Skip to content

References: AI in Information Systems

  1. Artificial intelligence - Wikipedia - Comprehensive overview of AI history, subfields, and current capabilities. Anchors the chapter's AI taxonomy used to organize predictive ML, generative AI, and agentic systems.

  2. Generative artificial intelligence - Wikipedia - Detailed treatment of generative AI including LLMs, diffusion models, and major vendors. Foundation for the chapter's generative-AI section.

  3. Retrieval-augmented generation - Wikipedia - Clear coverage of RAG architecture and its role in grounding LLMs in enterprise data. Directly supports the chapter's RAG content.

  4. AI Engineering - Chip Huyen - O'Reilly - Modern reference on building production AI systems including evaluation, prompt engineering, and deployment patterns; an essential complement to the chapter's apply-level RAG outcomes.

  5. Hands-On Large Language Models - Jay Alammar and Maarten Grootendorst - O'Reilly - Practitioner reference on working with LLMs in business applications; useful for the chapter's hands-on content.

  6. OpenAI Documentation - OpenAI - Authoritative documentation for one of the dominant LLM APIs, including embeddings, function calling, and structured outputs.

  7. Anthropic Claude Documentation - Anthropic - Documentation for the Claude API including prompt engineering best practices and tool use. Useful contrast to OpenAI for vendor-comparison exercises.

  8. Google Cloud AI Solutions - Google Cloud - Vendor reference for AI capabilities embedded in cloud platforms, including Vertex AI and Gemini. Supports the chapter's build-vs-buy-vs-API content.

  9. Microsoft AI Learning Path - Microsoft Learn - Free training paths covering AI services in Azure including OpenAI Service, Cognitive Services, and ML. Pairs well with the chapter's enterprise-AI content.

  10. LangChain Documentation - LangChain - Reference for the dominant open-source framework for building RAG and agentic applications. Useful for the chapter's hands-on prototype lab.