Sizing a contact center with Erlang C
Headcount drives cost, so size the team before you pick a tier. A worked example with 120 calls an hour.
Take 120 calls in the busiest hour, a 240-second average handle time, and a target of answering 80% within 20 seconds. That is about 8 Erlangs of work.
The answer is 11 agents
With 10 agents, only 65% of calls are answered in 20 seconds. With 11, it’s 81% at 73% occupancy. A twelfth agent buys 90% — useful to know before you commit.
Mind the assumption
Erlang C assumes nobody hangs up, so it slightly overstaffs. Check the result against your own historic peaks before you hire.
Field notes
Keep reading
Build an AI voice bot like an Express app
The dialpress Node SDK turns SIP into routes and handlers. Here is a PBX and an AI voice bot that share one gateway — and pass calls between them.
SIP vs WebRTC for AI voice agents
SIP reaches every phone number on earth; WebRTC reaches every browser. A production voice agent needs both — here is how they fit together.
Giving voice agents tools with MCP
Your booking system, your CRM, your order lookup — any API can become a voice agent’s tool without writing a line of agent code.
