📚 References

Bibliography organized by theme. Each entry includes, when applicable:

• Title.
• Author / Organization.
• Type — paper, spec, docs, official technical blog, framework, benchmark, book.
• Why it is relevant — in one line.
• Book section — where the reference is used.

Editorial principle. Vendor documentation is included only when it is the best available technical source. Purely promotional material does not appear as a primary reference; when useful, it is placed in clearly identified "Further reading". Emerging topics have their maturity level declared explicitly, and the book does not claim consensus where there is none yet.

---

🗂️ Table of contents

• 📚 References
• 🗂️ Table of contents
• 📊 1. Traditional ML, MLOps and statistics
  • 📑 Papers and books
  • 📘 Official documentation
  • 📜 Technical blogs
• 🤖 2. LLM fundamentals, tokenization and fine-tuning
  • 📑 Papers
  • 📘 Official documentation and frameworks
  • 📜 Official technical blogs
• 🧬 3. Embeddings, Matryoshka and retrieval
  • 📑 Papers
  • 📘 Official documentation
  • 📜 Blogs / GraphRAG
• 🚀 4. Serving, throughput and inference optimization
  • 📑 Papers
  • 📘 Official documentation
• 🧩 5. Agentic AI, MCP and A2A
  • 📘 MCP - Model Context Protocol
  • 🤝 A2A - Agent2Agent
  • 📘 Frameworks and SDKs
  • 📑 Memory in agents
  • 🏗️ Architectural patterns
• 🛡️ 6. Security, identity and governance
  • 📘 Risk frameworks
  • 🧰 Policy engines (policy-as-code)
  • 🔐 Identity and authorization (OAuth/OIDC)
  • 🔓 Prompt injection and guardrails (research and practice)
• 🏗️ 7. AI supply chain
• 🌐 8. AI gateways
• 🔭 9. Observability
• 🔄 10. Workflows and infrastructure
• 💰 11. FinOps
• ✅ 12. Evaluation
• 🏋️ 13. Distributed training and scale (vocabulary)
• 🧰 14. Frameworks and ecosystem
• 📖 15. Books and cross-cutting reading
• 🚫 Note on promotional sources

---

📊 1. Traditional ML, MLOps and statistics

📑 Papers and books

• Mitchell et al. — Model Cards for Model Reporting (FAT* 2019). Original paper — https://arxiv.org/abs/1810.03993. Basis for Model Cards. Used in Ch. 1.7 and 1.11.
• Gebru et al. — Datasheets for Datasets (CACM 2021). Paper — https://arxiv.org/abs/1803.09010. Basis for Dataset Cards. Ch. 1.2, 1.7.
• Hardt, Price & Srebro — Equality of Opportunity in Supervised Learning (NIPS 2016). Paper — https://arxiv.org/abs/1610.02413. Basis for equalized odds and equality of opportunity. Ch. 1.11.
• Guo et al. — On Calibration of Modern Neural Networks (ICML 2017). Paper — https://arxiv.org/abs/1706.04599. Calibration and ECE. Ch. 1.3.
• Ribeiro, Singh & Guestrin — "Why Should I Trust You?" Explaining the Predictions of Any Classifier (KDD 2016). Paper — https://arxiv.org/abs/1602.04938. LIME. Ch. 1.11.
• Friedman — Greedy Function Approximation: A Gradient Boosting Machine (Annals of Statistics 2001). Paper — https://projecteuclid.org/journals/annals-of-statistics/volume-29/issue-5/Greedy-function-approximation-A-gradient-boosting-machine/10.1214/aos/1013203451.full. Origin of the Partial Dependence Plot. Ch. 1.11.
• Barocas, Hardt & Narayanan — Fairness and Machine Learning: Limitations and Opportunities (open book). https://fairmlbook.org/. Ch. 1.11.
• Chip Huyen — Designing Machine Learning Systems (O'Reilly). Book. Covers pipelines, monitoring and deployment. Ch. 1.1-1.10.
• Lakshmanan, Robinson & Munn — Machine Learning Design Patterns (O'Reilly). Book. Reusable patterns. Ch. 1.5-1.10.

