- Published on
Building a Robinhood trading assistant on Claude Code: an MCP connector for market data, a strategy engine with hard-coded risk rules, and a design where unattended order placement is structurally impossible, not just discouraged.
All Posts
- Published on
A source-grounded look at what's grown around vLLM's V1 engine since the canonical PagedAttention story: fault-tolerant engine cores, tiered KV offload, dual-batch overlap, async scheduling, and adaptive speculative decoding — with the real config flags for each.- Published on
What Claude Code actually is, how it differs from autocomplete-style AI tools, and the concepts — tools, permissions, subagents, skills, MCP, hooks — that make it useful for real engineering work instead of toy demos.- Published on
A practical, opinionated guide to designing memory for multi-agent LLM systems: topology, structural tenant isolation, the short-to-long maturation pipeline, retrieval and clamping, concurrency, and the four canonical failure modes.- Published on
Explore AWS Aurora: Scalable, secure, and high-performance relational databases on Amazon Web Services. Learn architecture, benefits, and best practices.