Volatility targeting: sizing by realized vol instead of conviction
Early in my systematic trading career, I blew up a highly promising trend-following model because of a single, deeply human flaw: I sized my positions bas…
Read entryLatest
Building a quant research pipeline with AI agents
I spent the first half of last year writing the same boilerplate code over and over again. My workflow as a quant researcher followed a mind-numbing patte…
Read entry
Building a crypto trading bot with Temporal and PostgreSQL
When building a high-frequency or medium-frequency crypto trading bot, developers usually start with a simple asyncio loop or a Celery queue. I did exactl…
Read entry
LangGraph vs Temporal for AI workflow orchestration
I've shipped agent workflows on both LangGraph and Temporal, and I keep seeing them framed as competitors. They're not. They solve different problems, and…
Read entry
Using LLMs to generate trading signals: what actually works
The first thing I tried with LLMs and trading was the obvious, wrong thing: I asked the model to predict price direction. "Given this news, will the stock…
Read entry
How I use regime detection to switch trading strategies automatically
For about a year I ran a single mean-reversion book and quietly accepted that it bled money for weeks at a time. The strategy was fine. The problem was th…
Read entry
pgBouncer connection pool exhaustion: a real production postmortem
At 2:14 AM the pager went off: every API request was timing out with remaining connection slots are reserved for non-replication superuser connections. Th…
Read entry