Leaving this course?

Standards and frameworks covered

The published frameworks this course teaches toward. Saolix is not affiliated with, endorsed by or accredited by any of these bodies; naming a standard is a citation, not a claim about its author.

Sources

The official documents this course relies on. Laws and guidance change, so check the current version.

  1. Data Protection Act, 2019 (sections 25 and 48 to 50) · Kenya Law
  2. OpenAI compatibility (the chat-completions endpoint and tool support) · Ollama
  3. Python downloads and documentation · Python Software Foundation
  4. Building effective agents (workflows and agents; start with the simplest solution) · Anthropic
  5. OWASP Top 10 for Agentic Applications for 2026 (the principle of least agency) · OWASP GenAI Security Project
  6. Mandate fraud (changed supplier bank details) · National Business Crime Centre (UK police)
  7. OWASP Non-Human Identities Top 10 · OWASP Foundation
  8. JSON Schema reference (types, enum, pattern, minimum and maximum) · JSON Schema
  9. Python documentation, unittest (writing the lab's tests) · Python Software Foundation
  10. Data Protection (General) Regulations, 2021 (regulations 19, 22, 26, 37, 40, 46 and 49) · Kenya Law
  11. Text Embeddings Reveal (Almost) As Much As Text (Morris and others, EMNLP 2023) · arXiv
  12. τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains (Yao and others, Sierra, 2024), the source of pass^k · arXiv
  13. Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations (Miller, 2024) · arXiv
  14. Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena (Zheng and others, 2023), on the biases of model graders · arXiv
  15. Demystifying evals for AI agents (2026) · Anthropic
  16. Glossary (temperature: even at 0.0, results are not fully deterministic) · Anthropic
  17. Python documentation, random (seeded random numbers for repeatable tests) · Python Software Foundation
  18. Python documentation, unittest.mock (replacing a function during a test) · Python Software Foundation
  19. OWASP Top 10 for Large Language Model Applications 2025 · OWASP GenAI Security Project
  20. What is OpenTelemetry? (an open-source, vendor-neutral toolkit for traces, metrics and logs) · OpenTelemetry (Cloud Native Computing Foundation)
  21. Model IDs and versioning (pinned versions, aliases and serving changes) · Anthropic
  22. Gemini API models (stable versions and "latest" names) · Google
  23. Python documentation, hashlib (stable hashes) and copy (deep copies) · Python Software Foundation