Skip to content
AI-grafen
Sign in
☰ Menu

The goal E University

An AI service in operation

Observability, prompts as code, agent loops and tool use — how an AI feature is run once it actually has users.

Knowledge nodes
87
From zero
about 60 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: build an eval harnessEa 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 min

The whole path

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

AExplorer5 knowledge nodes
  1. Patterns and categories
  2. Sequences and precise instructions
  3. Basic programming with blocks
  4. Controlling a process with commands
  5. Repeat: loops
BInvestigator16 knowledge nodes
  1. Data in everyday life
  2. Algorithmic thinking
  3. Debugging: finding the error in the code
  4. Rule-based systems and machine learning
  5. Source criticism and responsibility in AI use
  6. Reinforcement learning: learning from feedback
  7. Training data, features and labels
  8. Classification: how a model sorts information
  9. Generative AI: how it creates content
  10. Language models and probabilities
  11. AI's invented answers
  12. Conditions in code: if–else
  13. Variables: named storage locations
  14. Identifying and fixing bugs
  15. Build a simple scoring system in code
  16. From idea to app
CBuilder17 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. Manual data labelling
  10. Linear regression: fitting a straight line to data
  11. Neural networks — the intuition
  12. Prompting — steering a language model
  13. Experiment: biased training data and its consequences
  14. Project: train an image classifier in the browser
  15. Retraining the model with your own examples
  16. AI that uses tools: the calculator
  17. Does my app need AI?
DAI developer26 knowledge nodes
  1. Derivatives and optimisation
  2. Python — functions, scope and exceptions
  3. Python — classes and objects
  4. APIs and HTTP
  5. Probability distributions
  6. Loss functions
  7. The normal distribution and standardisation
  8. Samples and uncertainty
  9. Testing with pytest
  10. Tokenisation
  11. Gradient descent
  12. The context window, system prompts and few-shot
  13. Vectors
  14. Matrices and matrix multiplication
  15. Linear regression with several features
  16. Neural networks — the forward pass with matrices
  17. Backpropagation
  18. Embeddings — words as vectors
  19. Attention
  20. Overfitting and generalisation
  21. PyTorch — tensors and autograd
  22. Retrieval — finding the right text
  23. Training, validation and test
  24. Train a neural network in PyTorch
  25. Transformers — the architecture
  26. Designing for the AI being wrong
EUniversity23 knowledge nodes
  1. Asynchronous programming
  2. Building an API with FastAPI
  3. Confidence intervals
  4. Hypothesis testing and p-values
  5. A/B tests and experiment design
  6. Multi-head attention in detail
  7. The KV cache
  8. Latency, throughput and batching in inference
  9. Cost modelling for LLM systems
  10. Cost, quotas and pricing
  11. Language models — training and generation
  12. Hallucinations — causes and countermeasures
  13. UX for AI features
  14. Model evaluation
  15. Build an eval harness
  16. Prompts as code: versioning and testing
  17. From prototype to product
  18. Observability for ML systems
  19. Product metrics for AI features
  20. RAG — retrieval-augmented generation
  21. Tool use
  22. Agents — plan, act, observe
  23. The ReAct loop: think, act, observe