Escalation Assess

GPTClaudeDeepSeek··▲ 1,260 copies·updated 2026-07-14

escalation-assess.prompt

# Action: escalation_assess

For each DQ/TP in a domain, assess whether the agent can auto-resolve it or must escalate to the human. Evaluate four dimensions: reversibility, blast radius, ambiguity, and tech-vs-business. Conservative default: when uncertain, escalate.

## Input

when to use it

Community prompt sourced from the open-source GitHub repo lin13k/cplus (MIT). A "Escalation Assess" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.