Customer support · Production

What Assembled learned by deploying its own voice AI in its support queue

The problem

Assembled's support operation relied heavily on tribal knowledge, and its knowledge base covered mainly the happy path — missing the edge-case documentation that AI requires to handle real customer queries consistently.

First attempt

At a previous role, the support lead had over-focused on automating first-touch contacts without designing the broader workflow architecture, making the wider flow of work harder to manage. Early voice AI workflows at Assembled were also too rigid — structured like decision trees — causing the agent to keep asking for clarification even when the customer had already provided the needed context.

Workflow diagram · grounded in source
1
Customer calls support queue
trigger
“when the team decided to put Assembled's own AI voice agent into its own support queue”
2
Tier 1 vs complex routing
routing
“the answer was to focus on Tier 1 contacts: recurring, transactional questions where speed and consistency matter, and where customers benefit from immediate help or a clear next step. More advanced troubleshooting, especially issues tha…”
3
Voice AI handles Tier 1 query
ai_action
“identify recurring question types, help build the workflows that respond to them, then review and refine the guidance over time”
4
Escalation to human agent
human_review
“We did have to design that handoff procedure to make sure that we don't leave customers hanging”
5
Workflow review and iteration
feedback_loop
“use live AI interactions to reveal what is still missing”
Reported outcome

Assembled had its first agentic workflows live within a few weeks, with support agents shifting toward editing and fact-checking AI outputs rather than handling routine queries directly, and workflow ownership becoming part of the support role itself.

Reported metrics
Time to first agentic workflows livewithin a few weeks
Reported stack
AI voice agent
Source
https://www.assembled.com/blog/implementing-voice-ai-in-support
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Assembled had its first agentic workflows live within a few weeks, with support agents shifting toward editing and fact-checking AI outputs rather than handling routine queries directly, and workflow ownership becomin…

What tools did this team use?

AI voice agent.

What results were reported?

Time to first agentic workflows live: within a few weeks (source-reported, not independently verified).

What failed first in this deployment?

At a previous role, the support lead had over-focused on automating first-touch contacts without designing the broader workflow architecture, making the wider flow of work harder to manage.

How is this customer support AI workflow structured?

Customer calls support queue → Tier 1 vs complex routing → Voice AI handles Tier 1 query → Escalation to human agent → Workflow review and iteration.

Related customer support cases