Context compaction made our agent blame the user
Our runtime's own compaction interrupt was recorded as the user refusing a tool. Why the SDK can't say who interrupted, and the fix we shipped.
Qwen Flash on two RTX 5090s: speed, cache and the queue
Completed 256K output, returning-prefix reuse and a 226-second overload probe. Serving results, failure boundaries and reproduction recipes.
MoE vs dense LLM inference: vLLM benchmark on two RTX 5090s
A 35B mixture-of-experts model against the dense 27B we run in production, on the same two GPUs with the same vLLM flags: 106 measured cells, KV capacity, tool calls, and where each one wins.
How I work with you: a private AI partner, not an agency
The whole engagement on one page: measured baseline, scope on paper, a 30-day sprint with written acceptance, monthly ownership, gates instead of dates, liability first, and what I refuse to build.
Qwen3.8-27B NVFP4 on two RTX 5090s: production field report
What Qwen, Unsloth, vLLM and Blackwell each contribute, the exact serving configuration, fourteen days of production counters, the failure modes, the official recipe compared, and the planned post-training loop.
Claude Code agent teams: what they are, when to use them
What a team is, how the lead, teammates, task list, and hooks fit, what it costs, and why a production content pipeline runs subagents with file handoff instead.
Claude Code memory: CLAUDE.md, auto memory, and rules
CLAUDE.md scopes and load order, path-scoped rules, how auto memory and its 200-line index work, what survives compaction, and the failure modes of memory at scale.
Claude Code plugins: install, build, and distribute
What a plugin contains, the two-step marketplace install, building with --plugin-dir, the marketplace file, and when a standalone .claude directory is the better answer.
Claude Code skills: SKILL.md, triggers, and context cost
SKILL.md frontmatter that changes behavior, dynamic context and its failure modes, the listing budget, and a real /skill-doctor report from a 66-skill setup.
AI agents in agriculture: from field update to decision
A privacy-safe implementation guide to work orders, voice and photo intake, source systems, human approval, recovery, and plan-vs-actual operations.
AI agents for business: what works in practice
The implementation method: start with recurring work, separate facts from judgment, keep authority narrow, and prove the finished result where it lands.
Codex skills: build reusable workflows that trigger
A complete SKILL.md, the trigger design that decides whether it runs, how to split scripts from judgment, and when a local skill should become a plugin.