Leveraging an API-first approach to chatbots

Publish date:

Chatbots are more than just answering customer-service questions. They have the ability to support your business, improve customer experience, and help your employees work more efficiently.

With the emergence of artificial intelligence (AI) and machine learning, companies have been searching for new and innovative ways to engage with customers and employees. Chatbots are one new technology leading the way. This software conducts a conversation to simulate how a human would behave in a back-and-forth interaction, in order to deliver a better customer experience.

Chatbot use has risen exponentially. Statistics have shown by the end of 2019, 75% of workers whose tasks involve enterprise applications will have access to some form of digital assistant (Source: IDC).  Baby boomers and millennials have provided positive feedback: interactions with chatbots feel familiar and natural (Source: Chatbots Magazine).

More modern chatbots leverage AI and natural language processing (NLP), learn from their interactions, and tailor responses to the user. When having a conversation with a friend or co-worker, it is common for that person to remember details from past conversations. In the same way, chatbots can use past interactions to tailor a streamlined user experience.

In addition to AI and machine learning, the use and enablement of APIs are becoming more common. APIs (application programming interfaces) are a set of protocols that allow systems to talk to each other.

You might be thinking at this point: how does this help my company? With different systems in place, all with unique purposes, functions and users, how can a chatbot make a meaningful impact?

With any technology-driven approach which spans near-limitless, unique scenarios, the strategy is to solve the problem at a higher level. With API-enabled applications, it becomes easier to incorporate multiple systems into one streamlined architecture. We have smart speakers that control lights, TV, door locks, and alarm clocks, so it is hard not to imagine a chatbot which can interface with demand-planning, category-management, CRM, and ERP systems.

This initial thought became the primary building block for what is now Capgemini’s CApi platform, an API-first approach to implementing chatbots. We have demonstrated a conversation with our chatbot, which interacts with three different systems to simulate a day-in-the-life scenario. The user accesses their daily tasks in JIRA, completes planogram work in category management, and then views the future impact of their work via Power BI – all by conversing with a chatbot.

The interactions are seamless and the chatbot is capable of determining the systems with which the user would like to interface. Through conversation, the chatbot can provide a full interactive experience by analyzing user intents, extracting variables, using those variables to implement API calls, and providing the response to the user in terms they can understand.

An additional example is a chatbot’s ability to determine which course of action the user wants to take, use terms from the conversation to fill variables, and then use those variables to interact with the CRM APIs. It is important to note that you can teach your chatbot new things without having to write code. Through its dashboard, you can teach the chatbot new phrases, responses, and intents. You can also map API routes and teach the chatbot how to turn a conversation into an API call. We demonstrated using the CApi dashboard adding basic functionalities to the chatbot, which does not have any interactions learned.

Chatbots are more than just answering customer-service questions. They have the ability to support your business, improve customer experience, and help your employees work more efficiently. By connecting systems, chatbots have the ability to drive agility and growth.

Derek Levesque is part of the Digital Supply Chain group at Capgemini. Contact him at derek.levesque@capgemini.com for more information.

Related Posts

AI

Beyond the health crisis – Embracing the idea of enterprise as a platform

Lanny Cohen
Date icon September 23, 2020

In this third article to a series of blogs, Lanny Cohen shares insights on the concept of...

AI

Implementing an AI strategy and framework

Lee Beardmore
Date icon September 17, 2020

The journey to an AI-driven future operating model requires continued executive support, a...

AI

Beyond the health crisis – Positioned for success?

Lanny Cohen
Date icon September 16, 2020

In this second article to a series of blogs, Lanny Cohen focuses on importance of Position –...