Use Case Intelligence RSS Search use cases Search
IBM Public Sector New Zealand

South Waikato District Council

Customer Service Automation · Enterprise Knowledge Search

South Waikato District Council needed a better way for citizens and employees to find information hidden across siloed public-service repositories because its first attempt at a virtual assistant lacked the technical accuracy needed for production use.

Read the original story Explore all use cases
91.5% accuracy rate validated across 300 test questions

Reported impact

Business outcome

SWDC dramatically improved answer accuracy, gained a production-ready public information assistant, and expects to reduce the amount of staff time spent on routine question handling.

  • Customer Experience
  • Productivity Improvement

Solution

IBM helped South Waikato District Council rebuild its virtual assistant as a three-layer conversational search system using IBM watsonx.ai, watsonx Assistant, and IBM Watson Discovery. Watson Discovery handles deep retrieval across archival and hard-to-access documents, watsonx Assistant provides the interaction layer, and watsonx.ai augments that assistant with more advanced reasoning so answers are not limited to simple FAQ matching. The experience also exposes document URLs with results so users can see where the information came from, which was important for transparency in a public-sector setting. By combining generative AI with enterprise retrieval, the council created a single entry point for information that had previously required hours or days of manual searching across disconnected stores. The strong proof-of-concept accuracy gave SWDC enough confidence to commit fully to production, with the expectation that employee effort can move away from repetitive question answering and into higher-value community work.

Data flow

A citizen or employee asks a natural-language question, watsonx Assistant routes it through watsonx.ai for improved reasoning, Watson Discovery searches across council repositories to locate the supporting documents, and the assistant returns the answer along with source URLs for transparency.

Solution architecture

3 components · 3 layers
  1. Compute
    • IBM watsonx.ai Adds generative intelligence that improves how the assistant answers council questions.
  2. Storage
    • IBM Watson Discovery Retrieves the correct subset of information from archival and hard-to-access council documents.
  3. Serving
    • IBM watsonx Assistant Provides the user-facing conversational interface for the council’s virtual assistant.

Architecture clues

  • The council first tried to build the assistant alone before IBM reworked the stack for production accuracy.
  • The proof of concept was accurate enough that SWDC decided to fund the production rollout.
  • The solution returns document URLs to show users the supporting source.

Evidence from the source

“91.5% accuracy rate validated across 300 test questions”
“Integrates results with document URLs to facilitate easy access for users seeking additional details”
“The council expects to reduce the time employees spend answering questions”
“The new virtual assistant combines the capabilities of IBM watsonx.ai, IBM watsonx Assistant and IBM Watson Discovery.”
“Watson Discovery provides data discovery capabilities, enabling the solution to dig deep into archival and difficult to access documents”
Transparency Evidence & methodology 90/100 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 value90/100
  • 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 impact15/25
    1 metric 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
    5 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

    South Waikato District Council customer story

    First-party
    https://www.ibm.com/case-studies/south-waikato-district-council
    Source type
    Vendor-published customer story
    Published
    Apr 2, 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.

Related

Similar use cases

See all like this
IBM Nov 12, 2024 INAIL Public Sector Italy INAIL needed to absorb a surge in grant-funding inquiries and application volume for its Bandi ISI program without overwhelming the contact center or delaying applicant guidance during the submission and admission… 2 months Customer Service AutomationEnterprise Knowledge Search IBM Watson Discovery · IBM watsonx Assistant · IBM watsonx.ai Google Cloud Archived · Oct 2, 2026 Hawaii DCCA Public Sector Honolulu, Hawaii The Hawaii Department of Commerce and Consumer Affairs (DCCA) serves a vital mission: protecting residents while ensuring a level playing field that promotes fair business competition across the state. Reclaiming Time: Streamlined operations and reduced manual work across 52 state boards and commissions by… Customer Service AutomationEnterprise Knowledge Search Cloud Storage · Contact Center AI Platform · Customer Experience Agent Studio Baidu AI Cloud Sep 24, 2025 All-China Federation of Trade Unions Public Sector China The All-China Federation of Trade Unions needed a unified AI foundation that could support legal aid, rights protection, and other worker services at national scale instead of leaving union service digitization… Delivery cycle fell from 3-6 months to under 1 month. Customer Service AutomationEnterprise Knowledge Search Qianfan AppBuilder · Qianfan ModelBuilder · Union Industry Model