| RTF | Prompt engineering — best practices | OpenAI (Developer docs) |
| RTF | Prompting best practices — Give Claude a role | Anthropic (Claude Platform docs) |
| TAG | Prompting best practices — Add context to improve performance | Anthropic (Claude Platform docs) |
| TAG | Prompt design strategies | Google (Gemini API docs) |
| APE | Prompt engineering — best practices | OpenAI (Developer docs) |
| RACE | Prompt design strategies | Google (Gemini API docs) |
| RACE | Prompting best practices | Anthropic (Claude Platform docs) |
| CRAFT | Prompting best practices — Structure prompts with XML tags | Anthropic (Claude Platform docs) |
| CRAFT | Gemini 3 developer guide | Google (Gemini API docs) |
| GCSE | Get started writing prompts in Microsoft 365 Copilot | Microsoft Support |
| GCSE | The building blocks of a good Copilot prompt (quick reference guide, PDF) | Microsoft |
| TCREI | Google Prompting Essentials | Google (via Coursera) |
| TCREI | Prompt design strategies | Google (Gemini API docs) |
| RISEN | Prompting best practices — Use examples effectively | Anthropic (Claude Platform docs) |
| RISEN | Prompt engineering (how-to guide) | Meta (Llama developer docs) |
| CO-STAR | How I Won Singapore’s GPT-4 Prompt Engineering Competition | Sheila Teo, Towards Data Science |
| CO-STAR | Mastering the art of prompt engineering | GovTech Singapore |
| CLEAR | The CLEAR path: A framework for enhancing information literacy through prompt engineering | Lo, L. S. (2023), The Journal of Academic Librarianship 49(4), 102720 |
| CLEAR | The CLEAR Path (open-access record) | University of New Mexico Digital Repository |
| OpenAI | Model guidance | OpenAI (Developer docs) |
| OpenAI | Models | OpenAI (Developer docs) |
| OpenAI | Prompt engineering | OpenAI (Developer docs) |
| Anthropic | Prompting best practices | Anthropic (Claude Platform docs) |
| Anthropic | Models overview | Anthropic (Claude Platform docs) |
| Google | Gemini 3 developer guide | Google (Gemini API docs) |
| Google | Prompt design strategies | Google (Gemini API docs) |
| Google | Models | Google (Gemini API docs) |
| Google | Google Prompting Essentials | Google (via Coursera) |
| Meta | Prompt engineering (how-to guide) | Meta (Llama developer docs) |
| Meta | Llama 4 — model cards and prompt formats | Meta |
| Meta | Developer docs and resources | Meta |
| Microsoft | Get started writing prompts in Microsoft 365 Copilot | Microsoft Support |
| Microsoft | The building blocks of a good Copilot prompt (PDF) | Microsoft |
| xAI | Models | xAI / SpaceXAI |
| xAI | Reasoning | xAI / SpaceXAI |
| xAI | Prompt caching best practices | xAI / SpaceXAI |
| Mistral AI | Prompt engineering best practices | Mistral AI |
| Mistral AI | Models | Mistral AI |
| Mistral AI | Regional inference | Mistral AI |
| DeepSeek | Thinking mode | DeepSeek |
| DeepSeek | JSON output | DeepSeek |
| DeepSeek | Pricing | DeepSeek |
| DeepSeek | Privacy policy | DeepSeek |
| Few-shot examples | Prompting best practices — Use examples effectively | Anthropic |
| Few-shot examples | Prompt design strategies | Google |
| Delimiters and tags | Prompting best practices — Structure prompts with XML tags | Anthropic |
| Delimiters and tags | Gemini 3 developer guide | Google |
| System versus user message | Prompt engineering (how-to guide) | Meta |
| System versus user message | Prompt engineering | OpenAI |
| Structured output | Prompt engineering (how-to guide) | Meta |
| Structured output | Prompt engineering | OpenAI |
| Chain of thought | Chain-of-Thought Prompting Elicits Reasoning in Large Language Models | Wei et al., 2022 (arXiv) |
| Chain of thought | The Decreasing Value of Chain of Thought in Prompting | Wharton Generative AI Labs |
