Use Case Intelligence RSS Search use cases Search
IBM Software / SaaS New Zealand

Frankly.AI

Enterprise Knowledge Search

Frankly.AI needed a faster way to turn AI-mediated interviews, panel transcripts and research papers into trustworthy summaries and queryable insights for public-sector consultation work.

Read the original story Explore all use cases
2 weeks to achieve POC
>90% reduction in time for reporting
roughly 100 members of the New Zealand AI Forum used the POC solution

Reported impact

Business outcome

The two-week proof of concept cut reporting time by more than 90% and enabled roughly 100 New Zealand AI Forum members to generate a white paper from the proceedings faster and with more targeted insight.

  • Productivity Improvement
  • Speed to Market

Solution

Frankly.AI worked with IBM Customer Success and Client Engineering to build a proof-of-concept on IBM watsonx.ai and IBM Watson Discovery for the New Zealand AI Forum consultation workflow. The system ingests forum discussion transcripts plus associated research papers, then uses Smart Document Understanding in Watson Discovery to organize the material by topic, speaker and other relevant parameters. On top of that indexed corpus, watsonx.ai runs each user query through pre-trained large language models to return concise, targeted insights inside the consultation chatbot. Rather than simply collect opinions, the implementation turns multi-source discussion content into a searchable evidence base that can be used to draft a white paper and surface the most relevant perspectives across a broad community of stakeholders.

Data flow

Forum discussion transcripts and associated research papers are ingested into Watson Discovery, organized with Smart Document Understanding, and then passed to watsonx.ai so the consultation chatbot can answer user-specific questions and support white-paper creation.

Solution architecture

2 components · 2 layers
  1. Compute
    • IBM watsonx.ai Runs pre-trained large language models to answer user questions with concise, targeted insights.
  2. Storage
    • IBM Watson Discovery Organizes transcripts and research papers by topic, speaker and related parameters using Smart Document Understanding.

Architecture clues

  • The implementation uses Smart Document Understanding to classify content by topic and speaker.
  • The output feeds a consultation chatbot and downstream white-paper drafting workflow.
  • Watsonx.ai applies pre-trained large language models rather than a custom model named in the story.

Evidence from the source

">90% reduction in time for reporting"
"IBM watsonx.ai runs all that aggregated content through one of its many pre-trained large language models (LLMs)."
"The joint team built a model that automatically extracts raw data from forum discussion transcripts, along with associated research papers."
"roughly 100 members of the New Zealand AI Forum used the POC solution to generate a white paper"
"the solution uses the Smart Document Understanding function within the IBM Watson Discovery service to organize the content by topic, speaker and other relevant parameters"
Transparency Evidence & methodology 95/100 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 value95/100
  • 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 scale5/10
    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

    Frankly.AI customer story

    First-party
    https://www.ibm.com/case-studies/frankly-ai
    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.

Related

Similar use cases

See all like this
IBM Jul 31, 2026 Crazylog Software / SaaS France Crazylog needed to help industrial maintenance technicians find trusted technical information quickly during equipment failures, even as documentation volumes, compliance needs, and workforce turnover made field… 10 frontline naval vessels Enterprise Knowledge SearchPredictive Maintenance IBM Cloud · IBM watsonx.ai · IBM watsonx.data IBM Mar 28, 2026 Shorthills AI Software / SaaS Global Shorthills AI needed to make legal research more comprehensive and trustworthy across very large corpora without forcing users to accept incomplete, hallucinated or weakly sourced answers. 4X increase in comprehensiveness Enterprise Knowledge Search IBM watsonx.data · Langflow IBM Mar 24, 2026 IBM Human Resources Software / SaaS Global IBM HR needed to make people analytics easier for business leaders and non-technical users because dashboard growth alone still left managers dependent on analysts to interpret metrics, filters, and workforce context. 20% each year initial self-serve Dashboards Adoption Growth Enterprise Knowledge SearchReal-time Analytics IBM Cognos · IBM watsonx BI