
operational sandbox, coordinated across Coworker, Triage, agents, capabilities and workflows,
governed before consequential action, executed across connected systems, reconciled against
actual state, and returned to organizational continuity as the basis for the next piece of work.
54. The Deepest Ontological Question
For this organizational need, objective, work, user, role, domain, context, and moment: what
should the human do, what should the Twin do, what should they do together, what should be
delegated, what is authorized, what is missing, what needs to happen next — and how do we know
the business outcome actually occurred?
Foundational law:
Business Context is the center. Spine Fabric preserves and serves that context. Human and AI
operate on governed projections of it. Work is shared. Authority is governed. Execution is
reconciled. Continuity is preserved.