| Chain of thought | Gemini 3 developer guide | Google |
| Prompt chaining | Prompting best practices — Chain complex prompts | Anthropic |
| Self-consistency | Prompt engineering (how-to guide) | Meta |
| Grounding and retrieval | Prompt engineering (how-to guide) | Meta |
| Grounding and retrieval | Get started writing prompts in Microsoft 365 Copilot | Microsoft |
| Negative constraints | Model guidance | OpenAI |
| Negative constraints | Prompting best practices — Add context to improve performance | Anthropic |
| Meta-prompting | A practical guide to building with AI | OpenAI |
| Meta-prompting | Prompting best practices | Anthropic |
| Myths & anti-patterns | Should We Respect LLMs? A Cross-Lingual Study on the Influence of Prompt Politeness | Yin et al., 2024 (arXiv) |
| Myths & anti-patterns | Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy | Dobariya & Kumar, 2025 (arXiv) |
| Myths & anti-patterns | Prompting best practices — Give Claude a role | Anthropic |
| Myths & anti-patterns | Model guidance | OpenAI |
| Myths & anti-patterns | The Decreasing Value of Chain of Thought in Prompting | Wharton Generative AI Labs |
| Myths & anti-patterns | Gemini 3 developer guide | Google |
| Myths & anti-patterns | A practical guide to building with AI | OpenAI |
| Myths & anti-patterns | Prompt engineering — hallucination reduction | Meta |
| Myths & anti-patterns | The CLEAR path (open access) | Lo, L. S. (2023) |
| Reasoning models | The Decreasing Value of Chain of Thought in Prompting | Wharton Generative AI Labs |
| Reasoning models | Gemini 3 developer guide — thinking_level | Google |
| Reasoning models | Model guidance | OpenAI |
| Reasoning models | Prompting best practices — Thinking and reasoning | Anthropic |
| Reasoning models | Prompt engineering — chain-of-thought | Meta |
| Qwen 3.8 | Qwen3.8-27B model card | Alibaba (Hugging Face) |
| Qwen 3.8 | Qwen3.8-Flash-Next model card | Alibaba (Hugging Face) |
| DeepSeek V4 | DeepSeek-V4-Flash model card | DeepSeek (Hugging Face) |
| DeepSeek V4 | DeepSeek V4 release note | DeepSeek |
| GLM-5.x | GLM-5.2 model card | Z.ai (Hugging Face) |
| GLM-5.x | GLM-5.3 model card | Z.ai (Hugging Face) |
| Gemma 4 | Gemma 4: expanding the Gemmaverse with Apache 2.0 | Google Open Source Blog |
| Gemma 4 | Gemma 4 31B model card | Google (Hugging Face) |
| Mistral 3 / Small 4 | Mistral Small 4 announcement | Mistral AI |
| Mistral 3 / Small 4 | Mistral Small 4 model card | Mistral AI (Hugging Face) |
| Self-hosting | Chat templates | Hugging Face (Transformers docs) |
| Self-hosting | Optimizing LLMs for speed and memory | Hugging Face (Transformers docs) |
| Self-hosting | Gemma prompt structure | Google |
| Self-hosting | Gemma model overview | Google |
| Self-hosting | Reasoning best practices | OpenAI |
| Self-hosting | Chain-of-Thought Prompting Elicits Reasoning in Large Language Models | Wei et al., 2022 (arXiv) |
| Self-hosting | Lost in the Middle: How Language Models Use Long Contexts | Liu et al., 2023 (arXiv) |
| Self-hosting | Structured outputs | Ollama |
| Self-hosting | Context length | Ollama |
| Self-hosting | Ollama Cloud | Ollama |
| Self-hosting | GBNF grammars | llama.cpp |
| Self-hosting | Model deprecations | OpenAI |
| Self-hosting | Article 3: Definitions | EU Artificial Intelligence Act |
| Self-hosting | Article 4: AI literacy | EU Artificial Intelligence Act |
| Self-hosting | Opinion 28/2024 on AI models and GDPR | European Data Protection Board |
| Legal & privacy | Article 50: Transparency obligations for providers and deployers of certain AI systems | EU Artificial Intelligence Act |
| Legal & privacy | Guidelines on transparency obligations | European Commission |