Create more intelligent chatbots that can leverage relevant data at the right time and in the right circumstances.
Why context is important for chatbots
Bots are inherently stateless, and conversations between people can differ greatly based on their relationship and how much they know about each other. Because of this, chatbot developers struggle with how to keep track of different variables while maintaining the context and natural flow of a conversation. This is further complicated by the fact that data is created everywhere – including by your users, your company, and your bots – and it varies in importance, utility, and lifespan.
Effective context management is important because it allows bots to interact with users in a way that is easier, quicker, and more helpful – and less robotic and scripted. Contextual data helps users complete tasks faster and allows you to create more natural, human-like back and forth conversations. It can even be used to personalize your bot’s message and sales pitch – helping you sell more effectively.
Kore.ai allows you to capture and reuse contextual data for a large variety of scenarios, so you can create more complex use cases and redefine the enterprise customer experience.
Context Management at the Framework Level
Kore.ai allows you to manage data and contextual details at the framework level – data that can come from user inputs, API responses, sessions, and more – with little coding required. This allows you to create context-aware bots that can follow conversation history, harvest and harness information from 3rd-party systems, and accurately predict and populate the appropriate task or response.
Variable Memory
When you first create tasks, you can access session variables provides by our platform, or custom variables that you define, as well as the context that defines the scope of the variable.
This allows you to store and retrieve data that can be used for a variety of things, such as personalized greetings, determining where prior conversations left off, or pre-filling order details.
Developers can determine how long these variables are stored and accessible by your bots – so you can create more intuitive conversations with users on your terms.
Context Switching
Humans tend to switch back and forth between intents. To facilitate this, our platform allows developers to determine the conditions that must be met to enable or disable context switches, and can add conditional exceptions between tasks with the ability to pass contextual data between them.
Our platform handles virtually all complex and diverse content switching scenarios in an effective and efficient manner.
Also read : Dialog management
Unparalleled Flexibility With Multiple Context Types
Create bots that can remember user inputs and answers – and that can automatically modify their behavior based on sentiment and context. Connect to your backend business systems to get and store the data you need – data that is otherwise often static, contained within a single location, and rarely remembered in context. Our platform allows you to create dynamic conversational experiences with the ability to customize, categorize, and apply contextual information as you see fit.
What: Individual user information and preferences can be stored and used in varying tasks. This information can be shared with all enterprise bots that the user interacts with.
Why: Transactions and interactions are made shorter and easier, as users no longer have to provide the same basic information again and again.
Example: Information like a user’s home address, payment information, airline seat, or baggage preference can be stored and remembered for future interactions.
What: Information that represents company-wide rules and standards that apply to all users and bots.
Why: Allows developers to ensure bots keep company requirements in context and that they are enforced when needed.
Example: A company travel or expense policy could be applied that overrides an employee’s preferences when using a travel bot to book a flight or hotel.
What: User or task information dynamically captured at the bot level that can be used with some or all of the users of that bot.
Why: Allows you to use information captured by your bots – such as user or task counts and transaction values – to design additional logic that is specific to that bot.
Example: A customer-facing shopping bot could collect information about the number of users that purchase a product on a given day. Developers could design and apply logic that says to offer every 100th user a special promotion or discount.
What: Information given by the user that the bot must remember during a session.
Why: Keeps the user from having to repeat information that’s relevant for completing multiple tasks in a single session.
Example: A bank customer says, “how much do I have in checking?,” and then asks to “transfer $500 to savings.” The bot could recognize “checking” as session context and thus make the transfer without asking the user, “from which account?”.
- User Context
What: Individual user information and preferences can be stored and used in varying tasks. This information can be shared with all enterprise bots that the user interacts with.
Why: Transactions and interactions are made shorter and easier, as users no longer have to provide the same basic information again and again.
Example: Information like a user’s home address, payment information, airline seat, or baggage preference can be stored and remembered for future interactions.
- Enterprise Context
What: Information that represents company-wide rules and standards that apply to all users and bots.
Why: Allows developers to ensure bots keep company requirements in context and that they are enforced when needed.
Example: A company travel or expense policy could be applied that overrides an employee’s preferences when using a travel bot to book a flight or hotel.
- Bot Context
What: User or task information dynamically captured at the bot level that can be used with some or all of the users of that bot.
Why: Allows you to use information captured by your bots – such as user or task counts and transaction values – to design additional logic that is specific to that bot.
Example: A customer-facing shopping bot could collect information about the number of users that purchase a product on a given day. Developers could design and apply logic that says to offer every 100th user a special promotion or discount.
- Session Context
What: Information given by the user that the bot must remember during a session.
Why: Keeps the user from having to repeat information that’s relevant for completing multiple tasks in a single session.
Example: A bank customer says, “how much do I have in checking?,” and then asks to “transfer $500 to savings.” The bot could recognize “checking” as session context and thus make the transfer without asking the user, “from which account?”.
Custom Code Logic
Manipulate API responses, promote additional data to the user context, and pull data from the user context with support for custom code logic. This allows you to seamlessly extend the existing functionality of our platform and create advanced, custom conversational experiences that are driven by virtually any form of context.
