Adrian Waldronllm
- How I Got 12/12 Clean Sections Out of a Batched LLM Pipeline
- What 36 LLM Calls Taught Me About Network Retry and Empty Defaults
- How I Hardened Apollo's Scanner Against Prompt Injection (Two Cheap Fixes That Actually Work)
- How One Bad Enum Was Silently Killing My Entire Scan Batch
- What Pydantic's `extra="forbid"` Gets Wrong When Your Data Comes From an LLM
- Why I Ended Up with One JSON Parser for Two Different LLM Models
- The API Won't Tell You When You're Paying Twice