{"slug": "ai-without-illusions-appendices", "title": "AI without illusions: Appendices", "summary": "The appendices for the 'AI without illusions' course provide reference material including a working vocabulary, a vendor-neutral tool selection framework, practical checklists for AI-assisted technical work, and a catalogue of common AI failure patterns. The appendices are designed to make professional AI use repeatable and are meant to be consulted as needed rather than read sequentially.", "body_md": "You are here:Appendices IndexCourse Index][ Appendix A ][Workshops\n\nThe main course follows a sequence. The appendices are reference material designed to be revisited.\n\nConsult them when a term becomes unclear, a tool decision needs structure, you are preparing to delegate work to an AI agent, or an AI-generated answer looks plausible but wrong.\n\nTogether, the appendices provide the course’s working vocabulary, decision frameworks, checklists, and failure references.\n\nRead the appendices as needed rather than working through all of them before starting the course.\n\nTheir purpose is to make professional AI use repeatable without adding process for its own sake.\n\nAI discussions become messy quickly because many important terms are overloaded. “Agent” can mean a tool-using model, a scripted workflow, a coding assistant, or a product feature. “Memory” can mean conversation history, persistent product memory, retrieved documents, or context still available within the current session. “Reasoning” can refer to inference-time computation, product branding, explicit problem decomposition, or simply an answer that sounds coherent.\n\nThis appendix defines the course’s terms in practical, technical language. It provides a working vocabulary for people who need to discuss generative AI, LLMs, tools, retrieval, agents, and AI-assisted programming precisely, without relying on vendor language or academic shorthand.\n\n**Use it when**\n\n**What it contains**\n\n**Best read with**\n\nTool selection becomes unreliable when people compare models through leaderboard screenshots, tools through social media momentum, and coding agents through the most impressive demonstration they have seen that week. Those signals can inform an evaluation, but they cannot replace requirements and evidence from the intended workflow.\n\nThis appendix provides a structured way to choose models and tools. It considers task shape, risk, data sensitivity, workflow fit, review burden, latency tolerance, cost profile, repository context, and operational overhead.\n\nThe framework is deliberately vendor-neutral so that it remains useful as products and model names change.\n\n**Use it when**\n\n**What it contains**\n\n**Best read with**\n\nChecklists become most valuable when work is moving quickly and shortcuts are tempting.\n\nThis appendix turns the course’s principles into practical review gates for technical work. Before asking AI to explain a codebase, change a file, carry out a refactor, generate tests, review a pull request, or act as an agent, establish clear answers to these questions:\n\nThese questions establish the boundary between supervised AI-assisted engineering and vibe-coding.\n\n**Use it when**\n\n**What it contains**\n\n**Best read with**\n\nRecurring AI failures are easier to manage when they have clear names.\n\nThese are recognizable failure patterns with causes that can be investigated and controls that can be improved.\n\nThis appendix catalogues common failures in AI-assisted technical work and provides a practical basis for diagnosing, supervising, correcting, and preventing them.\n\n**Use it when**\n\n**What it contains**\n\n**Best read with**\n\nProfessional AI use depends on durable reference material outside any single conversation.\n\nThe course explains the ideas. The appendices help readers apply them after they close the article.\n\n[AI without illusions: Appendices](https://blog.stackademic.com/ai-without-illusions-appendices-64f72c47c094) was originally published in [Stackademic](https://blog.stackademic.com) on Medium, where people are continuing the conversation by highlighting and responding to this story.", "url": "https://wpnews.pro/news/ai-without-illusions-appendices", "canonical_source": "https://blog.stackademic.com/ai-without-illusions-appendices-64f72c47c094?source=rss----d1baaa8417a4---4", "published_at": "2026-07-23 13:46:58+00:00", "updated_at": "2026-07-23 13:57:51.499058+00:00", "lang": "en", "topics": ["artificial-intelligence", "generative-ai", "ai-tools", "ai-agents", "ai-safety"], "entities": ["Stackademic"], "alternates": {"html": "https://wpnews.pro/news/ai-without-illusions-appendices", "markdown": "https://wpnews.pro/news/ai-without-illusions-appendices.md", "text": "https://wpnews.pro/news/ai-without-illusions-appendices.txt", "jsonld": "https://wpnews.pro/news/ai-without-illusions-appendices.jsonld"}}