Explore by Question

Begin with the question closest to the problem you are trying to understand. The directory contains all 100 canonical CKP questions, grouped by their governed themes.

Reliability and Hallucination

  1. Why does AI make things up?
  2. How can I stop AI hallucinating?
  3. Why is AI confidently wrong?
  4. Why does AI give different answers to the same question?
  5. How do I know whether an AI answer is trustworthy?
  6. Why does AI invent sources or quotations?
  7. Should I ask AI to admit when it does not know?
  8. Can a better prompt guarantee accuracy?
  9. Why does AI repeat an error after I correct it?
  10. When should I verify an AI answer myself?

Context and Relevance

  1. How much context should I give AI?
  2. Why does too much context make answers worse?
  3. Why does AI ignore an important detail I supplied?
  4. Should I paste my entire document into AI?
  5. How do I make AI understand what I really want?
  6. Why does AI answer the wrong question?
  7. How do I keep background information from overwhelming the task?
  8. What should go into a project context file?
  9. How do I handle conflicting information in my notes?
  10. Can AI decide which context is relevant by itself?

Memory and Continuity

  1. Why does AI forget what I told it?
  2. Why do long conversations become less reliable?
  3. How do I continue a project in a new chat?
  4. What should AI remember permanently?
  5. How do I stop repeating myself to AI?
  6. Is AI memory enough for serious work?
  7. How do I preserve decisions made across many sessions?
  8. What is the difference between memory and preparation?
  9. How do I recover after a project conversation has become confused?
  10. How can AI maintain continuity without carrying every old message?

Prompting and Instruction

  1. Why are my prompts becoming longer and longer?
  2. Do I need to become a prompt engineer?
  3. What makes a good professional AI instruction?
  4. Why does a prompt work once and fail later?
  5. Should I use a standard prompt template?
  6. How detailed should my instructions be?
  7. Why does AI follow some instructions and ignore others?
  8. Should I tell AI what role to adopt?
  9. Can examples improve AI output?
  10. What is more important: the prompt or the context?

Professional Work and Quality

  1. Why does AI produce generic professional writing?
  2. How do I make AI work like an experienced colleague?
  3. Why do I spend so long correcting AI output?
  4. How can AI preserve my voice?
  5. How do I stop AI changing the meaning of my work?
  6. Can AI perform expert work without an expert present?
  7. How do I get consistent output across repeated tasks?
  8. Why does AI polish weak thinking instead of improving it?
  9. How should AI handle specialist terminology?
  10. What does 'human in the loop' actually require?

Decision-Making and Priorities

  1. Can AI help me decide what to do next?
  2. Why does AI give me obvious recommendations?
  3. How can AI prioritise competing work?
  4. Can AI act as a chief of staff?
  5. How do I make AI challenge my assumptions?
  6. Why does AI agree with me too easily?
  7. How can AI help with strategic planning?
  8. How should AI deal with uncertainty in a decision?
  9. Can AI distinguish urgent work from important work?
  10. How do I prevent AI from creating more work than it saves?

Knowledge Management and Retrieval

  1. How should I organise knowledge for AI?
  2. Do I need a vector database?
  3. What is the difference between RAG and CKP?
  4. Why does search return relevant documents but poor answers?
  5. How do I know which source AI should trust?
  6. Should all company knowledge be available to AI?
  7. How do I keep AI knowledge up to date?
  8. What should happen when two authoritative sources disagree?
  9. How can AI reuse lessons from previous work?
  10. Why is a folder full of documents not a knowledge system?

Governance, Risk and Accountability

  1. How do we govern AI without stopping useful work?
  2. Who is accountable for an AI-assisted decision?
  3. How do we prevent confidential information leaking into AI?
  4. When should AI be prohibited from acting alone?
  5. How can we audit an AI-generated result?
  6. What should an AI policy contain?
  7. How do we stop outdated rules guiding new work?
  8. Can AI governance be automated?
  9. How should AI handle personal or sensitive data?
  10. What evidence should be kept when AI contributes to work?

Teams, Organisations and Scale

  1. How do we stop everyone using AI differently?
  2. Should teams share prompts?
  3. How do we keep AI outputs consistent across departments?
  4. How should we train staff to use AI?
  5. Why do AI pilots succeed but operational use fails?
  6. How can organisational knowledge survive staff turnover?
  7. Can CKP work across different AI systems?
  8. How do we prevent duplicate AI work?
  9. How can managers know whether AI is genuinely helping?
  10. What changes when AI use scales across an organisation?

Architecture, Workflow and the Future of AI Work

  1. Why is a chatbot not enough for complex work?
  2. What is the missing layer between people and AI?
  3. How should an AI workflow begin?
  4. When should AI retrieve information and when should it generate?
  5. How do I design AI work that survives model changes?
  6. Should AI systems prepare information before I ask?
  7. How can AI move from answering questions to supporting action?
  8. What makes an AI system professionally dependable?
  9. Is better AI mainly a model problem?
  10. What is CKP's central answer to these 100 questions?