📘 Official documentation

• scikit-learn — https://scikit-learn.org/stable/. Docs (framework).
• PyTorch — https://pytorch.org/docs/stable/index.html. Docs (framework).
• JAX — https://docs.jax.dev/. Docs (framework).
• MLflow — https://mlflow.org/docs/latest/index.html. Docs (experiment tracking + registry). Ch. 1.7.
• Kubeflow — https://www.kubeflow.org/docs/. Docs (orchestration).
• Feast — https://docs.feast.dev/. Docs (feature store).
• Feast — Point-in-time joins — https://docs.feast.dev/getting-started/concepts/point-in-time-joins. Ch. 1.5.
• Tecton — https://docs.tecton.ai/. Docs (commercial feature store).
• Evidently AI — https://docs.evidentlyai.com/. Docs (drift, monitoring). Ch. 1.2, 1.9.
• Great Expectations — https://docs.greatexpectations.io/. Docs (data quality). Ch. 1.2.
• Pandera — https://pandera.readthedocs.io/. Docs (validation). Ch. 1.2.
• Dagster — https://docs.dagster.io/. Docs (orchestration).
• Apache Airflow — https://airflow.apache.org/docs/apache-airflow/stable/. Docs (orchestration).
• SHAP — https://shap.readthedocs.io/. Docs (interpretability). Ch. 1.11.

📜 Technical blogs

• Evidently AI — What is concept drift in ML — https://www.evidentlyai.com/ml-in-production/concept-drift. Ch. 1.9.
• Google Developers — Classification: accuracy, precision, recall — https://developers.google.com/machine-learning/crash-course/classification/accuracy-precision-recall. Ch. 1.3.
• ICLR Blog 2025 — Understanding model calibration (ECE) — https://iclr-blogposts.github.io/2025/blog/calibration/. Ch. 1.3.
• Sebastian Raschka — LoRA vs full fine-tuning — https://sebastianraschka.com/faq/docs/lora-vs-full-finetuning.html. Ch. 2.2.
• Hugging Face — Tokenizers — https://huggingface.co/docs/tokenizers/en/index. Ch. 2.1.

---

🤖 2. LLM fundamentals, tokenization and fine-tuning

📑 Papers

• Vaswani et al. — Attention Is All You Need (NeurIPS 2017). Paper — https://arxiv.org/abs/1706.03762. The foundational Transformer. Ch. 2.1.
• Sennrich, Haddow & Birch — Neural Machine Translation of Rare Words with Subword Units (ACL 2016). Paper — https://aclanthology.org/P16-1162/. Origin of BPE. Ch. 2.1.
• Kudo & Richardson — SentencePiece: A simple and language independent subword tokenizer (EMNLP 2018 demo). Paper — https://arxiv.org/abs/1808.06226. Ch. 2.1.
• Hu et al. — LoRA: Low-Rank Adaptation of Large Language Models (ICLR 2022). Paper — https://arxiv.org/abs/2106.09685. Ch. 2.2.
• Dettmers et al. — QLoRA: Efficient Finetuning of Quantized LLMs (NeurIPS 2023). Paper — https://arxiv.org/abs/2305.14314. NF4, double quantization, paged optimizers. Ch. 2.2.
• Frantar et al. — GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers (ICLR 2023). Paper — https://arxiv.org/abs/2210.17323. Ch. 2.2.
• Lin et al. — AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration (MLSys 2024). Paper — https://arxiv.org/abs/2306.00978. Ch. 2.2.
• Xiao et al. — SmoothQuant (ICML 2023). Paper — https://arxiv.org/abs/2211.10438. Ch. 2.2.

