Conversational ai
Conversational AI is artificial intelligence that enables software systems to interact with users through natural-language dialogue.
AI for Everyday IT
Conversational AI is artificial intelligence that supports ongoing dialogue by interpreting user messages and generating context-aware responses.
- How it is used
- Deploys conversational interfaces for IT support, document work, email assistance, database tasks, analysis, and practical problem solving.
- How deep it goes
- Explains capabilities through workplace scenarios and prompts, while deferring model internals and emphasizing token limits, verification, and privacy.
- Examples
- Demonstrates email prompts, VPN-ticket analysis, SQL generation, document extraction, and clarification of a caller’s fuzzy screen complaint.
- What you can do after
- Apply it via ChatGPT, Claude, Gemini, Copilot, or APIs to draft, analyze, troubleshoot, translate, and generate task-specific outputs.
Natural Language Processing in Action, Second Edition
A dialog engine is a software system that manages conversational interaction and generates responses to user statements.
- How it is used
- Supports back-and-forth natural-language interaction in assistants, customer service, healthcare, and team operations.
- How deep it goes
- Builds from a two-intent Python recognizer to response strategies and a five-subsystem pipeline, while treating speech processing largely as an external wrapper.
- Examples
- Uses a Python greeting recognizer, customer-service bots, virtual assistants, and a diagram of the recirculating chatbot pipeline.
- What you can do after
- Build it from scratch by assembling recognition, response generation, decision, and memory components around a user's conversational goal.
Read how Natural Language Processing in Action, Second Edition explains conversational ai →
Introduction to Generative AI, Second Edition
A conversational agent is an AI software system that interacts with users through natural-language dialogue to answer questions or perform tasks.
- How it is used
- Frames dialogue as an interface for answering questions and assisting with work, shopping, customer service, and daily tasks.
- How deep it goes
- Compares pattern-matching, fixed-command, and LLM-powered systems at a high level without detailing implementation.
- Examples
- Uses ELIZA, ChatGPT, bank chatbots, shopping queries, and a confidential-contract prompt to show capabilities and risks.
- What you can do after
- Evaluate/understand conversational tools by distinguishing flexible replies from reliable answers and considering what information a prompt reveals.
Read how Introduction to Generative AI, Second Edition explains conversational ai →
Effective Conversational AI
A virtual assistant is software that conducts natural-language interactions to answer questions or perform tasks for a user.
- How it is used
- Automates customer service, answers questions, guides transactions, or routes users to specialist bots and human agents.
- How deep it goes
- Explains the request-to-fulfillment flow, its main components, user-centered design, and improvement criteria; defers a fuller build-process treatment.
- Examples
- Contrasts burdensome and context-aware claim-status conversations and uses password resets to illustrate intent recognition and fulfillment.
- What you can do after
- Build it from scratch with IBM watsonx Assistant, then evaluate user friction and improve the assistant against business outcomes.
Read how Effective Conversational AI explains conversational ai →
The Complete Obsolete Guide to Generative AI
Software that interacts with users conversationally and performs information, control, or task-oriented operations.
- How it is used
- Positions assistants as round-the-clock service and customer-support automation for faster responses and leaner operations.
- How deep it goes
- Mentions assistant applications and benefits but does not detail their implementation, prompting, or configuration.
- Examples
- Uses round-the-clock virtual assistance and startup customer-support chatbots as practical examples.
- What you can do after
- Evaluate/understand assistants as tools for improving service speed, automating work, and supporting business decisions while allowing for output errors.
Read how The Complete Obsolete Guide to Generative AI explains conversational ai →
Generative AI in Action
A chatbot is software that conducts conversational interactions with users through text or speech.
- How it is used
- Uses conversational interfaces for customer queries, enterprise-data questions, and developer assistance.
- How deep it goes
- Works through a staged retrieval-and-generation design and application layers, without detailing speech handling or model internals.
- Examples
- Uses a post archive for chat with data and Copilot Chat for explaining selected or legacy code.
- What you can do after
- Build it from scratch as a chat-with-data application using stored embeddings, search, and LLM generation.
Read how Generative AI in Action explains conversational ai →
AI Agents and Applications
A chatbot is a conversational software interface that maintains context across multiple exchanges for dialogue and interactive question answering.
- How it is used
- Provides a dialogue interface for interactive Q&A that carries context across exchanges.
- How deep it goes
- Builds from single-document prompting to a RAG function and a chat-history-aware chain, exposing the failure of stateless follow-ups.
