Sources¶
Every reference used across this knowledge base — research papers, official documentation, practitioner content, frameworks, standards, and curated links — in one place. 120+ sources, deduplicated and organized.
Last updated: 2026-03-22
Research papers¶
| # | Authors / Title | Year | Topic | Link |
|---|---|---|---|---|
| 1 | Vaswani et al., Attention Is All You Need | 2017 | LLM foundations | arXiv:1706.03762 |
| 2 | Lewis et al., Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks | 2020 | Context engineering | arXiv:2005.11401 |
| 3 | Kaplan et al., Scaling Laws for Neural Language Models | 2020 | LLM foundations | arXiv:2001.08361 |
| 4 | Hu et al., LoRA: Low-Rank Adaptation of Large Language Models | 2022 | Full-stack LLM | arXiv:2106.09685 |
| 5 | Hoffmann et al., Training Compute-Optimal Large Language Models (Chinchilla) | 2022 | LLM foundations | arXiv:2203.15556 |
| 6 | Ouyang et al., Training Language Models to Follow Instructions with Human Feedback | 2022 | Full-stack LLM | arXiv:2203.02155 |
| 7 | Yao et al., ReAct: Synergizing Reasoning and Acting in Language Models | 2023 | Agentic AI | arXiv:2210.03629 |
| 8 | Schick et al., Toolformer: Language Models Can Teach Themselves to Use Tools | 2023 | Agentic AI | arXiv:2302.04761 |
| 9 | Liu et al., Lost in the Middle: How Language Models Use Long Contexts | 2023 | Context engineering | arXiv:2307.03172 |
| 10 | OpenAI, GPT-4 Technical Report | 2023 | LLM foundations | arXiv:2303.08774 |
| 11 | Zhao et al., A Survey of Large Language Models | 2023 (updated 2025) | LLM foundations | arXiv:2303.18223 |
| 12 | Rafailov et al., Direct Preference Optimization | 2023 | Full-stack LLM | arXiv:2305.18290 |
| 13 | Dettmers et al., QLoRA: Efficient Finetuning of Quantized Language Models | 2023 | Full-stack LLM | arXiv:2305.14314 |
| 14 | A Survey on the Memory Mechanism of LLM-based Agents | 2024 | Agentic AI | arXiv:2404.13501 |
| 15 | Maximum Effective Context Window | 2024 | Context engineering | OAJAIML |
| 16 | Meta, The Llama 3 Herd of Models | 2024 | LLM foundations | arXiv:2407.21783 |
| 17 | Memory in the Age of AI Agents | 2024 | Agentic AI | arXiv:2512.13564 |
| 18 | Beyond ReAct: Planner-Centric Framework for Complex Tool-Augmented LLM Reasoning | 2025 | Agentic AI | arXiv:2511.10037 |
| 19 | PROBE: Measuring Proactive Problem Solving in LLM Agents | 2025 | Agentic AI | OpenReview |
| 20 | (Mis)Fitting: A Survey of Scaling Laws | 2025 | LLM foundations | arXiv:2502.18969 |
| 21 | Post-Training Scaling survey | 2025 | Full-stack LLM | ACL Anthology |
| 22 | DeepSeek, DeepSeek-R1 Technical Report | 2025 | LLM foundations | arXiv:2501.12948 |
| 23 | What Works for 'Lost-in-the-Middle'? | 2025 | Context engineering | arXiv:2511.13900 |
| 24 | Lost in the Middle follow-up | 2025 | Context engineering | arXiv:2510.10276 |
| 25 | The Landscape of Agentic RL for LLMs: A Survey | 2026 | Agentic AI | arXiv:2509.02547 |
| 26 | Context Engineering vs Prompt Engineering (9,649 experiments) | 2026 | Context engineering | KeepMyPrompts |
AI vendor documentation¶
| # | Provider | Resource | Link |
|---|---|---|---|
| 27 | Anthropic | Claude API docs | docs.anthropic.com |
| 28 | Anthropic | Context windows | docs.anthropic.com/.../context-windows |
| 29 | Anthropic | Compaction | docs.anthropic.com/.../compaction |
| 30 | Anthropic | Prompt caching | docs.anthropic.com/.../prompt-caching |
| 31 | Anthropic | Prompt engineering / Claude best practices | docs.anthropic.com/.../claude-4-best-practices |
| 32 | Anthropic | Tool use | docs.anthropic.com/.../tool-use |
| 33 | Anthropic | Introducing prompt caching (news) | anthropic.com/news/prompt-caching |
| 34 | OpenAI | Platform docs | platform.openai.com/docs |
| 35 | OpenAI | Conversation state | platform.openai.com/.../conversation-state |
| 36 | OpenAI | Compaction (API) | developers.openai.com/.../compaction |
| 37 | AI / Gemini docs | ai.google.dev/docs | |
| 38 | Rules of ML (ML engineering) | developers.google.com/.../rules-of-ml | |
| 39 | AWS | Bedrock docs | docs.aws.amazon.com/bedrock |
| 40 | Azure | OpenAI Service docs | learn.microsoft.com/.../openai |
| 41 | Hugging Face | Hub and docs | huggingface.co/docs |
Cursor and editor documentation¶
| # | Resource | Link |
|---|---|---|
| 42 | Cursor documentation (official) | docs.cursor.com |
| 43 | Cursor — Rules | cursor.com/docs/context/rules |
| 44 | Cursor — Chat overview | docs.cursor.com/chat/overview |
