Automation helps support teams drive faster resolution
Frankly.AI + IBM
Digital rendering of the IBM watsonx image
Filtering the AI conversation

Security. Governance. Transparency. These are just a small sampling of the issues that organizations will need to confront as they seek to capitalize on the vast opportunities presented by generative AI (gen AI).

In New Zealand, a hotbed for gen AI innovation, Frankly.AI has developed a platform that amalgamates expert insights from various sources, including AI-mediated interviews, detailed panel transcripts and published papers.

Based on its mission of “no voice left behind,” Frankly.AI designed its platform to do more than just gather opinions; it scales the discourse using gen AI, ensuring that a broad spectrum of perspectives are heard—not just those with the most influence. By synthesizing these diverse inputs, Frankly.AI effectively identifies and focuses on the most pertinent and impactful aspects of experts’ views.

Testing the gen AI waters

Looking for a faster and more efficient way to capture the “meat” of these discussions, Frankly.AI turned to, IBM’s next-generation AI and data platform. To test its effectiveness, the company brought in a team from IBM to co-create—with its own internal staff—a proof-of-concept (POC) solution. Its target: the transcripts of the New Zealand AI Forum, through which government agencies regularly convene to assess the impact of AI on all facets of New Zealand society.

The joint team built a model that automatically extracts raw data from forum discussion transcripts, along with associated research papers. In the background, 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.

Where IBM® plays its core role is in delivering the most accurate, concise and targeted insights to the people using the consultation chatbot. Based on each user’s unique query into the system, IBM runs all that aggregated content through one of its many pre-trained large language models (LLMs). What it generates are pithy, relevant insights they can use—and trust.

>90% reduction in time for reporting 2 weeks to achieve POC
Our proof of concept succeeded thanks to IBM’s swift, secure and scalable solution in Matt Ensor CEO Frankly.AI
A faster path to insights

By all measures, the two-week project delivered on its stated goal of more efficient and timely summarization. By working with IBM Customer Success and Client Engineering teams to deliver a practical use case, roughly 100 members of the New Zealand AI Forum used the POC solution to generate a white paper from its proceedings for consumption by AI entrepreneurs, investor groups, regulators, researchers, educators and the public at large.

Ordinarily, such an “authorship by committee” endeavor could conceivably take months or more. By capitalizing on the advanced capabilities of IBM, Frankly.AI has shown that gen AI can dramatically streamline and simplify the process.

Frankly.AI logo
About Frankly.AI

Frankly.AI (link resides outside of is an Auckland, New Zealand-based startup focused on accelerating the adoption of generative AI. A unit of Beca—one of the largest independent advisory, design and engineering consultancies in the Asia Pacific region— Frankly.AI is a platform that utilizes generative AI to facilitate user-led discussions on a broad spectrum of topics.The company uses AI to automatically process conversations to provide insights into the diversity of community views. is helping companies custom build AI solutions to suit their specific needs
Start your free trial: View more case studies

© Copyright IBM Corporation 2023. IBM Corporation, New Orchard Road, Armonk, NY 10504

Produced in the United States of America, December 2023.

IBM, the IBM logo,, IBM Watson, and are trademarks or registered trademarks of International Business Machines Corporation, in the United States and/or other countries. Other product and service names might be trademarks of IBM or other companies. A current list of IBM trademarks is available on

This document is current as of the initial date of publication and may be changed by IBM at any time. Not all offerings are available in every country in which IBM operates. 

All client examples cited or described are presented as illustrations of the manner in which some clients have used IBM products and the results they may have achieved. Actual environmental costs and performance characteristics will vary depending on individual client configurations and conditions. Generally expected results cannot be provided as each client’s results will depend entirely on the client’s systems and services ordered. THE INFORMATION IN THIS DOCUMENT IS PROVIDED “AS IS” WITHOUT ANY WARRANTY, EXPRESS OR IMPLIED, INCLUDING WITHOUT ANY WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND ANY WARRANTY OR CONDITION OF NON-INFRINGEMENT. IBM products are warranted according to the terms and conditions of the agreements under which they are provided.