Skills Compliance

Where support data actually goes

Every support operation has a documented set of data flows and a real one, and they diverge. The documented set was written at a point in time; the real one grows every time someone connects an integration, trials a tool, or adds an AI feature that was already in the product they use.

ComplianceData protectionAnalysisAny helpdeskRead-only
Installnpx rulebase-skills install cx-data-flow-review

When to use it

Reach for this when someone says any of these — they are the phrases the skill itself triggers on:

  • where does our support data go
  • map our data flows
  • which vendors process our conversations

How it works

The method, in the order the skill runs it. The full procedure — tables, worked examples and the edge cases — is in the skill itself.

  1. Build the real map from the systems, not from the register

    Start from where the data is, not from what the register claims: Outbound webhooks and API consumers, Analytics and BI, and where those tools are hosted, Transcription and voice vendors, Vendor and BPO systems, and their own subcontractors, Search and vector indexes, and where the embedding was computed, Local copies.

  2. Compare against the documented position

    Three comparisons, and each finds a different class of problem.

  3. Making it stay accurate

    A one-off map is stale within a quarter. The durable output is the mechanism: A named owner for the support data map.

Related skills

Free and open source, and vendor-neutral — it reads the conversations from whichever helpdesk you already run. Browse all 149 skills · connect your helpdesk over MCP · source on GitHub

Review every conversation. Act on what it finds.

AI for customer operations, built for financial services. Specialist agents chase every issue to resolution and every stalled customer to activation.

Rulebase dashboard