Sefism is free for learners. We are here to help you grow, one step at a time.Join for free
Sefism.

AI cheat sheets

AI cheat sheets on Sefism, written by Tauseef Fayyaz: every concept in plain words, why it is used and the pitfall that catches people out.

  • 76 sheets
  • 5120 concepts

Free to learn. Credits keep it fair.

Reading is free. Adding a roadmap, keeping a cheat sheet or asking Tauseef a question uses credits, which only make sure the platform goes to people who are actually learning.

  • 15creditswhen you join
  • 1stroadmapfree to add
  • Morecreditson request, as you learn

Foundations

1

Start here if you are new or your basics are patchy.

  • Cheat sheet · Foundations

    Coding with AI tools cheat sheet

    Claude Code, Cursor, Copilot, used well.

    Chapters

    1. 1What AI coding tools are good and bad at
    2. 2Setup and project context
    3. 3Prompting for code

    + 7 more

    • 10 chapters
    • 77 concepts
    Free

Build products

2

Ship real apps for the web and phones.

  • Cheat sheet · Build products

    Prompt Engineering cheat sheet

    Prompt anatomy, few-shot examples, chain of thought, structured output, long context, prompts for code and study, and testing prompts.

    Chapters

    1. 1Anatomy of a prompt
    2. 2Zero-shot and few-shot prompting
    3. Chain of thought and reasoning

    + 5 more

    • 8 chapters
    • 55 concepts
    Opens with credits

Specialise

15

Go deep in one area of engineering.

  • Cheat sheet · Specialise

    AI engineering cheat sheet

    Build products on LLMs and generative AI.

    Chapters

    1. 1How LLMs work: tokens and context
    2. 2Prompting and model APIs
    3. RAG: embeddings, chunking and retrieval

    + 6 more

    • 9 chapters
    • 70 concepts
    Opens with credits

  • Cheat sheet · Specialise

    Machine learning cheat sheet

    Data, models, deep learning.

    Chapters

    1. 1Python for data
    2. 2The maths you need
    3. Data cleaning and feature engineering

    + 5 more

    • 8 chapters
    • 69 concepts
    Opens with credits

  • Cheat sheet · Specialise

    AI agents and MCP cheat sheet

    Tool calling, MCP servers, evals.

    Chapters

    1. 1How agents work
    2. 2Tool calling from scratch
    3. Structured output and validation

    + 7 more

    • 10 chapters
    • 74 concepts
    Opens with credits

  • Cheat sheet · Specialise

    MLOps and LLMOps cheat sheet

    Ship, serve and monitor models.

    Chapters

    1. 1From notebook to package
    2. 2Data and model versioning
    3. Experiment tracking and the registry

    + 7 more

    • 10 chapters
    • 70 concepts
    Opens with credits

  • Cheat sheet · Specialise

    AI security cheat sheet

    Secure LLM apps and agents, test models safely.

    Chapters

    1. 1Security foundations for AI work
    2. 2How LLM apps and agents break
    3. Risk maps: OWASP, ATLAS, NIST, SAIF

    + 6 more

    • 9 chapters
    • 78 concepts
    Opens with credits

  • Cheat sheet · Specialise

    AI governance cheat sheet

    Inventory, oversight, EU AI Act, ISO 42001.

    Chapters

    1. 1Regulations and frameworks
    2. 2AI inventory and ownership
    3. Data foundation

    + 4 more

    • 7 chapters
    • 63 concepts
    Opens with credits

  • Cheat sheet · Specialise

    LLM APIs cheat sheet

    Building on OpenAI, Anthropic and Gemini APIs: prompts, streaming, structured output, tools, RAG, caching, cost, evals and safety.

    Chapters

    1. 1How LLM APIs work
    2. 2Prompts, roles and sampling
    3. Streaming, structured output and images

    + 5 more

    • 8 chapters
    • 56 concepts
    Opens with credits

  • Cheat sheet · Specialise

    Model Context Protocol cheat sheet

    How MCP connects AI applications to tools and data: hosts and servers, messages, transports, auth, building servers and staying safe.

