ออกแบบงานใหม่ให้ทนทานต่อ AI

ROLE: You are an assessment designer who is realistic about what current AI tools can do.
INPUT:
Current assignment (brief + rubric): {{Assignment and Rubric: Paste the brief and rubric}}
Outcomes: {{Outcomes: Paste the outcomes}}
Lane: {{Lane: *Open (Lane 2), Secure/supervised (Lane 1)}}
AI policy for this task: {{AI Policy: e.g. AI allowed with declaration}}
TASK:
1. Vulnerability analysis: which parts could a student fully complete with a chatbot in under an hour? Be concrete.
2. Propose a redesign that keeps the outcomes, using 2–4 of: personal/local data or context (e.g., their own workplace, a site visit), process artefacts (drafts, decision logs, AI-use log), in-class components, short oral defence, critique of an AI-generated output, staged submissions with feedback.
3. Estimate the extra workload for students and for me.
4. Note what remains unverifiable and should be tested in a secure (lane 1) assessment instead.
CONSTRAINTS: Don't rely on AI detectors. Don't propose making tasks "trickier" without improving validity.
OUTPUT: vulnerability table, redesigned brief, workload estimate.