IBM Public Sector Arizona, United States

Clerk of the Superior Court in Maricopa County

Customer Service Automation

The Clerk's Office was handling large volumes of time-sensitive citizen inquiries, and staff were losing time to repetitive calls, transfers and routine questions instead of focusing on more complex work.

15,569 conversations
214 human hours per month
33,000 calls a month
95.78% containment rate in 2023

Reported impact

Business outcome

Cleo now handles a large share of incoming demand, saving staff time every month while letting the office offer faster, more consistent support to citizens without making agents pause complex work to answer routine calls.

  • Customer Experience
  • Productivity Improvement
  • Scalability

Solution

The Clerk of the Superior Court in Maricopa County built Cleo, a virtual assistant powered by IBM watsonx Assistant, to centralize self-service support for citizens and staff. The project evolved from internal ChatOps experiments into an enterprise-grade conversational system that could survive beyond its original creator and be maintained by non-specialists. Watsonx Assistant became the operational core, giving the Clerk's Office a natural-language interface that could interpret requests, answer high-volume questions and route people without dead ends across existing customer-service channels. The design goal was not just to deflect calls, but to provide fair and timely access to public services such as record requests, marriage licenses and passport renewals even when employees were not physically present. By shifting routine inquiries to Cleo, the office created a scalable public-service support layer that reduced call burden and improved service continuity.

Data flow

Citizen and employee questions enter Cleo through customer-service channels, watsonx Assistant interprets intent and returns an answer or guided next step, and unresolved requests are routed onward instead of forcing callers to restart the process.

Solution architecture

1 components · 1 layer
  1. Serving
    • IBM watsonx Assistant Runs the Cleo virtual assistant that interprets user questions, serves answers and routes citizens through self-service support flows.

Architecture clues

  • The deployment is intended to avoid dead ends by answering or routing requests instead of restarting the support journey.
  • The office prioritized maintainability by nontechnical staff as a key design constraint.
  • The project grew out of internal ChatOps experiments before moving to a managed conversational platform.

Evidence from the source

IBM watsonx Assistant held 15,569 conversations with a 95.78% containment rate in 2023
IBM watsonx Assistant's handling of inquiries currently saves 214 human hours per month
it was very easy to transition the technology to a non-technical individual
the Clerk's Office was fielding 33,000 calls a month
Transparency Evidence & methodology 100/100 reference value · 89% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value100/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact25/25
    2 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence89%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    4 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. IBM

    Clerk of the Superior Court in Maricopa County customer story

    First-party
    https://www.ibm.com/case-studies/clerk-superior-court-maricopa
    Source type
    Vendor-published customer story
    Published
    May 14, 2024
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.