Rise of the Bots

by Rafael Casuso


Who is @Rafael_Casuso

  • Lead Front-End Engineer en StayApp

  • SnowStorm CEO and Co-Founder

  • Merlin Creator

  • Fullstack Senior Developer

  • Software Architect

  • JavaScript enthusiast


What is a Bot?

  • A Bot is an artificial intelligence with a human-like interface

  • A Conversational Bot simulates a conversation through programmatic responses

  • Are ChatBots the new apps?

  • Next big interface after Graphic, Mouse and Touch is Conversations (none is exclusive)

  • It usually runs on a messaging platform, external or custom, or is integrated into the OS

  • Famous bots (a type called Digital Assistants) include Siri, Cortana or Alexa


The Interface War

  • There is an ongoing War of Interfaces, driven by UX, with user adoption as the main goal

  • Conversation is the most natural interface for a human being

  • When Conversation is the Interface, Bot Personality is the UX

  • Different interfaces can be combined, graphical and conversational for example, as needed

  • There is also an ongoing Quest for the Lowest Friction

  • Bots on Messaging Platforms dodge the need for another app installation, thus reducing friction dramatically


Bot Types

  • There are endless possibilities for applications using conversational interfaces, both text and voice 

  • Internet of Things Device Manager: command-oriented

  • Customer Service: support and suggestions

  • Digital Assistant: hub for connected services, reservations, shopping

  • Advertisement: brand ambassadors, characters, friendly offers

  • Healthcare: medical appointments, diagnosis helper

  • Fintech: bank agent, financial advisor

  • Education: digital teachers, virtual tutors, examinators


Bot Intelligence

  • Rise of the Bots have come with the perfect storm: the emergence of AI, online services and the digital consumer

  • Conversational Accuracy is its UX success measure 

  • Simple Bots are applications that perform actions in response to keywords, exact phrases or predefined choices

  • Intelligent Bots can use Cognitive Services with Machine Learning

  • Natural Language Processing (NLP) is the most important cognitive process to achieve conversational accuracy

  • Machine Learning is based on general learning algorithms grounded in statistical inference instead of large sets of static rules 

Bot Intelligence


  • Discipline that uses Learning Algorithms, often grounded in statistical inference, to automatically learn rules through the analysis of large ammount of data

  • Statistical Inference is the process of infering Predictive Models

  • Predictive Models are created through main steps: data analysis, distribution visualization, transformation, predictive patterns inference from part of transformed data (Training) and finally model Evaluation with the other part of data

  • Neural Networks are a family of algorithms and models inspired by central nervous systems of animals

  • Examples are Google Cloud Machine Learning and Prediction APIAmazon Machine Learning or Microsoft Azure Machine Learning

Bot Intelligence

  • Bot main needs: Understand (parse text into structured data, categorize user intent), Converse (build natural answers), and Take Actions

  • Understanding includes extracting intents and entities from expressions through language models

  • Converse includes language generation, maintaining context (entities variables, user reference) and building a meaningful dialog

  • This main goals are achieved using Linguistic Analysis Libraries (Duckling) or APIs (IBM Linguistics)

  • Examples are Wit.ai (now Facebook Bot Engine), TextRazor, IBM Alchemy or Api.ai


Bot Intelligence

  • Taxonomy of models:

    • Retrieval-based models (easier) use a repository of predefined responses and heuristic to pick an appropriate response based on the input and context.

    • Generative models (harder) don’t rely on pre-defined responses. They generate new responses from scratch. Typically based on Machine Translation techniques.

  • Short (easier) conversations with goal of offering single response for single input vs Long (harder) ones with multiple turns and context.

  • Open domain (harder) where the user can take the conversation anywhere vs Closed domain (easier) where there is a specific goal.


Bot Intelligence

  • Image Analysis extracts useful information from images, related taxonomy (tags and categories) and face recognition

  • Emotion Recognition extracts range of feelings from images, texts or recordings

  • Speech Recognition allows text-to-speech and speech-to-text

  • ​Recommendations allows Frequently Bought Together, Item to Item and Personalized User Suggestions

  • Others include Academic Knowledge Relations or Articles Analysis

  • Examples are Microsoft Cognitive Services, IBM Watson and Google Cloud Vision, Speech Recognition and Translate APIs