Building an AI Agent¶
If you are new to the Platform and want to familiarize yourself with the terms and concepts we use, please refer to Concepts and Terminology.
Disclaimer
PCI Compliance Disclaimer: You must use data masking to collect credit card information but never capture CVV numbers. Kore.ai is committed to safeguarding all payment card data collected and processed for its business. However, card payment processing is not supported in Kore.ai-owned systems. If card payment processing is required during agent interactions, you must transfer the processing to a PCI-compliant merchant.
Steps for Building your AI Agent¶
Once you get access to the Platform, you can build your first AI Agent by following the steps below.
- Define / Design: This is the step during which you clarify the necessary details, before you begin to actually build your agent.
- Build / Develop: At this stage, your agent takes shape within the Platform; you begin making the necessary configurations and developing it to continuously fit your organization’s needs.
Define / Design the AI Agent¶
Every agent must be built to solve a well-defined use case.
The first step to create a well-defined use case involves gathering market requirements and assessing internal needs. Typically, you want to include all relevant stakeholders, such as business sponsors, product owners, business analysts, and an agent developers in this process.
Next, get a good idea of what the agent needs to do. A clear description of each step and a flow chart of the various conversation flows will go a long way in easing the process of building the agent.
Questions to Ask during the Design Process¶
Try to answer the following questions (some if not all):
- Who is the target audience? Technical help agents targeted for a tech-savvy customer need a different design when compared to agents for a layperson, such as an airline’s customer. Hence assessing the target audience is always important.
- What Agent persona will resonate the most with this group? This will help define how the agent talks and acts in every situation.
- What is the purpose of the Agent? The goal i.e. the customer query that the agent needs to address defines the endpoint of any conversation.
- What pain points will the Agent solve? The purpose and scope of agents are set to identify what the agent addresses and when the human agent needs to take over.
- What benefits will the agent provide for us or our customers? The main benefit of using an agent is time-saving. Users need not waste their time waiting for a human agent to be available for answering their query. You, as the business owner, don’t worry about not being there to cater to all customer needs.
- What tasks do I want my agent to perform? Simulation of user conversation helps identify the tasks that need to be catered to by the agent.
- What channels will the agent communicate through? This will to some extent drive the way the agent is presented, the various options available for the agent are limited by the channel/medium it is used in.
- What languages should the agent speak? When catering to a multilingual community the language support is imperative and building the dictionary simultaneously is useful.
Build an AI Agent Using the Setup Guide¶
- Sign in to the Platform Homepage.
- On the Homepage, click the New App button and then choose New App. The Get Started options are displayed.
- Under Automation AI, click Create New and then select your onboarding experience - Guided Onboarding.
- Click Next at the bottom-right corner, and follow the onscreen instructions to complete the onboarding journey.
- At the end of the journey, your agent will be ready. You can go back to any step in the journey and change the provided information.