Skip to content

Chapters

This textbook is organized into 20 chapters covering 400 concepts.

Chapter Overview

  1. AI-Powered Customer Research Foundations — Introduces AI, generative models, synthetic users, persona testing, and traditional methods, establishing the foundation for comparing human and AI-assisted customer research.
  2. Research Design and Evidence Quality — Examines focus groups, interviews, surveys, research objectives, validity, reliability, repeatability, and evidence so learners can frame credible, appropriately scoped persona-testing studies.
  3. AI Capabilities, Limitations, and Bias — Explores simulation fidelity, response variability, hallucinations, bias, confidence, and human judgment so learners recognize where synthetic feedback succeeds or fails.
  4. Responsible AI, Privacy, and Governance — Establishes responsible practices for consent, privacy, sensitive data, transparency, fairness, oversight, governance, auditing, accountability, and escalation in AI-assisted research.
  5. Building Complete Customer Personas — Builds persona profiles from identity, context, demographics, psychographics, attitudes, values, goals, motivations, needs, pain points, and frustrations.
  6. Persona Motivations, Behaviors, and Evidence — Extends personas with emotional and functional needs, buying behavior, decision criteria, channels, scenarios, evidence bases, specificity, and completeness.
  7. Customer Segmentation and Persona Archetypes — Introduces segmentation methods while distinguishing primary, secondary, negative, adversarial, international, accessibility, and customer-state archetypes.
  8. Jobs-to-Be-Done and Customer Journeys — Applies Jobs-to-Be-Done, switching forces, customer circumstances, journey stages, touchpoints, moments of truth, friction, and opportunity.
  9. Persona Consistency, Validation, and Reuse — Develops methods for detecting drift, validating fidelity, measuring coverage and diversity, managing versions, and building reusable persona libraries and benchmarks.
  10. Prompt Engineering Foundations — Introduces prompt objectives, structures, roles, persona and reviewer instructions, context management, task definitions, constraints, and output requirements.
  11. Structured Prompts and Reliable Outputs — Refines prompts through specificity, grounding, examples, variables, templates, chaining, schemas, structured fields, evidence, confidence, and missing-data handling.
  12. Prompt Testing and Research Dialogue — Covers prompt benchmarks, iteration, failure modes, instruction conflicts, consistency, neutral questioning, probes, adversarial questions, reflection, and synthesis.
  13. Designing AI Agents and Expert Roles — Defines agent goals, instructions, context, memory, tools, autonomy, and boundaries before configuring persona, moderator, skeptic, analyst, and expert agents.
  14. Multi-Agent Workflows, Debate, and Consensus — Builds multi-agent workflows through orchestration, handoffs, shared contexts, parallel evaluation, moderated discussion, debate, consensus, minority opinions, and disagreement analysis.
  15. Moderation Risks and Brand Strategy — Addresses neutrality, groupthink, opinion contamination, aggregation, and conflict resolution before connecting those safeguards to brand identity, positioning, voice, and messaging.
  16. Evaluating Marketing Assets and Messaging — Applies the system to logos, websites, product pages, advertisements, campaigns, social content, email, calls to action, journeys, competitors, and differentiation.
  17. Evaluation Rubrics, Scoring, and Evidence — Creates reusable frameworks with criteria, rubrics, fairness checks, rating scales, weighted scores, normalization, confidence ratings, evidence standards, trust, and clarity measures.
  18. Marketing Metrics and Pattern Analysis — Measures resonance, memorability, intent, credibility, relevance, and accessibility before analyzing benchmarks, persona comparisons, themes, contradictions, gaps, and trust signals.
  19. Risk-Based Recommendations and Knowledge Graphs — Converts findings into rated risks and prioritized recommendations while introducing knowledge graphs containing personas, assets, goals, pain points, and reactions.
  20. Automation, Reporting, and Capstone Systems — Completes the graph model, then automates evaluation, summarization, comparisons, reports, dashboards, improvement plans, organizational memory, and the capstone system.

How to Use This Textbook

Work through the chapters in order because each chapter is placed only after all concepts it depends on have been introduced. Learners with prior experience may use the prerequisite links in each outline to identify the shortest safe path to a later topic.

Note: Each chapter includes a list of concepts covered. Complete the listed prerequisites before moving to advanced chapters.