📘 Official documentation and frameworks

• OpenAI API — https://developers.openai.com/api/docs. Docs.
• OpenAI — Function calling — https://developers.openai.com/api/docs/guides/function-calling. Ch. 2.4, 3.5.
• OpenAI — Structured outputs — https://developers.openai.com/api/docs/guides/structured-outputs. Ch. 0.2, 2.4.
• OpenAI — Prompt caching — https://developers.openai.com/api/docs/guides/prompt-caching. Ch. 2.3, 6.4.
• OpenAI — Latency optimization — https://developers.openai.com/api/docs/guides/latency-optimization. Ch. 6.3, 6.4.
• OpenAI — Supervised fine-tuning — https://developers.openai.com/api/docs/guides/supervised-fine-tuning. Ch. 2.2.
• OpenAI — Working with evals — https://developers.openai.com/api/docs/guides/evals. Ch. 2.11, 5.4.
• OpenAI — Evaluation best practices — https://developers.openai.com/api/docs/guides/evaluation-best-practices. Ch. 5.4.
• OpenAI — Evaluate agent workflows — https://developers.openai.com/api/docs/guides/agent-evals. Ch. 5.4.
• OpenAI — Graders — https://developers.openai.com/api/docs/guides/graders. Ch. 5.4.
• Anthropic Claude docs — https://docs.anthropic.com/. Docs.
• Anthropic — Tool use — https://docs.anthropic.com/en/docs/build-with-claude/tool-use. Ch. 2.4, 3.5.
• Anthropic — Prompt caching — https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching. Ch. 6.4.
• Google ADK — https://adk.dev/. Docs.
• Google Vertex AI — https://docs.cloud.google.com/vertex-ai/docs. Docs.
• Microsoft Foundry Agent Service — https://learn.microsoft.com/en-us/azure/foundry/agents/overview. Docs.
• Microsoft Agent Framework — https://learn.microsoft.com/en-us/agent-framework/overview/. Docs.
• Semantic Kernel — https://learn.microsoft.com/en-us/semantic-kernel/. Docs.
• Amazon Bedrock — https://docs.aws.amazon.com/bedrock/latest/userguide/. Docs.
• bitsandbytes — https://huggingface.co/docs/bitsandbytes/main/en/index. Docs (8-bit/4-bit in Hugging Face). Ch. 2.2.
• llama.cpp and GGUF — https://github.com/ggml-org/llama.cpp. Project (local inference + quantization format). Ch. 2.2.
• MLC LLM — https://llm.mlc.ai/. Docs (cross-hardware inference).

📜 Official technical blogs

• Anthropic — Effective context engineering for AI agents — https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents. Ch. 2.3, 3.3.
• Anthropic — Demystifying evals for AI agents — https://www.anthropic.com/engineering/demystifying-evals-for-ai-agents. Ch. 5.4.
• Anthropic — Effective harnesses for long-running agents — https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents. Ch. 3.3.
• Anthropic — Writing effective tools for agents — https://www.anthropic.com/engineering/writing-tools-for-agents. Ch. 3.5.
• Anthropic — Code execution with MCP — https://www.anthropic.com/engineering/code-execution-with-mcp. Ch. 4.10.
• Anthropic — Measuring AI agent autonomy in practice — https://www.anthropic.com/news/measuring-agent-autonomy. Ch. 3.2.
• OpenAI Cookbook — Prompt Caching 201 — https://developers.openai.com/cookbook/examples/prompt_caching_201. Ch. 2.3.
• BentoML — Prefill–decode disaggregation — https://bentoml.com/llm/inference-optimization/prefill-decode-disaggregation. Ch. 2.1, 6.3.

---

🧬 3. Embeddings, Matryoshka and retrieval

📑 Papers

• Kusupati et al. — Matryoshka Representation Learning (NeurIPS 2022). Paper — https://arxiv.org/abs/2205.13147. Theoretical basis of Matryoshka. Ch. 2.8.
• Malkov & Yashunin — Efficient and robust approximate nearest neighbor search using HNSW (TPAMI 2018). Paper — https://arxiv.org/abs/1603.09320. Ch. 2.7, 2.8.
• Lewis et al. — Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (NeurIPS 2020). Paper — https://arxiv.org/abs/2005.11401. Ch. 2.6.
• Edge et al. (Microsoft Research) — From Local to Global: A Graph RAG Approach to Query-Focused Summarization. Paper — https://arxiv.org/abs/2404.16130. Ch. 2.9.

