About shimo4228/agent-adoption-triage
An Agent Skill holding a five-question triage for routing AI work to the right architecture (script, algorithmic search, LLM workflow, or autonomous agentic loop) *before* any agent is built. It is for anyone who hears "let's build an agent for X" and has to decide, or review, whether the use case actually needs an autonomous agent. The core inversion: the question is not whether an agent can do the work (it usually can), but whether accountability can still be distributed after you deploy it, that is, whether a failure can still be traced to someone who answers for it. Route the work first; pick the architecture second.