Retail Sector

Inbound Call Routing Agent

A conversational receptionist that routes callers to the right department on the first attempt, and resolves simple queries without a transfer.

system.statusinbound-call-routing-agent.runagent.liveworkflow.ok
Problem

A retail business with several departments needed inbound calls routed correctly on the first attempt, without a human receptionist screening every call.

System architecture
  1. 01
    Conversational triage

    An ElevenLabs voice agent answers all inbound calls and asks the caller what they need, using natural conversation rather than a rigid phone tree menu.

  2. 02
    Department routing

    Based on the caller's stated need, the agent performs a blind transfer to the correct department line, covering seven distinct departments in this build.

  3. 03
    Knowledge layer

    An embedded prompt database gives the agent company specific information (hours, policies, common answers) so it can resolve simple queries itself before transferring, reducing unnecessary transfers.

Result in production

Callers reach the right department without navigating a traditional IVR menu, and simple queries get resolved without a transfer at all.

Who this pattern fits

Originally built for the retail sector, the same architecture applies to any team facing a similar volume, compliance, or coordination problem. The stack (ElevenLabs, Twilio, Blind transfer, and others) is stable, self hosted where it matters, and designed to be operated by a small team without a platform crew.

Keywords
  • AI call routing agent
  • virtual receptionist AI
  • inbound voice AI for retail
  • AI IVR replacement
Tools used, with role
  • ElevenLabsSpeech synthesis for the voice agent. Chosen for latency and voice quality on production calls.
  • TwilioTelephony carrier. Handles inbound and outbound PSTN, SMS, and recording.
  • Blind transferPart of the production stack for this build.
  • Embedded prompt databasePart of the production stack for this build.
What I would do differently

The next iteration would push more of the intent routing into a smaller, cheaper model with structured outputs, keeping the expensive model only for the last mile. It cuts cost noticeably at scale without hurting quality.

Content angle

Why conversational routing beats a phone tree menu. Positions this as a UX first alternative to legacy IVR.

Frequently asked
How is this better than a normal IVR?+

Callers describe what they need in natural language instead of navigating a menu, which routes them faster and eliminates the zero out behaviour that breaks IVR analytics.

More solutions

Related work