📘 Official documentation

• OpenAI — Embeddings (includes the dimensions parameter) — https://platform.openai.com/docs/guides/embeddings. Ch. 2.8.
• Cohere — Embed v3 — https://docs.cohere.com/docs/cohere-embed. Matryoshka support. Ch. 2.8.
• Nomic — Nomic Embed Text — https://docs.nomic.ai/atlas/embeddings-and-retrieval/text-embedding. Open-weight Matryoshka model. Ch. 2.8.
• Sentence Transformers — Matryoshka embeddings — https://www.sbert.net/examples/training/matryoshka/README.html. Ch. 2.8.
• Faiss — https://faiss.ai/. ANN library. Ch. 2.7, 2.8.
• Cormack, Clarke & Buettcher — Reciprocal Rank Fusion outperforms Condorcet and individual Rank Learning Methods (SIGIR 2009). Paper — https://plg.uwaterloo.ca/~gvcormac/cormacksigir09-rrf.pdf. RRF in hybrid search. Ch. 2.7.
• Robertson & Zaragoza — BM25 review (classic reference cited in the book). Ch. 2.7.
• Pinecone — Hybrid search — https://docs.pinecone.io/guides/search/hybrid-search. Ch. 2.7.
• Weaviate — Hybrid search — https://docs.weaviate.io/weaviate/search/hybrid. Ch. 2.7.
• Qdrant — Hybrid queries — https://qdrant.tech/documentation/search/hybrid-queries/. Ch. 2.7.
• OpenSearch — Hybrid search — https://docs.opensearch.org/latest/vector-search/ai-search/hybrid-search/index/. Ch. 2.7.
• Elasticsearch — RAG — https://www.elastic.co/docs/solutions/search/rag.
• Milvus — https://milvus.io/docs.
• pgvector — https://github.com/pgvector/pgvector.
• Amazon Bedrock — Reranking — https://docs.aws.amazon.com/bedrock/latest/userguide/rerank.html. Ch. 2.7.
• Cohere — Rerank — https://docs.cohere.com/docs/rerank-overview. Ch. 2.7.

📜 Blogs / GraphRAG

• Microsoft GraphRAG — https://microsoft.github.io/graphrag/. Ch. 2.9.
• Neo4j GraphRAG (Python) — https://neo4j.com/docs/neo4j-graphrag-python/current/. Ch. 2.9.
• Google Cloud — GraphRAG with Spanner Graph — https://docs.cloud.google.com/architecture/gen-ai-graphrag-spanner. Ch. 2.9.
• Toloka — RAG evaluation — https://toloka.ai/blog/rag-evaluation-a-technical-guide-to-measuring-retrieval-augmented-generation/. Ch. 2.6.
• Google Cloud — Retrieval-Augmented Generation — https://cloud.google.com/use-cases/retrieval-augmented-generation. Ch. 2.6.
• Ragas — Metrics — https://docs.ragas.io/en/stable/concepts/metrics/available_metrics/. Ch. 2.11, 5.4.
• TruLens — RAG triad of metrics — https://www.trulens.org/getting_started/core_concepts/rag_triad/. Ch. 2.6, 2.11 (further reading).

---

🚀 4. Serving, throughput and inference optimization

📑 Papers

• Kwon et al. — Efficient Memory Management for Large Language Model Serving with PagedAttention (SOSP 2023). Paper — https://arxiv.org/abs/2309.06180. Basis of vLLM. Ch. 6.3.
• Leviathan, Kalman & Matias — Fast Inference from Transformers via Speculative Decoding (ICML 2023). Paper — https://arxiv.org/abs/2211.17192. Ch. 6.3.
• Pope et al. — Efficiently Scaling Transformer Inference (MLSys 2023). Paper — https://arxiv.org/abs/2211.05102. Ch. 6.3.