- Examples
- Uses document-grounded questions about Paestum and a vague follow-up whose meaning depends on chat history.
- What you can do after
- Build it from scratch with RAG, then apply LangChain to retain chat history and handle follow-up questions.
Read how AI Agents and Applications explains conversational ai →
Writing for Developers: Blogs that get read
A software system that communicates with users through conversational messages, typically in response to prompts or events.
- How it is used
- Uses conversational AI as a final writing-review assistant for surfacing possible language errors.
- How deep it goes
- Explains prompting, iterative review, and skeptical validation, but stops short of describing chatbot implementation internals.
- Examples
- Demonstrates article-usage questions and prompts checking grammar, spelling, punctuation, verb tense, and terminology.
- What you can do after
- Apply via AI chatbots to surface candidate language errors, then verify each suggestion and revise selectively.
Read how Writing for Developers: Blogs that get read explains conversational ai →
Build AI-Enhanced Web Apps
AI technology that supports interactive, dialogue-based communication with users.
- How it is used
- Enables natural-language dialogue in web apps, from message-based help to questions about uploaded documents.
- How deep it goes
- Develops the UI, backend, conversation-state, and retrieval flows; the supplied evidence does not detail model internals.
- Examples
- Uses a text chat app and a PDF/DOCX knowledge base whose uploaded documents support question answering.
- What you can do after
- Build it from scratch as a text-chat web app, then apply the Vercel AI SDK and LangChain.js to document-grounded dialogue.
Read how Build AI-Enhanced Web Apps explains conversational ai →
WordPress Power Toolkit: Harness AI to build next-level websites
An AI system is a software system that uses artificial-intelligence methods to perform tasks such as interpreting queries and generating or ranking answers.
- How it is used
- Supports website planning, design, promotion, and visitor-facing answers through conversational requests.
- How deep it goes
- Explains prompting, conversational refinement, input limits, and search behavior without describing AI internals.
- Examples
- Uses a detailed bakery-writer prompt, catering color-scheme advice, and blog-promotion suggestions from analytics data.
- What you can do after
- Apply it through chatbots to refine requests and obtain tailored website recommendations.
Lead Developer Career Guide
Artificial intelligence that communicates with people through natural-language dialogue.
- How it is used
- Supports developer productivity through code suggestions and gives lead developers an adoption decision to assess.
- How deep it goes
- Explains capabilities, benefits, risks, and evaluation criteria, but does not teach assistant implementation.
- Examples
- Uses GitHub Copilot, Tabnine, and Kite as examples of coding assistants.
- What you can do after
- Evaluate/understand AI coding assistants for team adoption and communicate a balanced recommendation to management.
Read how Lead Developer Career Guide explains conversational ai →
AI Agents in Action, Second Edition
A software system that performs tasks with user approval, typically through a conversational interface.
- How it is used
- Distinguishes supervised conversational assistance from direct LLM chat and autonomous agent workflows.
- How deep it goes
- Defines the patterns through tools, approval, and execution loops, without descending into model internals.
- Examples
- Uses image generation, web search, document editing, and Claude Desktop to illustrate different interaction patterns.
- What you can do after
- Evaluate/understand whether a conversational system is answering, performing an approved task, or pursuing a multistep goal.
Read how AI Agents in Action, Second Edition explains conversational ai →
The Quick Python Book, Fourth Edition
A chatbot is software that conducts conversational interactions with users through natural-language input and output.
- How it is used
- Uses chatbot prompts to generate or refactor Python solutions for programming exercises.
- How deep it goes
- Works through prompt context, code generation, and output checks; does not explain chatbot internals.
- Examples
- Shows a wc-style command-line refactor and a weather-file CSV conversion whose generated county filter fails.
- What you can do after
- Apply it via Colaboratory or GitHub Copilot to request Python code, then run and evaluate the result.
Read how The Quick Python Book, Fourth Edition explains conversational ai →
LLMs in Production
An AI assistant is software that interacts with users and performs tasks through artificial-intelligence capabilities.
- How it is used
- Uses language interaction to improve communication and automate tasks such as customer support, shopping recommendations, and coding assistance.
- How deep it goes
- Links chatbot dataset preparation to a VS Code copilot built around an existing model and RAG, without detailing assistant internals.
- Examples
- Uses an HR FAQ chatbot and a Python-focused VS Code copilot to illustrate practical applications.
- What you can do after
- Build a Python-focused VS Code copilot around an existing coding model and RAG, or prepare Slack data for chatbot training.
