A public journey from QA engineer to AI test architect. 52 weeks, 9 hours a week, every experiment documented honestly. The goal: ship a real LLM testing framework on PyPI by week 52.
9 of 52 weeks complete (17%)
Phase 1: LLM Fundamentals (Weeks 9-18) - In Progress
Phase 2: Evaluation Core (Weeks 19-28)
19
20
21
22
23
24
25
26
27
28
Phase 3: Frameworks Mastery (Weeks 29-38)
29
30
31
32
33
34
35
36
37
38
Phase 4: Agentic AI and Production (Weeks 39-46)
39
40
41
42
43
44
45
46
Phase 5: Capstone - LLMTestKit on PyPI (Weeks 47-52)
47
48
49
50
51
52