Skip to content
AI-grafen
Sign in
☰ Menu

The goal F AI engineering

Build a memory system for an agent

Episodic and semantic memory, retrieval and long-horizon evaluation — a working memory system that makes an agent better over time.

Knowledge nodes
68
From zero
about 53 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.

Project 5: Build a memory system for an agentFa sandbox · about 180 minLab: BM25 and a minimal RAG pipelineEa 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

AExplorer3 knowledge nodes
  1. Patterns and categories
  2. Sequences and precise instructions
  3. What is a computer?
BInvestigator10 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. The technology behind the web: how a page is fetched
  8. Generative AI: how it creates content
  9. Language models and probabilities
  10. AI's invented answers
CBuilder15 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. Search strategies: linear search vs binary search
  8. Statistics — mean, median and spread
  9. Probability — the basics
  10. Linear regression: fitting a straight line to data
  11. Neural networks — the intuition
  12. Prompting — steering a language model
  13. Fundamentals of search engines: indexing and ranking
  14. Asking effective questions to AI
  15. RAG: letting AI answer based on your own documents
DAI developer22 knowledge nodes
  1. Derivatives and optimisation
  2. Licences and open data
  3. Loss functions
  4. Tokenisation
  5. Text preprocessing
  6. BM25 and keyword search
  7. Gradient descent
  8. Build a small search engine
  9. Give your chatbot a memory
  10. Vectors
  11. Matrices and matrix multiplication
  12. Linear regression with several features
  13. Neural networks — the forward pass with matrices
  14. Backpropagation
  15. Embeddings — words as vectors
  16. Attention
  17. Overfitting and generalisation
  18. PyTorch — tensors and autograd
  19. Retrieval — finding the right text
  20. Training, validation and test
  21. Train a neural network in PyTorch
  22. Transformers — the architecture
EUniversity8 knowledge nodes
  1. Personal data and anonymisation
  2. Hybrid search and RRF
  3. Language models — training and generation
  4. Model evaluation
  5. RAG — retrieval-augmented generation
  6. Vector databases and indexing
  7. Tool use
  8. Agents — plan, act, observe
FAI engineering9 knowledge nodes
  1. Evals for language models and agents
  2. Episodic memory for agents
  3. Memory and privacy
  4. Memory retrieval: when should the memory be fetched?
  5. Semantic memory and consolidation
  6. Long-term evaluation of agents
  7. Consolidation and forgetting in memory systems
  8. Evaluating memory systems
  9. Contradictions and updating facts
GFrontier Lab1 knowledge nodes
  1. Procedural memory: learnt skills