    Chapters

    1. 1What MCP is
    2. 2Messages and lifecycle
    3. Transports

    + 6 more

    • 9 chapters
    • 62 concepts
    Opens with credits

  • Cheat sheet · Specialise

    Vector databases cheat sheet

    Embeddings, similarity metrics, ANN indexes, filtering, hybrid search, reranking, RAG chunking, pgvector, dedicated stores and evaluation.

    Chapters

    1. 1Embeddings and similarity
    2. 2Nearest neighbour search
    3. Index types: HNSW, IVF and PQ

    + 6 more

    • 9 chapters
    • 64 concepts
    Opens with credits

  • Cheat sheet · Specialise

    LangChain and LlamaIndex cheat sheet

    RAG pipelines, retrieval quality, agents, tools, memory and evaluation in Python, with LangChain and LangGraph or LlamaIndex.

    Chapters

    1. 1RAG and agents: the big picture
    2. 2Loading and chunking
    3. Embeddings and vector stores

    + 3 more

    • 8 chapters
    • 58 concepts
    Opens with credits

  • Cheat sheet · Specialise

    Hugging Face cheat sheet

    The Hub, transformers, tokenisers, datasets, fine-tuning, LoRA, quantisation, inference and embeddings with the Hugging Face libraries.

    Chapters

    1. 1The Hub
    2. 2Running models with transformers
    3. Tokenisers

    + 5 more

    • 8 chapters
    • 51 concepts
    Opens with credits

  • Cheat sheet · Specialise

    Running LLMs locally cheat sheet

    Ollama commands, Modelfiles, quantisation, memory and hardware, the local API, clients, tools, embeddings and safe serving.

    Chapters

    1. 1Getting started with Ollama
    2. 2Models, tags and sizes
    3. Quantisation and memory

    + 6 more

    • 9 chapters
    • 69 concepts
    Opens with credits

  • Cheat sheet · Specialise

    RAG cheat sheet

    Retrieval augmented generation end to end: chunking, embeddings, hybrid retrieval, reranking, grounded prompts, evaluation and failure modes.

    Chapters

    1. 1RAG basics
    2. 2Loading and chunking
    3. Embeddings and the index

    + 5 more

    • 8 chapters
    • 54 concepts
    Opens with credits

  • Cheat sheet · Specialise

    GenAI app architecture cheat sheet

    How a production GenAI app fits together: request flow, layers, RAG, agent loop, memory, caching, guards, evals, tracing, folder layout and launch checklist.

    Chapters

    1. 1The request flow
    2. 2Frontend and backend layers
    3. The RAG pipeline

    + 7 more

    • 10 chapters
    • 58 concepts
    Opens with credits

  • Cheat sheet · Specialise

    AI evals cheat sheet

    Evals for LLM apps and agents: golden datasets, metrics, LLM-as-judge and its biases, RAG and agent metrics, offline and online evals, CI, human review, tools.

    Chapters

    1. 1What evals are
    2. 2Golden datasets
    3. Metrics by task type

    + 7 more

    • 10 chapters
    • 67 concepts
    Opens with credits

Career

2

Get hired, get seen and grow.

Earn independently

2

Freelance, work remotely or sell what you build.

Browse the cheat sheets by topic

Each of these is its own page: the foundations shelf, the career shelf, the sheets that are open end to end. The filters above do the same thing without a page load.

Work with me

Stuck on something specific?

Writing only gets you so far. If you want an answer to your situation rather than the general case, book a session and we will work through it together. Sessions are free for approved Sefism members, and a few slots open each week.

  • 1:1 Mentorship
  • Fresh Graduate Mentorship
  • Career Guidance
Book a free sessionSee all services

Brand deals, promos and partnerships: tauseeffayyaz@gmail.com

Follow along

New writing, resources and project ideas land here first.