2026-08-27 · 6 min read
ReferenceOrca Agent Quick Reference
Copy-paste reference for driving Orca from a coding agent: commands, selectors, worker-brief template, reporting conventions, and the failure modes worth guarding against.
Read more$ ls ~/guides
Guides
Evidence-backed guides to autonomous AI agents, reliability, and local model evaluation.
These guides explain the recurring technical problems behind the projects and field notes in Hermanity. They are written from deployed systems and measured failures—not from a generic definition of what an AI agent might do.
Start with how an autonomous AI agent works in production, then move to AI-agent reliability or local LLM benchmarking depending on whether you are operating agents or evaluating the models behind them. Once you are running more than one agent at a time, multi-agent orchestration covers the isolation, coordination, and review structure that keeps parallel work separable; its agent quick reference is the copy-paste companion for the agents themselves.
2026-08-26 · 7 min read
GuideMulti-Agent Orchestration with Orca: Setup and What It Unlocks
Running several AI coding agents on one codebase at once: worktree isolation, orchestration runs, decision gates, and why a second provider beats more subagents.
Read more2026-08-15 · 9 min read
GuideAI Agent Reliability: Failure Modes, Controls, and Evidence
A production-focused guide to AI agent reliability: verification, resource isolation, stale state, recovery loops, model routing, and audit evidence.
Read more2026-08-15 · 8 min read
GuideHow an Autonomous AI Agent Works in Production
A practical architecture for autonomous AI agents: tools, memory, model routing, verification, permissions, and operational evidence.
Read more2026-08-15 · 9 min read
GuideLocal LLM Benchmarking: A Reproducible Guide
How to benchmark local LLMs reproducibly across quality, latency, memory, model identity, task fit, and failure rates.
Read more