Skills CX operations

Sampling conversations

Every manual review of support conversations is a sample, including the ones nobody calls a sample. The question is only whether it was drawn deliberately.

CX operationsReportingAnalysisAny helpdeskRead-only
Installnpx rulebase-skills install cx-conversation-sampling

When to use it

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

  • “which tickets should we review”
  • “how do we pick a sample”
  • “is our QA sampling representative”

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. The frame comes first

    The sampling frame is the list of conversations you could have drawn from. Almost every generalisation failure is a frame problem, not a size problem.

  2. Choose the design to match the question

    Simple random. The default, and correct when you want one overall estimate. Boring and defensible. Use it unless you have a specific reason not to.

  3. Sampling for QA coverage

    Ongoing QA sampling is the same problem with an extra constraint: it must also be fair to the people being measured.

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

Monitor every agent. Improve every outcome.

AI agent monitoring for customer-facing agents. See what your human team resolved that your agent couldn't, and the prompt, knowledge or tool fix that closes the gap.

Rulebase dashboard

Necessary

Enables core site behavior and stores your privacy choice in this browser for 180 days.

Always on

PostHog measures page views and interactions. It uses in-memory identifiers, and session recording is disabled.

Mesh by Avina records session and form interactions and can use device or IP data to resolve business visitors through providers such as Vector or RB2B.