AI Overlap Check

LIVE

Full Overlap

2 / 8

delegate to the agent platform

Partial / Minimal

2 / 8

Cockpit grounds the answer

No Overlap

4 / 8

Cockpit-unique capability

Recommendation

Delegate

do not duplicate agent strengths

Capability Overlap Matrix

CPM AI Cockpit vs. Claude Enterprise vs. Coworker.ai

Cockpit capabilityClaude EnterpriseCoworker.aiVerdictAssessment
Chat / Q&A over documentsYes — native strengthPartial (via OM1 context)Some overlapCockpit's chat layer is grounded in live spend and supplier data, not general documents
Cross-module data joins (GraphQL, REST)No — no ERP/finance connectors nativelyNo — connectors are Jira/Slack/CRM, not SAP/AribaNo overlapThis is the core gap the Cockpit closes
Read-only adapters to 30+ finance / register systemsNoneNoneNo overlapNeither platform has finance-grade system-of-record connectors (Ariba, S/4HANA, DED, D&B)
Monte Carlo, VaR/CVaR, FX and commodity shock simulationNo — can compute if manually fed data, no simulation engineNo — task/workflow orchestrator, not a quant engineNo overlapProprietary CPM AI engine is unique
19-chain causal / scenario pathway modellingNo — can narrate a scenario, no structured causal engineNoNo overlapNo driver library outside the Cockpit
Governance: KPI dictionary, source lineage, data-vintage stampingNoPartial — OM1 context memory, no KPI governanceMinimal overlapCockpit remains the governed source of truth
Task automation / drafting emails / following upYesYes — core strengthFull overlapExactly what Coworker.ai already does well — delegate, do not rebuild
General business writing, summarisation, coding helpYesPartialFull overlapClaude Enterprise's bread and butter — delegate, do not rebuild

Coverage by Capability

2 = native capability · 1 = partial · 0 = none

Where Full Overlap Exists

Two capabilities — delegate rather than rebuild

Full overlap · Coworker.ai

Task automation, email drafting, deal & issue follow-up

Do not build a workflow engine in the Cockpit. Emit the existing webhook events — Maverick Spend Detected, Reconciliation Mismatch, Financial Health Deterioration, ESG Assurance Expiring, Contract Compliance Breach — and let Coworker.ai run the follow-up sequence with the supplier or category owner.

Cockpit role · Signal producer — detects, scores and stamps the event

Full overlap · Claude Enterprise

General writing, summarisation, narrative reporting, coding help

Do not build a general chat product. Expose a read-only, RBAC-scoped connector over /api/v1/spend/*, /api/v1/suppliers/* and /api/v1/metrics/* so Claude answers are grounded in live Cockpit data with source lineage and data-vintage stamping.

Cockpit role · Grounded data provider — governed, versioned, auditable

Recommended Integration Surface

How each agent platform plugs into the existing API layer

ToolProtocolAuthScopesData returnedLimitsAudit
Claude EnterpriseMCP server / REST (read-only)OIDC service identity via Azure AD, short-lived tokenspend:read, suppliers:read, metrics:read, esg:readClassified spend lines, supplier master + financial health, SUM / maverick / compliance metrics600 req/min, 50k rows per query, no raw registry payloadsEvery call written to audit.event.v1 (WORM) with actor, prompt hash, resource
Coworker.aiHTTPS webhook subscriber + task write-backHMAC-signed webhooks, scoped API key for status write-backevents:subscribe, tasks:writeAlert payloads only (IDs, category, severity, thresholds) — no supplier financial raw dataEvent-driven, at-least-once delivery with DLQ replayDelivery receipts and task outcomes appended to audit.event.v1

Guardrails

Applies to every external AI agent connected to the Cockpit

  • Read-only by default — agents never write to spend, classification or supplier master records
  • RBAC-scoped service identity mapped to the existing role matrix; agents inherit the requesting user's scope
  • Every agent request and response hash written to the append-only WORM audit log (audit.event.v1)
  • No agent access to raw commercial register or credit-bureau payloads — only derived, licensed-safe scores
  • Answers always carry source lineage and data-vintage stamps so agent output stays defensible