flamingo ai case study · hello@flamingo. ai. usa + 1 855 282 9272 aus + 1300 556 368. for more...

4
Flamingo Ai Case Study MAGGIE: Virtual Inquiry Assistant A Conversational Ai platform to help your employees and customers access information quickly. Powering Human Capability www.flamingo.ai

Upload: others

Post on 04-Aug-2020

3 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Flamingo Ai Case Study · hello@flamingo. ai. USA + 1 855 282 9272 AUS + 1300 556 368. For more information or a demonstration. Future. The FinServCo is considering: → Building

Flamingo Ai Case Study MAGGIE: Virtual Inquiry Assistant

A Conversational Ai platform to

help your employees and customers

access information quickly.

Powering Human Capabilitywww.flamingo.ai

Page 2: Flamingo Ai Case Study · hello@flamingo. ai. USA + 1 855 282 9272 AUS + 1300 556 368. For more information or a demonstration. Future. The FinServCo is considering: → Building

→ How do I set up an account in multiple regions?→ What forms do I need to fill in and are there different forms for each region?

→ Are there different fees and charges for the account when transacting in different regions?

About International Financial Services Company (FinServCo)*The FinServCo is one of the world’s largest multinational financial services companies present in over 50 countries and servicing almost 40 million customers.

ProblemFinServCo Customer Service Reps (CSR) and employees had the problem of efficiently responding and finding answers over the phone or via email to general customer queries including:

FinServCo’s legacy knowledge retrieval system was not able to provide its CSR and employees with the relevant information in a timely manner to address these queries, thus requiring the CSR to set a time to call the customer back with the correct information. Additionally, the CSR would need to reach out to the FinServCo’s Subject Matter Expert post call to seek the correct answer and process that the customer is to follow.

Not only is it an inconvenience for a customer to have to reschedule a time to get the correct information, the delay could mean a loss of new business for the Bank. As well, it creates enormous internal inefficiencies within the FinServCo’s operating model. It was estimated by the FinServCo that 60% of the Subject Matter Expert’s time was spent chasing up initial requests from the CSR to gather more information which may in turn have been initially unclear or incomplete.

The role of the Subject Matter Expert within the FinServCo is to update the main documentation and source of truth; keeping documents relevant with current procedures and legislation for the current product, rather than responding to constant requests on where information is stored in the FinServCo’s knowledge management system.

The FinServCo’s incumbent knowledge retrieval system is expensive to run and maintain, difficult to search and cumbersome to use by employees, whom spent hours trying to find the relevant information about products and services often to only fail in this pursuit. These challenges drove FinServCo’s decision to replace its knowledge retrieval system with an alternate innovative solution that allows for scale, uses AI, machine learning and natural language processing and importantly, could be fully automated or used in human-machine augmentation mode.

SolutionFinServCo engaged Flamingo Ai, a Machine Learning & AI solutions provider, to run a 2 month pilot deploying MAGGIE, a Cognitive Virtual Assistant for Knowledge Retrieval, to act as a Subject Matter Expert and knowledge retrieval tool for their CSR and employees.

For the two month pilot, MAGGIE, was deployed in one region and one department to help the CSRs and employees query and search Frequently Asked Questions about products and processes and help reduce emails and calls going into the Subject Matter Experts.

→ Where do I find the form to download on the website?

Page 3: Flamingo Ai Case Study · hello@flamingo. ai. USA + 1 855 282 9272 AUS + 1300 556 368. For more information or a demonstration. Future. The FinServCo is considering: → Building

Solution, cont . . .MAGGIE was trained by the Subject Matter Experts in live mode in order to pre-seed information in the machine learning brain. The FinServCo also crowd-sourced information from its teams in a quick, fun and easy way which allowed for the brain to quickly populate with frequently asked questions asked in a variety of ways. This process allowed for the FinServCo to capture multiple Subject Matter Expert’s knowledge which the company had previously no other effective way of retaining in a searchable system. The pre-seeding took only two weeks and the Virtual Assistant was fully operational.

MAGGIE, the Virtual Inquiry Assistant for Knowledge Retrieval, was deployed for use by the FinServCo’s employees and CSRs within six weeks from contract signing.

Throughout the trial, there were only a few occasions where MAGGIE was not able to provide the correct answer or process, and the Subject Matter Experts were contacted. Once MAGGIE has learned this new information once, she never forgets it.

The brain was also continuously learning with every interaction through a method called unsupervised machine learning and reinforcement learning. This means MAGGIE automatically learns from new questions and answers but will only be able to use an answer if it has been reinforced by a human. This involves an easy 'gating’ system where a Subject Matter Expert or other authorised person approves the answer MAGGIE provides. This can be done by business people without the need for technologist or data scientists.

Page 4: Flamingo Ai Case Study · hello@flamingo. ai. USA + 1 855 282 9272 AUS + 1300 556 368. For more information or a demonstration. Future. The FinServCo is considering: → Building

www.flamingo.ai [email protected]

USA + 1 855 282 9272AUS + 1300 556 368

For more information or a demonstration

FutureThe FinServCo is considering:

→ Building upon the initial MAGGIE trial and looking to expand its use into other product lines aswell as potentially deploying across18 additional countries.

→ Using MAGGIE for employee on-boarding and training.→ Once MAGGIE is fully trained, having MAGGIE as customer facing Virtual Assistant or Web

Concierge for customers.→ Using MAGGIE as an afterhours Virtual Assistant in the contact center.→ Other Use Cases for the Virtual Assistant which could service other divisions within of the

company.

→ Increased speed of employee’s responses to customer queries.→ Significant reduction of email inquiries going through to Subject Matter Experts.→ Greater level of compliance in responses.→ Ability to keep information up to date quickly and easily.→ The Virtual Assistant used as a training guide used to on-board employees.

Benefits RealisedBenefits to the FinServCo from the trial of MAGGIE the Virtual Knowledge Assistant included:

Other aspects of MAGGIE the Virtual Knowledge Assistant are:

→ The Virtual Assistant is constantly learning new products and processes.→ Employees didn’t require training to use the Virtual Assistant as the system was

intuitively and very easy to use.→ CSRs and employees enjoy using the Virtual Assistant.→ Employees began championing and showcasing the capability to other

colleagues across departments.→ The FinServCo is looking to use MAGGIE on mobile devices whilst they are

servicing customers.→ The ability to use the platform without the need for a data scientist teams.→ Previous AI projects had taken over six months whilst Flamingo Ai delivered

within six weeks.

*not real company name