RECAST AI :: How to Process Complex Conditions using Requirements

[t_skrypko]

About me

I've been working in SAP segment for 5 years. I have diverse SAP experience dealing with various consulting projects, such as end-to-end implementation, including integration with third party applications. Currently, I’m leading the SAP Consultancy activities at Skybuffer.

Introduction

As we develop our own products and face a need to make customers acquainted with our applications and company's general information in a convenient and easy way, we have found SAP Recast AI platform and decided to use it and build a smart chat-bot for our website.

As SAP Recast AI is not so widely used yet and there is not so much information about it, I’ve decided to share my experience with SAP Community.

This article shows how you can train your bot in such a way that it should be able to react to the combination of a phrase and a special trigger differently than to a separate phrase.

 

Prerequisites

You are to sign up to Recast AI platform and create an initial version of your chat-bot.

Business case

Your bot needs to recognize the urgency of the purchase and propose a specific Document type:

• When the user asks for a new contract – the bot suggests selecting a document type for a new contract


• But if there is an urgent need for such a contract – there is another type of document, relevant for Urgent cases

Steps to fulfill requirement

Create Intents: @contract and @urgent

Mark Entity: #Urgent

Skill: Create a requirement to check #Urgent entity and react accordingly

Solution

1. Add 2 intents to Train: @contract and @urgent

2. Create Entity #Urgent

3. Create Skill for your Bot.

4. In triggers tab add your Intent

5. Add Requirement: record Entity #urgent to memory:

5.1.  Add reply if #urgent is complete

5.2.  Add reply if #urgent is missing

6. Test the Bot:

Result

Now your bot is able to recognize a specific trigger in the User’s Intent and react to it accordingly. This piece of logic can be injected as a part of your bot communication skills.

 

Conclusion

This is just a simple hint of how the bot can responsively react to the Intent, taking into account the specific trigger. Hope it will help you to start developing a more complex logic for your amazing chat-bot.