AI Engineering Brain

Central hub for the AI Engineering brain — every major category linked from one place. Start here to navigate foundation models, agents, RAG, fine-tuning, evals, prompting, security, and infrastructure.

Updated Invalid Date·

Central hub for all AI engineering knowledge. Every page in the AE brain connects here.


Foundation Models

llms/claude · llms/transformer-architecture · llms/model-families · llms/tokenisation · llms/hallucination · llms/inference-time-scaling · llms/small-language-models

Safety and Alignment

safety/alignment · safety/constitutional-ai · safety/mechanistic-interpretability

Agents and Orchestration

agents/langchain · agents/langgraph · agents/langgraph-cloud · agents/practical-agent-design · agents/crewai · agents/autogen · agents/react-pattern · agents/multi-agent-patterns · agents/memory · agents/agent-memory-systems · agents/langmem · agents/openai-agents-sdk · agents/pydantic-ai · agents/mastra · agents/computer-use

RAG and Retrieval

rag/pipeline · rag/chunking · rag/embeddings · rag/hybrid-retrieval · rag/reranking · rag/query-expansion · rag/graphrag

Prompting and Context

prompting/techniques · prompting/dspy · prompting/context-engineering · prompting/structured-outputs

Evaluation

evals/methodology · evals/llm-as-judge · evals/benchmarks · evals/openai-evals · evals/bfcl

Fine-Tuning

fine-tuning/decision-framework · fine-tuning/lora-qlora · fine-tuning/dpo-grpo · fine-tuning/frameworks

Math Foundations

math/linear-algebra · math/transformer-math · math/optimisation · math/probability

Multimodal

multimodal/vision · multimodal/audio

APIs and Protocols

apis/anthropic-api · apis/openai-api · apis/google-ai · protocols/mcp · protocols/mcp-http-transport · protocols/a2a · protocols/tool-design

AI Tools

ai-tools/claude-code · ai-tools/cursor-copilot · ai-tools/tavily · ai-tools/openai-codex

Observability

observability/platforms · observability/helicone · observability/tracing · observability/llmops

Security

security/owasp-llm-top10 · security/prompt-injection · security/mcp-cves · security/red-teaming · security/guardrails · security/oauth-boundary-testing · security/llm-red-teaming-tools

Infrastructure

infra/vector-stores · infra/inference-serving · infra/huggingface · infra/gpu-hardware · infra/flash-attention · infra/deepspeed-zero · infra/experiment-tracking

Data

data/synthetic-data · data/distilabel · data/rlhf-datasets · data/pipelines

Landscape and Research

landscape/ai-labs · landscape/model-timeline · landscape/open-source-models · landscape/regulation · landscape/enterprise-ai-adoption · landscape/ai-use-case-identification · papers/attention-is-all-you-need · papers/key-papers

Synthesis

synthesis/rag-vs-finetuning · synthesis/llm-decision-guide · synthesis/architecture-patterns · synthesis/cost-optimisation · synthesis/getting-started · synthesis/learning-path · synthesis/software-engineer-to-ai-engineer · synthesis/data-as-system · synthesis/technical-communication

Connections

  • para/resources — parent node for all AE brain content
  • cs-fundamentals/se-hub — SE fundamentals hub; software engineering underpins agent and pipeline design
  • cloud/cloud-hub — cloud infrastructure hub; AI inference and training workloads run on cloud
  • landscape/aws-ai-practitioner — AWS AI certification content that maps AWS services to concepts in this hub

Open Questions

  • Which AE brain categories have the thinnest page coverage and most need new entries?
  • Are there emerging areas (e.g. world models, video generation, AI hardware) absent from this hub that belong here?
  • How should the hub handle topics that span both AE and SE (e.g. distributed training, MLOps pipelines)?