Menu
Hero image: Enterprise Client
Case StudiesEnterprise Client
Case Study

Bespoke engineering for high-scale operations.

How TIN partnered with leadership to design, build, and deploy production AI systems with measurable ROI.

Client
Enterprise Client
Engagement
Advisory + Custom Build
Duration
12–16 weeks
Year
2025
50k
Calls / month
−68%
Avg handle time
99.94%
Uptime since launch
14wk
Scope to live
01 · Brief02 · Architecture03 · Build04 · Outcome05 · Stack
01 · The brief

A queue-based call centre that couldn't scale.

Konnect's existing setup routed every inbound call through a static IVR into one of fourteen agent queues. Average handle time was creeping past nine minutes; the cost of adding capacity was linear in headcount. They wanted AI in the loop — but with real telephony, real CRM lookups, real handoff. Not a chatbot wearing a phone.

“We were pricing the next 50% of growth in seats. TIN priced it in code.”
Routing console / old IVR screenshot

02 · Architecture

We rebuilt the call path around a routing brain that owns the conversation until escalation. Telnyx handles SIP and recording; OpenAI Realtime handles the voice loop; an internal policy engine decides when a human takes over.

SIP / PSTNTelnyx — inbound, recording, fallback
Voice loopOpenAI Realtime · gpt-4o-realtime-preview
KnowledgeRAG over Konnect KB · pgvector + rerank
CRMTwo-way sync · Salesforce + custom DLQ
PolicyCustom DSL · escalation, compliance, tone
ObservabilityDatadog + per-call eval scoring

03 · Build

Two-week sprints. Live staging from week three. We shadowed the existing call centre in week six, ran 5% live traffic in week ten, and went to 100% in week fourteen. The cutover was reversible the entire way.

Three engineers from TIN. Two voice ops leads from Konnect. Friday demos every sprint, no surprises.

Staging dashboard / sprint demo screenshot

04 · Outcome

Average handle time dropped 68% in the first month and held. Customer CSAT moved from 7.4 to 8.1. Konnect cancelled a planned hiring round of 22 L1 agents and redeployed budget into expansion markets.

The architecture has been live for fourteen months at the time of writing. We retain a small ongoing pod for new policy work and Realtime model upgrades.

CSAT / handle-time results dashboard

05 · Stack

Node + Hono · Postgres + pgvector · Redis · Telnyx · OpenAI Realtime · Salesforce · Terraform on AWS · Datadog. SOC 2 Type II controls. PCI-DSS in-scope handling for billing transfers.

Have a system like this on your roadmap?

Book a discovery call