📘 Official documentation

• vLLM — https://docs.vllm.ai/en/latest/. Docs (PagedAttention, continuous batching, prefix caching). Ch. 6.3.
• vLLM — Architecture overview — https://docs.vllm.ai/en/latest/design/arch_overview.html. Ch. 6.3.
• NVIDIA TensorRT-LLM — https://nvidia.github.io/TensorRT-LLM/. Docs (in-flight batching, paged KV cache). Ch. 6.3.
• NVIDIA Triton Inference Server — https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/. Docs. Ch. 1.8.
• Hugging Face TGI — https://huggingface.co/docs/text-generation-inference. Docs. Ch. 6.3.
• Ray Serve — https://docs.ray.io/en/latest/serve/index.html. Docs. Ch. 1.8.
• TensorFlow Serving — https://www.tensorflow.org/tfx/guide/serving. Docs. Ch. 1.8.
• TorchServe — https://pytorch.org/serve/. Docs. Ch. 1.8.

---

🧩 5. Agentic AI, MCP and A2A

📘 MCP - Model Context Protocol

• MCP — Architecture overview — https://modelcontextprotocol.io/docs/learn/architecture. Spec. Ch. 3.5.
• MCP — Authorization (draft) — https://modelcontextprotocol.io/specification/draft/basic/authorization. Spec. Ch. 4.8.
• MCP — Tools spec — https://modelcontextprotocol.io/specification/2025-11-25/server/tools. Spec. Ch. 3.5.
• MCP — Security best practices — https://modelcontextprotocol.io/docs/tutorials/security/security_best_practices. Ch. 3.5, 4.

🤝 A2A - Agent2Agent

• A2A Protocol — official site — https://a2a-protocol.org/latest/. Emerging spec. Ch. 3.5.
• A2A Protocol — Google announcement (historical context) — https://developers.googleblog.com/en/a2a-a-new-era-of-agent-interoperability/. Context. Ch. 3.5.
• A2A — Agent Card schema (in the spec above). Ch. 3.5.

Maturity: emerging topic (spec evolving throughout 2024–2026). Treat it as a consolidating technology; no closed consensus.

📘 Frameworks and SDKs

• LangGraph — https://docs.langchain.com/oss/python/langgraph/overview.
• LangGraph — Persistence — https://docs.langchain.com/oss/python/langgraph/persistence. Ch. 3.6.
• LangChain — Context engineering — https://docs.langchain.com/oss/python/langchain/context-engineering.
• LangChain — Human-in-the-loop — https://docs.langchain.com/oss/python/langchain/human-in-the-loop.
• LangSmith — Observability — https://www.langchain.com/langsmith/observability.
• LlamaIndex — https://developers.llamaindex.ai/python/framework/.
• AutoGen — https://microsoft.github.io/autogen/dev/.
• OpenAI Agents SDK — Tracing — https://openai.github.io/openai-agents-python/tracing/.
• OpenAI Agents SDK — Guardrails — https://openai.github.io/openai-agents-python/guardrails/.
• OpenAI Agents SDK — Human-in-the-loop — https://openai.github.io/openai-agents-python/human_in_the_loop/.
• Google Vertex AI Agent Engine — Memory Bank — https://docs.cloud.google.com/agent-builder/agent-engine/use/adk.
• Amazon Bedrock Agents — https://docs.aws.amazon.com/bedrock/latest/userguide/agents.html.
• Amazon Bedrock Knowledge Bases — https://docs.aws.amazon.com/bedrock/latest/userguide/knowledge-base.html.

📑 Memory in agents

• Packer et al. — MemGPT: Towards LLMs as Operating Systems. Paper — https://arxiv.org/abs/2310.08560. Ch. 3.6.
• Yao et al. — ReAct: Synergizing Reasoning and Acting in Language Models. Paper — https://arxiv.org/abs/2210.03629.
• Schick et al. — Toolformer: Language Models Can Teach Themselves to Use Tools. Paper — https://arxiv.org/abs/2302.04761.

🏗️ Architectural patterns

• Google Cloud — Choose a design pattern for your agentic AI system — https://docs.cloud.google.com/architecture/choose-design-pattern-agentic-ai-system. Ch. 3.4.

