new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

IBM Carbon · all subjects

chatbot

8 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

When to use a chatbot

Use a chatbot when a user would benefit from requesting information on-demand with natural language. They should receive a useful and trustworthy response related to their question or task.

Common chatbot use cases

Common business use cases for chatbots include: providing in-context help and guidance (e.g., scaling a company's FAQ or helping a user get started); triaging or setting priority of cases by soliciting information from the user to decrease workload on humans (support tickets, patient symptom severity); performing common tasks or procedures (e.g., pay a bill, transfer money, or assist with electing health benefits); and using natural language to search for information (e.g., find specific information like current balance, or dosing instructions for a medication).

Questions to justify chatbot as appropriate solution

Before building a chatbot, ask these questions: What are the users' goals? How in-depth is the assistance the user will need? Is your domain better served by human assistance? How is a bot superior to online documentation, contextual support, wizards, etc.? What kind of data sources or abilities can this bot leverage for your business and your users?

User needs within a conversation

Within a conversation, a user may need to provide the bot with more context via structured responses, to know what the bot understands through reflection and confirming questions, and to identify the most recent and relevant message to improve understanding.

User needs from a chatbot

A user may need: access to help at any time; an on-demand, relevant answer to a question; and high quality, consistent information about a product or service.

When NOT to use a chatbot

Do not use a chatbot when: a task could be accomplished more efficiently using a traditional user interface; a process is very complex or could take a long time; or a real human is needed for sensitive or emotional topics.

Supported chatbot components and their status

Carbon currently offers the following chatbot components: Chatbot window (Design available, Contribution needed); Chatbot header (Design available, Contribution needed); System message (Design available, Contribution needed); User message (Design available, Contribution needed); Structured response (Design available, Contribution needed); Chatbot cards (Design available, Contribution needed); Chatbot text input (Design available, Contribution needed); Launch button (Design available, Contribution needed); Welcome screen (Preview, Contribution needed); Expandable card (Preview, Contribution needed); Human message (Preview, Contribution needed); List (Coming soon, Contribution needed); Launch button chips (Coming soon, Contribution needed); Multiple threads menu (Coming soon, Contribution needed).

Chatbot Design Kit Sketch library

The Chatbot Design Kit is available as a Sketch library that can be added to Sketch with Sketch Cloud. Users can access the link and click 'Add Library to Sketch' to receive automatic updates to chatbot symbols. A document with common chatbot sub-patterns, features, and preview components is available for download.

Give your agent this brain