Skip to content
AI-grafen
Sign in
☰ Menu

The goal F AI engineering

Build an agent you can trust

Architecture, planning, observability, safety and evaluation — and the coding agent that gets objective feedback from tests.

Knowledge nodes
77
From zero
about 64 h
Labs
6
See what you already know — no account

The diagnostic removes what you already know, so your path is usually much shorter.

What you can do afterwards

Labs along the way

You write the code. Tests you cannot see decide whether it holds up.

Lab: an agent loop with tools, a budget and a traceEa sandbox · about 60 minLab: a neural network in pure NumPy — forward, backprop, gradient checkDa sandbox · about 75 minLab: dot product, norm and cosine similarityDin the browser · about 40 minLab: gradient descent from scratchDin the browser · about 50 minLab: matrix multiplication and one layer of a neural networkDin the browser · about 45 minLab: scaled dot-product attention with a causal maskDa sandbox · about 60 min

The whole path

Everything the goal builds on, grouped by level and in the order it builds on itself. Show on the map

AExplorer2 knowledge nodes
  1. Patterns and categories
  2. Sequences and precise instructions
BInvestigator9 knowledge nodes
  1. Data in everyday life
  2. Algorithmic thinking
  3. Rule-based systems and machine learning
  4. Source criticism and responsibility in AI use
  5. Training data, features and labels
  6. Classification: how a model sorts information
  7. Generative AI: how it creates content
  8. Language models and probabilities
  9. AI's invented answers
CBuilder13 knowledge nodes
  1. Functions and coordinate systems
  2. Programming logic — variables, conditions, loops
  3. Python — the basics
  4. Python — lists, loops and dictionaries
  5. Python — strings and text processing
  6. Python — files, CSV and JSON
  7. Statistics — mean, median and spread
  8. Probability — the basics
  9. Linear regression: fitting a straight line to data
  10. Neural networks — the intuition
  11. Prompting — steering a language model
  12. Responsible use of AI
  13. AI that uses tools: the calculator
DAI developer23 knowledge nodes
  1. Derivatives and optimisation
  2. Python — functions, scope and exceptions
  3. Python — classes and objects
  4. APIs and HTTP
  5. Loss functions
  6. Testing with pytest
  7. Tokenisation
  8. Gradient descent
  9. The context window, system prompts and few-shot
  10. Build a simple agent with one tool
  11. Vectors
  12. Matrices and matrix multiplication
  13. Linear regression with several features
  14. Neural networks — the forward pass with matrices
  15. Backpropagation
  16. Embeddings — words as vectors
  17. Attention
  18. Overfitting and generalisation
  19. PyTorch — tensors and autograd
  20. Retrieval — finding the right text
  21. Training, validation and test
  22. Train a neural network in PyTorch
  23. Transformers — the architecture
EUniversity20 knowledge nodes
  1. Asynchronous programming
  2. Building an API with FastAPI
  3. Structured output and schemas
  4. Multi-head attention in detail
  5. The KV cache
  6. Latency, throughput and batching in inference
  7. Cost modelling for LLM systems
  8. Language models — training and generation
  9. Model evaluation
  10. RAG — retrieval-augmented generation
  11. Language models for code
  12. Tool use
  13. Agents — plan, act, observe
  14. Budget, stopping conditions and cost control
  15. Working memory: context, summary, window
  16. The ReAct loop: think, act, observe
  17. Tool schemas, validation and error handling
  18. Scientific method in AI
  19. Reproducibility
  20. Experiment tracking
FAI engineering10 knowledge nodes
  1. Evals for language models and agents
  2. Agent architectures
  3. AI safety and red teaming
  4. Agent security: authorisations, the sandbox, confirmation
  5. Multi-agent systems
  6. Evaluating agents
  7. Code agents
  8. Planning and breaking a goal into subgoals
  9. MCP and tool protocols
  10. Observability for agents