---

🛡️ 6. Security, identity and governance

📘 Risk frameworks

• OWASP — Top 10 for LLM Applications — https://owasp.org/www-project-top-10-for-large-language-model-applications/. Framework. Ch. 4.
• OWASP — Top 10 for LLM Applications 2025 PDF — https://owasp.org/www-project-top-10-for-large-language-model-applications/assets/PDF/OWASP-Top-10-for-LLMs-v2025.pdf.
• NIST — AI Risk Management Framework 1.0 — https://nvlpubs.nist.gov/nistpubs/ai/nist.ai.100-1.pdf. Ch. 0.3, 4.
• NIST — Generative AI Profile (AI RMF) — https://www.nist.gov/itl/ai-risk-management-framework. Ch. 4.2.
• NIST — alternative publication of the GenAI Profile — https://www.nist.gov/publications/artificial-intelligence-risk-management-framework-generative-artificial-intelligence.
• MITRE ATLAS — https://atlas.mitre.org/. Threat catalog. Ch. 4.2.
• Microsoft — STRIDE Threat Model (tool and vocabulary) — https://learn.microsoft.com/en-us/azure/security/develop/threat-modeling-tool-threats. Ch. 4.2.

🧰 Policy engines (policy-as-code)

• Open Policy Agent — Policy Language (Rego) — https://www.openpolicyagent.org/docs/policy-language. Ch. 4.7.
• Open Policy Agent — Policy Testing — https://www.openpolicyagent.org/docs/policy-testing. Ch. 4.7.
• AWS Cedar — Policy Language Reference — https://docs.cedarpolicy.com/policies/syntax-policy.html. Ch. 4.7.
• AuthZed SpiceDB — Concepts — https://authzed.com/docs/spicedb/concepts/zedtokens. Ch. 4.7.
• Google Zanzibar (paper) — https://research.google/pubs/pub48190/. Theoretical basis of SpiceDB.

🔐 Identity and authorization (OAuth/OIDC)

• IETF RFC 6749 — OAuth 2.0 Authorization Framework — https://datatracker.ietf.org/doc/html/rfc6749. Ch. 4.8.
• IETF RFC 8693 — OAuth 2.0 Token Exchange — https://datatracker.ietf.org/doc/html/rfc8693. Ch. 4.8.
• IETF RFC 8628 — OAuth 2.0 Device Authorization Grant — https://datatracker.ietf.org/doc/html/rfc8628. Ch. 4.8.
• IETF RFC 7636 — PKCE — https://datatracker.ietf.org/doc/html/rfc7636. Ch. 4.8.
• IETF RFC 9700 — OAuth 2.0 Security Best Current Practice — https://datatracker.ietf.org/doc/html/rfc9700. Ch. 4.8.
• OpenID Connect Core 1.0 — https://openid.net/specs/openid-connect-core-1_0.html. Ch. 4.8.
• Kubernetes — ServiceAccount Tokens — https://kubernetes.io/docs/tasks/configure-pod-container/configure-service-account/.
• AWS — IAM Roles for Service Accounts — https://docs.aws.amazon.com/eks/latest/userguide/iam-roles-for-service-accounts.html.
• GCP — Workload Identity Federation — https://cloud.google.com/iam/docs/workload-identity-federation.
• Azure — Managed Identities — https://learn.microsoft.com/en-us/azure/active-directory/managed-identities-azure-resources/overview.

🔓 Prompt injection and guardrails (research and practice)

• Greshake et al. — Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection (2023). Paper — https://arxiv.org/abs/2302.12173. Ch. 4.3.
• Anthropic — Reduce prompt injection — https://docs.anthropic.com/en/docs/test-and-evaluate/strengthen-guardrails/reduce-prompt-injection. Ch. 4.3.
• Simon Willison — Prompt injection series — https://simonwillison.net/series/prompt-injection/. Ch. 4.3 (vocabulary and cases).

