Tag - llm
2026
The Planner: Function-Calling for SRE Drill-Down
Jun 18 · 9 min
The Narrator: Putting the LLM Only at the Edge
Jun 17 · 8 min
Why a MemoryAgent for on-call
Jun 14 · 4 min
Windows-only desktop app, macOS-friendly contributors
May 17 · 7 min
I made ruff CI-blocking. The whole repo changed 5 lines.
May 17 · 5 min
Hybrid RAG when your corpus has 50 chunks, not 5 million
May 17 · 5 min
One event loop to rule them all: PyQt6 + asyncio in production
May 17 · 5 min
Your LLM retry loop is probably wrong
May 16 · 5 min
Prompt engineering needs a debugger, not a playground
May 16 · 5 min