The Art of AI Product Development
A virtual assistant is software that interacts with users conversationally to provide information or perform requested tasks.
- How it is used
- Supports user interaction through conversation, alongside graphical or hybrid interface options.
- How deep it goes
- Places conversational interfaces within the AI solution space and links interface design to automation and user control.
- Examples
- Uses an investment-professional chatbot that turns questions into SQL and raises reliability, training-data, and compliance concerns.
- What you can do after
- Evaluate interface choices by balancing automation with user control and allocating work between people and AI.
Read how The Art of AI Product Development explains conversational ai →
Authorization in Action
An AI system is software that applies artificial-intelligence capabilities to perform or assist with tasks such as interpreting information, generating content, analyzing artifacts, or making recommendations.
- How it is used
- Assists policy design, analysis, and authorized prompt construction while keeping access decisions with a deterministic policy engine.
- How deep it goes
- Explains authorization boundaries, nondeterminism, and design-time workflows, but defers concrete prompts and policy files to a separate walkthrough.
- Examples
- Uses a support chatbot, an engineer-request evaluator, nondeterministic permit-deny outcomes, and authorized prompt contexts.
- What you can do after
- Evaluate AI authorization proposals and apply assistants to policy design without placing them in the enforcement path.
Read how Authorization in Action explains conversational ai →
How Large Language Models Work
A software system that conducts conversational interactions with users through natural-language messages.
- How it is used
- Deploys conversational interaction as a possible customer-support interface, while weighing usefulness against accuracy, reliability, and liability.
- How deep it goes
- Explains the support use case and deployment risks, but stops short of specifying implementation details or a reliability procedure.
- Examples
- Uses technical support, FAQs, email tickets, automated phone systems, and decision-tree expert systems as comparison points.
- What you can do after
- Evaluate whether a chatbot is appropriate by comparing its benefits with the cost and liability of incorrect responses.
Read how How Large Language Models Work explains conversational ai →
Inside AI
A virtual assistant is a software system that performs tasks or provides information through interaction with users, often using natural-language requests.
- How it is used
- Provides information and real-time support through natural conversation with users.
- How deep it goes
- Explains ELIZA's keyword-and-rule replies and contrasts them with LLM-powered chatbots, but does not detail current model operation.
- Examples
- Uses ELIZA's therapeutic dialogue and names ChatGPT, Siri, Alexa, and Google Assistant as chatbot examples.
- What you can do after
- Evaluate conversational systems by distinguishing fluent replies from demonstrated understanding.
Effective Platform Engineering
An intelligent assistant is a software application that interprets user requests and automates tasks or provides information through conversational or other interactive interfaces.
- How it is used
- Supports engineering platforms by automating routine work and connecting teams with tools and information.
- How deep it goes
- Specifies implementation steps through testing and AI-feature planning, while leaving detailed AI application outside scope.
- Examples
- Uses deployment assistance, FAQ answers, monitoring alerts, deployment status, and documentation links as candidate functions.
- What you can do after
- Build it from scratch by prioritizing use cases, implementing an MVP, integrating a secure channel, and testing workflows.
Read how Effective Platform Engineering explains conversational ai →
Build Python Web Apps with Streamlit
A chatbot is a software application that conducts conversational interactions with users through natural-language input and output.
- How it is used
- Builds practical chat interfaces for LLM apps, from simple conversations to customer-service support.
- How deep it goes
- Demonstrates a short chatbot implementation and outlines retrieval and tool workflows, leaving their backend details for later.
- Examples
- Uses a short Streamlit chatbot and a customer-service bot for order tracking, cancellations, and human escalation.
- What you can do after
- Build from scratch a Streamlit chat interface, then extend it to answer company-specific questions and perform customer-service actions.
Read how Build Python Web Apps with Streamlit explains conversational ai →
Related concepts
- ChatGPTincludes · ChatGPT is OpenAI’s conversational AI service, which lets users interact with generative AI models and related tools through natural-language prompts.
- language modeluses · A language model is a computational model that represents patterns in linguistic tokens to estimate sequence probabilities and predict or generate language from context.
- GitHub Copilotincludes · GitHub Copilot is an AI-powered programming assistant that provides code suggestions, generation, and other software-development assistance based on prompts and programming context.
- AI agentkind of · An AI agent is a computational system that uses artificial intelligence to interpret information, select actions, and pursue goals through interaction with an environment.
- promptuses · An input, typically containing instructions or context, supplied to an artificial-intelligence model to guide or elicit its output.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.