| 45 | Cursor — llms.txt / doc index |
cursor.com/llms.txt |
| 46 | Cursor pricing | cursor.com/pricing |
Frameworks and tools¶
| # | Framework | Category | Link |
|---|---|---|---|
| 47 | LangChain / LangGraph | Agent frameworks | python.langchain.com |
| 48 | LangChain — Short-term memory | Agent memory | docs.langchain.com/.../short-term-memory |
| 49 | Microsoft AutoGen | Multi-agent | microsoft.github.io/autogen |
| 50 | CrewAI | Multi-agent | docs.crewai.com |
| 51 | LMSYS Chatbot Arena | LLM evaluation | chat.lmsys.org |
| 52 | vLLM | Inference serving | docs.vllm.ai |
| 53 | Neo4j — GraphRAG introduction | Knowledge graphs | neo4j.com/blog/... |
Established practitioners¶
| # | Author | Resource | Link |
|---|---|---|---|
| 54 | Lilian Weng | LLM Powered Autonomous Agents | lilianweng.github.io/.../agent |
| 55 | Lilian Weng | The Transformer Family | lilianweng.github.io/.../transformer-family |
| 56 | Chip Huyen | Building LLM Applications for Production | huyenchip.com/.../llm-engineering |
| 57 | Chip Huyen | AI Engineering (O'Reilly, 2025) | oreilly.com |
| 58 | Andrej Karpathy | Let's build GPT from scratch (YouTube) | youtube.com |
| 59 | Andrej Karpathy | nanoGPT (GitHub) | github.com/karpathy/nanoGPT |
| 60 | Andrej Karpathy / Tobi Lutke | Context engineering framing | the-decoder.com |
| 61 | Jay Alammar | The Illustrated Transformer | jalammar.github.io |
| 62 | Simon Willison | Long context / context engineering | simonwillison.net/tags/long-context |
| 63 | Simon Willison | Long context in LLM 0.24 | simonwillison.net |
| 64 | Shopify Engineering | Building production-ready agentic systems | shopify.engineering |
| 65 | Cognition AI | Devin (autonomous software engineer) | cognition.ai |
| 66 | Field Guide to AI | Context management | fieldguidetoai.com |
| 67 | Zylos | LLM context management (2026) | zylos.ai |
| 68 | Towards AI | Context Window Paradox | pub.towardsai.net |
| 69 | Towards AI | Context engineering for AI coding agents | pub.towardsai.net |
| 70 | AI Transfer Lab | Claude's 1M context... until it isn't | medium.com |
Standards and governance¶
| # | Body | Resource | Link |
|---|---|---|---|
| 71 | OWASP | Top 10 for LLM Applications | owasp.org |
| 72 | OWASP GenAI | LLM Top 10 (GenAI hub) | genai.owasp.org |
| 73 | OWASP | Top 10 (general application security) | owasp.org |
| 74 | NIST | AI Risk Management Framework | nist.gov |
| 75 | EU | AI Act | artificialintelligenceact.eu |
Git and GitHub¶
| # | Resource | Link |
|---|---|---|
| 76 | GitHub CLI manual | cli.github.com/manual |
| 77 | Connecting to GitHub with SSH | docs.github.com/.../ssh |
| 78 | GitHub Docs — Get started | docs.github.com/en/get-started |
| 79 | GitHub — Removing sensitive data | docs.github.com |
Product management¶
| # | Domain | Resource | Link |
|---|---|---|---|
| 80 | SVPG | Empowered product teams | svpg.com |
| 81 | SVPG | Product discovery | svpg.com |
| 82 | SVPG | Dual-Track Agile | svpg.com |
| 83 | SVPG | Continuous discovery | svpg.com |
| 84 | Intercom | RICE scoring | intercom.com |
| 85 | Product Talk | Opportunity solution trees | producttalk.org |
| 86 | Basecamp | Shape Up (overview) | basecamp.com/shapeup |
| 87 | HBR | Know your customers' jobs to be done | hbr.org |
| 88 | Wikipedia | Kano model | wikipedia.org |
| 89 | NN/g | UX roadmaps | nngroup.com |
| 90 | NN/g | Design thinking 101 | nngroup.com |
| 91 | NN/g | Personas vs. jobs-to-be-done | nngroup.com |
| 92 | Atlassian | Product roadmap guide | atlassian.com |
| 93 | ProductPlan | What is a product roadmap? | productplan.com |
| 94 | Amplitude | North Star metric | amplitude.com |
| 95 | Wikipedia | OKRs | wikipedia.org |
| 96 | Wikipedia | MoSCoW method | wikipedia.org |
| 97 | Jeff Patton | User story mapping | jpattonassociates.com |
| 98 | Wikipedia | New product development | wikipedia.org |
| 99 | Wikipedia | Phase-gate process | wikipedia.org |
| 100 | Lean Startup | Methodology / MVP loop | theleanstartup.com |
| 101 | Wikipedia | Minimum viable product | wikipedia.org |
| 102 | Industrial Logic | INVEST model (user stories) | industriallogic.com |
Source distribution¶
| Category | Count |
|---|---|
| Research papers | 26 |
| AI vendor documentation | 15 |
| Cursor and editor docs | 5 |
| Frameworks and tools | 7 |
| Established practitioners | 17 |
| Standards and governance | 5 |
| Git and GitHub | 4 |
| Product management | 23 |
| Total | 102 |