PROGRESS.md

My Agentic Engineering Progress

For each project, check the milestones only after you can explain the behavior.

Project	Read	Ran tests	Completed challenge	Wrote reflection
01 Experimentation	[ ]	[ ]	[ ]	[ ]
02 Engineering foundations	[ ]	[ ]	[ ]	[ ]
03 Jobs & events	[ ]	[ ]	[ ]	[ ]
04 LLM gateways	[ ]	[ ]	[ ]	[ ]
05 Agent design	[ ]	[ ]	[ ]	[ ]
06 Evaluations	[ ]	[ ]	[ ]	[ ]
07 Inference infrastructure	[ ]	[ ]	[ ]	[ ]
08 Load testing	[ ]	[ ]	[ ]	[ ]
09 Data retention	[ ]	[ ]	[ ]	[ ]
10 Kernels & performance	[ ]	[ ]	[ ]	[ ]
11 Ontologies & semantics	[ ]	[ ]	[ ]	[ ]
12 Cost of cognition	[ ]	[ ]	[ ]	[ ]
13 Agentic security	[ ]	[ ]	[ ]	[ ]
14 Agent identity	[ ]	[ ]	[ ]	[ ]
15 Human oversight operations	[ ]	[ ]	[ ]	[ ]
16 Context & memory systems	[ ]	[ ]	[ ]	[ ]
17 Evals, traces & logs	[ ]	[ ]	[ ]	[ ]
18 Guardrails in the request path	[ ]	[ ]	[ ]	[ ]
19 Adaptation economics	[ ]	[ ]	[ ]	[ ]
20 AI Act & governance	[ ]	[ ]	[ ]	[ ]
21 Tailnets & agent networking	[ ]	[ ]	[ ]	[ ]
22 Engineering best practices	[ ]	[ ]	[ ]	[ ]
23 The challenge	[ ]	[ ]	[ ]	[ ]

Reflection prompts

1. What invariant did the tests prove?
2. What important production behavior did they not prove?
3. Which failure surprised you?
4. What would you measure before increasing complexity?