Use direct technical terms. Map each answer onto the keys in clarify.md Step 3.
session_duration: “How long do agent tasks typically run? seconds / minutes / hours
(≤8h) / >8h or continuous.” (>8h no longer rules AgentCore out — it routes to the
Instances compute type, sessions up to 14 days. Truly always-on services are still
steered elsewhere by .)
instance_type_requirement: “Do you have a requirement to choose a particular EC2
instance type for your agent — a specific family/size, a GPU model, or ARM? yes / no.”
idle_resume: “On idle-then-resume, do running processes need to continue exactly
(process_level), is filesystem persistence enough (filesystem), or not needed (none)?”
deployment_preference: “Do you want a no-code managed agent runtime (AgentCore Harness),
bring your own framework code (Strands/LangGraph/CrewAI/custom), or either?” Ask early. Only
affects the AgentCore deployment model, not the runtime score. Default either.
model_features: if priority is specialized (or a specific need is hinted), ask for the ONE
most critical feature — tool use / long context (>300K) / extended thinking / RAG / multimodal
(vision) / image generation / speech / embeddings. Drives a hard model override
(see ${CLAUDE_PLUGIN_ROOT}/skills/agent-advisor/references/decision-refs/model-selection.md). Else none.
current_model: migrate only.
region: “Where are your users / where must this run — single region, multi-region, or
global? Any specific region (e.g. EU)?” Gates runtime availability (AgentCore/Harness aren’t
everywhere) and, for EU/GDPR, the geo-CRIS vs global-CRIS data-residency choice. Not scored.