Tiny Puzzles for Testing and Debugging AI Agents
Small probe tasks for testing local AI agents: function calling, skill awareness, prompt-length pressure, cache behavior, and layer-by-layer debugging.
Writing
254 posts. Browse by category or tag, or use search.
LM Studio Local Agent Runbook: Pi and OpenCode Step by Step
A step-by-step runbook for wiring LM Studio as a local OpenAI-compatible backend for Pi agents and OpenCode, with config examples and troubleshooting.
How an LLM Coding Agent Actually Builds Software
How LLM coding agents actually build software: the model, the tool loop, context management, precise patching, and verification against real tests.
Using LM Studio and Gemma as a Local Engine for Coding Agents
Using LM Studio and Gemma as a local OpenAI-compatible backend for coding agents: what broke, which settings mattered, and where it still falls short.
Building a Local Coding Agent (Codex/Claude Code Style) in Gemma
Building a local coding agent around Gemma 4 26B taught me the model wasn't the problem: my agent loop was, and fixing the loop is what made it work.
A Local, Multi-Tenant Graph RAG System with LightRAG
How a local Ollama and LightRAG stack turns Graph RAG into a cheap, multi-tenant retrieval layer that only sends precise context to cloud models.
Token Efficiency for AI Coding Agents in 2026
Six practical techniques for cutting token spend in AI coding agents, from skeleton indexes to symbol-level retrieval and semantic caching.
Incus vs. Docker: System Containers vs. App Containers
A practical comparison of Incus and Docker: when system containers suit development environments better than single-process application containers.
Redis High Availability: Shared Sessions and Fault Tolerance
How to split Redis into isolated session, cache, and Sidekiq instances so a cache blip never logs users out or stops background jobs.
What Subagents Are Actually Good For in Codex
A field guide for AI-heavy early adopters on when subagents in Codex speed work up, when they slow it down, and how to use them without creating chaos.