
Loop / Harness Engineering
Agent loops turn prompts into one part of a production harness: tools, state, checks, approvals, and exit conditions.
Read
Resources
Field notes, comparisons, and implementation guides for building AI-powered software.
Field notes, comparisons, and implementation guides for building AI-powered software.

Agent loops turn prompts into one part of a production harness: tools, state, checks, approvals, and exit conditions.
Read

Plain-text context files are the git-native, zero-ops way to steer AI agents.
Read

A guide to building an MCP server for Markdown note taking
Read

A short conceptual guide to organising tools in agentic workflows
Read

A simple engine for converting any file type to Markdown.
Read

A verbose explanation of common auto-regressive decoding methods: temperature, top k and top p.
Read

A comparison of some of the most popular libraries that constrain LLM generation.
Read