---

🏗️ 7. AI supply chain

• SLSA — Supply-chain Levels for Software Artifacts, spec v1.2 — https://slsa.dev/spec/v1.2/. Ch. 4.9.
• SLSA — overview — https://slsa.dev/.
• SPDX (Linux Foundation) — https://spdx.dev/. Ch. 4.9.
• SPDX — Specification — https://spdx.github.io/spdx-spec/.
• CycloneDX (OWASP) — https://cyclonedx.org/. Ch. 4.9.
• CycloneDX — ML-BOM — https://cyclonedx.org/capabilities/mlbom/. Models, datasets and hyperparameters. Ch. 4.9.
• OpenSSF — https://openssf.org/. Ch. 4.9.
• OpenSSF Scorecard — https://github.com/ossf/scorecard. Ch. 4.9.
• Sigstore — cosign — https://docs.sigstore.dev/cosign/signing/overview/.
• in-toto — https://in-toto.io/.
• NTIA — SBOM minimum elements — https://www.ntia.gov/SBOM.
• CISA — SBOM resources — https://www.cisa.gov/sbom.
• Hugging Face — Model Cards — https://huggingface.co/docs/hub/model-cards. Ch. 4.9, 1.7.

---

🌐 8. AI gateways

• LiteLLM — LiteLLM AI Gateway (LLM Proxy) — https://docs.litellm.ai/docs/simple_proxy. Open-source. Ch. 2.5.
• Kong — AI Gateway / AI Proxy plugin — https://docs.konghq.com/hub/kong-inc/ai-proxy/. Plugins over Kong. Ch. 2.5.
• Portkey — AI Gateway — https://portkey.ai/docs/product/ai-gateway. SaaS + self-hosted option. Ch. 2.5.
• Cloudflare — AI Gateway — https://developers.cloudflare.com/ai-gateway/. Ch. 2.5.

Editorial stance: neutral comparison. Evaluate the license, supported providers, deployment model and fit with your stack before adopting.

---

🔭 9. Observability

• OpenTelemetry — GenAI semantic conventions — https://opentelemetry.io/docs/specs/semconv/gen-ai/. Ch. 2.12, 5.2, 5.3.
• OpenTelemetry — GenAI spans — https://opentelemetry.io/docs/specs/semconv/gen-ai/gen-ai-spans/.
• OpenTelemetry — GenAI agent spans — https://opentelemetry.io/docs/specs/semconv/gen-ai/gen-ai-agent-spans/.
• Langfuse — https://langfuse.com/docs. Open-source observability for LLM/agents (further reading).
• Phoenix / Arize — https://docs.arize.com/phoenix. Open-source (further reading).
• Helicone — https://docs.helicone.ai/. Observability for LLMs (further reading).
• LangSmith — https://www.langchain.com/langsmith/observability. SaaS.
• Grafana Tempo — https://grafana.com/docs/tempo/latest/. Trace backend (with OTel). Ch. 5.2.
• Jaeger — https://www.jaegertracing.io/docs/. Ch. 5.2.

---

🔄 10. Workflows and infrastructure

• Temporal — https://docs.temporal.io/.
• Temporal — Workflow Execution — https://docs.temporal.io/workflow-execution.
• AWS Step Functions — https://docs.aws.amazon.com/step-functions/latest/dg/welcome.html.
• AWS Step Functions — Error handling — https://docs.aws.amazon.com/step-functions/latest/dg/concepts-error-handling.html.
• Azure Durable Functions — https://learn.microsoft.com/en-us/azure/azure-functions/durable-functions/durable-functions-overview.
• Apache Airflow — DAGs — https://airflow.apache.org/docs/apache-airflow/stable/core-concepts/dags.html.
• Dagster — https://docs.dagster.io/.

---

💰 11. FinOps

• FinOps Foundation — FinOps Framework — https://www.finops.org/framework/. Ch. 6.5.
• FinOps Foundation — FinOps for AI — https://www.finops.org/wg/finops-for-ai/. Working group, recent material. Ch. 6.5.
• OpenAI — Latency optimization — https://developers.openai.com/api/docs/guides/latency-optimization.
• Anthropic — Prompt caching — https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching.

