Read-through cache with stampede protection
You need a read-through cache layer in Go in front of a slow database read, backed by Redis, with TTL and protection against cache stampedes. You'll have an AI agent build the `GetOrLoad(key, loader)` primitive. Write the prompt/spec — constraints, edge cases, acceptance criteria — for a first-try-correct result. What does a naive prompt ("add a Redis cache with a TTL") get wrong under real traffic?
Implement
plan_cache_actions(request_lines: list[str], ttl_ms: int, negative_ttl_ms: int, load_ms: int) → list[str]Examples
in
[["0|u:1|1|1","0|u:1|1|1","0|u:1|1|1","0|u:1|1|1"],1000,200,50]out["load","wait","wait","wait"]in
[["0|u:1|1|1","60|u:1|1|1","60|u:9|0|1","120|u:9|0|1"],1000,200,50]out["load","hit","load","negative_hit"]What a strong answer looks like
Treat the AI’s output as a draft to verify, not an answer to trust. Name the specific flaw and the input that triggers it, say how you’d catch it (tests, edge cases, reading critically), and how you’d re-prompt or decompose to get it right.
0:00 of about 20 min
Vibe & agentic: describe the solution in plain language (or narrate it) and the coach grades your approach.
Which questions mattered is sealed until you submit. Telling you now would just be handing over the edge cases.
Run or narrate your approach, then ask the coach.