CX & Support Metrics

Containment Rate

Definition

Containment rate is the percentage of interactions that a bot or automated system handles to completion without escalating to a human agent.

Also known as: bot containmentautomation containment rateself-containment

How to calculate it

The formula is: (contained interactions ÷ total automated interactions) × 100, where "contained" means the session ended in the bot without a handoff. If a chatbot handled 5,000 sessions and 3,500 finished without reaching an agent, containment is 70%.

The critical caveat: containment counts sessions that didn't escalate, which isn't the same as sessions that succeeded. A customer who gives up in frustration is technically contained. Always read containment next to CSAT and repeat-contact rate to separate real resolutions from dead ends.

Why it matters

Containment is the primary efficiency metric for conversational automation — every contained session is one a human didn't have to work. But it's easy to inflate, so mature teams distinguish containment (didn't escalate) from true resolution (problem actually solved) and optimize for the latter.

Frequently asked

What is the difference between containment and deflection?

Deflection usually refers to preventing a ticket from being created at all (via self-service); containment refers to a bot completing an interaction it already started without handing off to a human. Both risk counting abandonments as successes.

Is a high containment rate always good?

Not on its own. High containment paired with low CSAT often means customers are being trapped rather than helped. Judge it alongside satisfaction and whether contained customers came back with the same problem.

Related terms

Ticket Deflection

Ticket deflection is the share of customer questions resolved through self-service or automation before they ever become a human-handled support ticket..

Self-Service Rate

Self-service rate is the share of customer questions resolved through self-service resources — help center, FAQs, portals, or automation — without a customer needing to contact a support agent..

Deflection vs Resolution

Deflection vs resolution is the distinction between preventing a ticket from reaching a human (deflection) and actually solving the customer's problem (resolution) — two outcomes that are easy to confuse but measure very different things..

Human Handoff

Human handoff is Macha's principle of keeping a person in the loop on anything customer-facing — most concretely through confirmation gates that pause an agent before any write action in interactive chat, and escalation patterns that route hard cases to your team..

Chatbot

A chatbot is a software program that simulates conversation with users through text, ranging from simple rule-based scripts that follow decision trees to AI-powered bots that understand natural language..

Put these ideas to work

Macha is an AI agent layer that sits on top of the help desk you already run — Zendesk, Freshdesk, Front, Intercom, or Gorgias.

Start Trial