---

✅ 12. Evaluation

• Anthropic — Demystifying evals — https://www.anthropic.com/engineering/demystifying-evals-for-ai-agents.
• OpenAI — Working with evals — https://developers.openai.com/api/docs/guides/evals.
• OpenAI — Evaluation best practices — https://developers.openai.com/api/docs/guides/evaluation-best-practices.
• OpenAI — Evaluate agent workflows — https://developers.openai.com/api/docs/guides/agent-evals.
• OpenAI — Graders — https://developers.openai.com/api/docs/guides/graders.
• Ragas — Metrics — https://docs.ragas.io/en/stable/concepts/metrics/available_metrics/.
• Ragas — Faithfulness — https://docs.ragas.io/en/stable/concepts/metrics/available_metrics/faithfulness/.
• Ragas — Context Precision — https://docs.ragas.io/en/stable/concepts/metrics/available_metrics/context_precision/.
• Zheng et al. — Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena (2023). Paper — https://arxiv.org/abs/2306.05685. Ch. 2.11, 5.4.
• Liu et al. — G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment (2023). Paper — https://arxiv.org/abs/2211.09110. Ch. 2.11.

---

🏋️ 13. Distributed training and scale (vocabulary)

Minimum scope of Ch. 7.7 — it does not replace GPU cluster manuals.

• Shoeybi et al. — Megatron-LM (tensor parallelism). Paper — https://arxiv.org/abs/1909.08053. Ch. 7.7.
• Rajbhandari et al. — ZeRO: Memory Optimizations Toward Training Trillion Parameter Models. Paper — https://arxiv.org/abs/1910.02054. Ch. 7.7.
• PyTorch — FSDP overview — https://pytorch.org/docs/stable/fsdp.html. Ch. 7.7.
• Microsoft — DeepSpeed — https://www.deepspeed.ai/. Ch. 7.7.
• Hugging Face — Accelerate — https://huggingface.co/docs/accelerate/index. Ch. 7.7.

---

🧰 14. Frameworks and ecosystem

• LangChain — https://docs.langchain.com/.
• LangGraph — https://docs.langchain.com/oss/python/langgraph/overview.
• LangSmith — https://www.langchain.com/langsmith/observability.
• LlamaIndex — https://developers.llamaindex.ai/python/framework/.
• AutoGen — https://microsoft.github.io/autogen/dev/.
• Semantic Kernel — https://learn.microsoft.com/en-us/semantic-kernel/.
• Microsoft Agent Framework — https://learn.microsoft.com/en-us/agent-framework/overview/.
• Google ADK — https://adk.dev/.
• Pinecone — https://docs.pinecone.io/.
• Weaviate — https://docs.weaviate.io/weaviate.
• Milvus — https://milvus.io/docs.
• Qdrant — https://qdrant.tech/documentation/.
• Elasticsearch — https://www.elastic.co/docs/solutions/search/rag.
• OpenSearch — https://docs.opensearch.org/latest/vector-search/.
• pgvector — https://github.com/pgvector/pgvector.

---

📖 15. Books and cross-cutting reading

• Chip Huyen — Designing Machine Learning Systems (O'Reilly). Book.
• Chip Huyen — AI Engineering: Building Applications with Foundation Models (O'Reilly, 2024). Book.
• Lakshmanan, Robinson & Munn — Machine Learning Design Patterns (O'Reilly). Book.
• Engineering blogs from OpenAI, Anthropic, Google, Meta, Netflix, Airbnb and Uber. Varied material on MLOps, LLMOps and Agentic AI.

---

🚫 Note on promotional sources

When a reference is primarily promotional of a product, it should not be used as the only basis for a technical claim. The criterion:

• ✅ Official documentation with verifiable technical details.
• ✅ Peer-reviewed papers or serious preprints.
• ✅ Open specifications (RFCs, MCP, A2A, OpenTelemetry, SLSA, SPDX, CycloneDX).
• ⚠️ A vendor blog post with technical substance — cite with caution and as complementary.
• ❌ A pure marketing post — do not cite.

Emerging topics (A2A, the most recent MCP Authorization, FinOps for AI) have their maturity declared explicitly and should be revisited periodically.