Planning and deploying chatbots

Before implementing chatbots in your organization, you must plan and identify the use cases that you want to address by using chatbot.

Typically, planning and deploying a chatbot includes the following stages:

Chatbot best practices_plan and deploy - v2.png

Best practices for planning, implementing, and operating chatbots

The following presentation explains the stages and best practices for planning, implementing, and operating BMC Helix Virtual Agent:

BMC Helix Chatbot_Operational Best Practices.pdf

Additional information about IBM Watson Assistant capabilities

The following blog links provide more information about IBM Watson Assistant capabilities. BMC does not endorse the information in these external blog links. The information provided in these links should be used for reference purposes only.

Best practices for IBM Watson Assistant capabilities

Category	Reference in IBM Watson Assistant documentation	Blogs
Disambiguation Self-learning from Disambiguation selections Measure customer effort	Controlling the conversational flow Enable your skill to improve itself with autolearning Tracking the impact of autolearning	General Guidelines For Chatbot Scripts Enable Your Chatbot To Disambiguate Intelligently With Automatic Learning How To Measure Customer Effort With IBM Watson Assistant
Digression	Understanding dialog skill digressions	Why Your Chatbot Conversation Must Allow For Digression
Spelling correction (language dependent) and Fuzzy marching	Correcting user input	How IBM Watson Assistant Is Correcting User Input For Chatbots
Irrelevancy detection	Defining what's irrelevant	Two Significant Enhancements Were Made To IBM Watson Assistant
Intent conflict resolution	Creating intents	How To Resolve Intent Conflicts With IBM Watson Assistant
Annotated Contextual Entities	Annotation-based method	Contextual Entities with IBM Watson Assistant
Handling compound intents	Tips for capturing information from user input	Dealing With Compound User Intents In IBM Watson Assistant
NLG (Random responses per node)	Adding variety	Chatbots: Creating Natural Language From Structured Data
Intent recommendations Example utterances recommendation	Getting help with intents Getting intent user example recommendations	Taking A Look at IBM Watson Assistant Intent Recommendations

Planning and deploying chatbots

Best practices for planning, implementing, and operating chatbots

Additional information about IBM Watson Assistant capabilities

On this page