View

Forethought

Company stage
Early stage, Private

Design lead
2019

Forethought was founded in 2017 and won TechCrunch Disrupt the following year with Agatha Answers, its flagship answer recommendation tool. Agatha is an AI-powered contextual information retrieval app that lives within other help desk software platforms. It leverages deep learning to help seamlessly reveal helpful and relevant information that allows agents to resolve customer support tickets. Forethought aims to bring its own proven model to new enterprise software verticals—providing intelligent predictive information through the use of AI and deep learning in processing and indexing massive data sets across 100 languages.

Onboarding and setup

During the initial onboarding setup, customers of Forethought complete a brief signup before being taken to their dashboard to connect all the pieces of their knowledge base. Active and disabled sources are clearly identified and a side panel is used to create a familiar and expected pattern for connecting and managing all their data sources.

Our MVP was very, very simple. We knew we needed to level up.
Deon Nicholas
Founder of Forethought

Intelligence in context

One of Agatha's core benefits is that it works silently in the background as the agent goes about their normal work.

The product is alwasy working. A lot of products have really long flows that tie together, but Agatha is about small, quick flows that need to work inside all of these different CRM tools.

Finding the answers

Agatha's core technology is power by natural language processing (NLP) and natural language understanding (NLU), which help connect customer tickets and scenarios with possible solutions. The accuracy of those solutions is only as strong as the data that Agatha can access. Forethought created a secure API where companies can give selected access to massive data stores — historial help center tickets, Google Drive, Dropbox, Github repos, and other private repositories. By constantly scanning through this knowledge base, Agatah is able to find correlations between tickets, find answers to esoteric technical problems, and process the semantics of any type of data set — all across 100 languages.

Real-time relevant answers

Agatha feeds Support agents contextually relevant answers to tickets in a prioritized fashion. In order to effectively create a visualization for a prioritized list, TM blended the use of both concentric squares and standardized color patterns (green, orange, red) to ensure the color-blind and those with visual impairments could quickly identify search rank order. Agatha gets smarter and smarter with every use, as support agents are given every opportunity to further train the model by giving thumbs-up or thumbs-down feedback to each suggestion.

Designing for sales growth

Administrators and power agents are especially interested in understanding and demonstrating return on investment. An efficient admin dashboard features an A/B test that showcases the performance of Agatha-supported agents, compared to those not using Agatha. This built-in validation feeds leaders the data they need to advocate for keeping Forethought as a partner.

Packaging it all up

The final design library is robust and user-friendly, ensuring that the internal team is fully empowered to drive the product’s future. I then helped Forethought vet design candidates and by the end of the project, they had successfully hired their own internal product designer. With this full set of design assets in hand, the team is set up to set them up for long-term success, continuing to build, ship, and scale products that meet the same high quality bar.

Next Up