Spare Connect Live 2026
Customer story

What PSTA learned after 275,000 AI Voice calls.

After eight months in production, PSTA shared how a phased AI Voice rollout reduced hold times, lowered abandoned calls, and expanded rider support beyond business hours.

At Spare Connect Live, the Pinellas Suncoast Transit Authority (PSTA) shared what it learned after eight months of running AI Voice in production.

Why PSTA Turned to AI Voice

PSTA was facing rising call volumes, longer wait times, and riders who expected faster support. The team turned to AI Voice to handle routine tasks so staff could spend their time on the calls that need a human.

Before launching, they asked four questions:

01
Could AI book trips?

Could a voice agent reliably complete a full reservation end-to-end?

02
Could it support existing riders?

Status checks, modifications, cancellations — the everyday asks.

03
Could it take pressure off staff?

Free up reservationists to focus on the more complex calls.

04
Could it work with existing systems?

Plug into the platforms already running the operation.

A Phased Rollout Built on the Right Foundations

PSTA rolled it out in phases. Access services came first, then MOD services, then AI Chat. Getting it right took more than the technology itself. The team had to sort out call routing, authentication, testing, and escalation before riders ever picked up the phone.

The rollout sequence
  1. Phase 01

    Access services

    Paratransit calls first — highest-touch, highest-value.

  2. Phase 02

    MOD services

    Microtransit added to the same voice layer.

  3. Phase 03

    AI Chat

    Extending the same logic to chat channels.

The foundations that had to come first

  • Call routing. Deciding what reaches AI Voice and what gets escalated.
  • Authentication. Confirming riders securely without adding friction.
  • Testing. Running real scenarios before any rider ever called in.
  • Escalation. Clean handoffs from AI to a human when complexity warranted it.

What AI Voice Handles Today

AI Voice now handles common rider requests like trip booking, status checks, modifications, cancellations, and transfers to customer service. The live demo showed a rider completing a full booking through a natural conversation, with saved profile and location details making repeat trips faster.

Trip booking
Status checks
Modifications
Cancellations
Transfers to customer service
Saved profiles for faster repeat trips

The Results After Eight Months

After eight months, PSTA reported the following:

275K+

Calls handled

140K+

Rider actions completed

36K

Calls supported per month

700

Rider outcomes delivered daily

Rider experience impact

Change in key contact-center metrics with AI Voice in production

Reduction in average hold time46%
Reduction in abandoned call rate~70%
Callers experiencing zero hold time44%
Neutral or positive call sentiment96%

Covering the overnight gap

The agency also noted that AI Voice provided valuable overnight support by covering the overnight gap. It answered roughly 2,000 calls between 7 PM and 7 AM over a two-month stretch when reservation staff were off the clock.

A day of rider support

Staff hours vs. the overnight window AI Voice now covers

12 AM6 AM12 PM6 PM12 AM
Reservation staff (7 AM – 7 PM) AI Voice (7 PM – 7 AM)

~2,000 overnight calls answered over a two-month stretch.

Lessons From Production

AI works best alongside human teams. About half of all calls are now fully resolved by AI Voice, while the more complex ones still go to staff. The split is roughly 50/50, and that balance is the point — the system handles the routine volume so staff have the time and focus for the conversations that actually need a person.

What the team had to tune after launch

  • Recurring trips. Managing repeat bookings without creating duplicate or conflicting reservations.
  • Local language and pronunciation. Getting place names, street names, and rider names right.
  • Post-launch tuning. Treating launch as the start, not the finish — the system kept getting better with use.

The takeaway

Adopting AI is an operational change, not just a tech install. PSTA's advice for agencies weighing AI Voice was simple:

01
Start with a focused rollout

Pick one service, get it right, then expand.

02
Bring the right people in early

Operations, IT, and customer service together from day one.

03
Measure your progress over time

Track hold times, abandonment, sentiment — and tune from there.