Search for a command to run...
Articles tagged with #python
The experiment was fine. The runner was the bug. A single hung API call discarded hours of completed work, and I kept blaming the data. If your long-running eval keeps dying at 80%, this is the five-p
TL;DR — Three MCP servers in, you lose track of who can do what. I built MCP Fabric, an open-source control plane that puts OPA policies, human approvals, and full audit logging between your agents an
The Real Cost of an AI Task Isn't the Per-Call Price TL;DR — I built an open-source tier router that tracks what AI tasks actually cost, not what individual calls cost. Field tested against real Fast
TL;DR — 14-node LangGraph pipeline. 521 tests. 88.3% field test pass rate across 15 real incidents. $0 to run on a local LLM. The biggest surprise: my test design was wrong, not the tool. The 2 AM P
TL;DR — I built a RAG assistant for on-call engineers that indexes 55 runbooks. Header-split chunking hit MRR 0.9524 vs 0.8893 for fixed-size. The embedding model, LLM, and vector DB never changed. Ch
TL;DR — I was paying 18× more than necessary because every LLM call went through one frontier model. After building a 3-tier routing architecture (Architect / Workhorse / Utility), my cost per complet
