Speculative Agents Need a Commit Boundary
Speculative execution cuts agent latency only when prediction and commitment are separate operations.
Read
LLM Infrastructure Guides
LLM applications depend on more than a model API. They need reliable ingestion, context preparation, tool interfaces, and runtime choices. This collection covers the infrastructure required to move from a prototype to maintainable AI-powered software.
Loop / Harness Engineering
Agent loops turn prompts into one part of a production harness: tools, state, checks, approvals, and exit conditions.
Read
How to Build an MCP Server
A guide to building an MCP server for Markdown note taking
Read
The Modern Document Processing Stack
A simple engine for converting any file type to Markdown.
Read
Decoding Methods for LLMs
A verbose explanation of common auto-regressive decoding methods: temperature, top k and top p.
Read