Methods · Perspective, simulation & context · Short guide
D20
Crisis scenario drill
Respond under time pressure to an unfolding situation: training prioritisation and decision hygiene when information is incomplete and the clock is moving.
When to use it
- You need practice deciding as information arrives, not in calm retrospect.
- A clinical, ops, debate, or on-call scenario rewards tempo.
- You freeze when plans meet the first surprise.
What to ask AI
Type something like: “Crisis drill: start a short unstable ward situation. Every 60-90 seconds of my replies, add a complication. Stay in role. Afterward debrief decision quality, not vibes.”
You decide in turns; no pausing for a textbook chapter.
How it helps
Crisis drills train decision under time pressure with unfolding information.
The skill is updating, prioritising, and communicating, not perfect foresight.
How to run it
- Agree the domain and stakes.
- Start with a short unstable situation.
- Respond in short moves; accept new complications.
- Debrief: what did you prioritise, ignore, or assume?
- Rerun the same stem with one constraint changed.
Example exchange
Start a paediatric fever crisis drill for a junior doctor. Escalate every turn,don’t give the whole algorithm up front.
Infant, high fever, parents anxious. First move?
ABC, think about fluids, call seniors early…
Two minutes later: mottling and delayed capillary refill. What changes in your priorities now?
Copyable prompt
Crisis drill. I am [ROLE]. Domain: [ ].
Start with a short unstable situation. Every 60-90 seconds of my responses,
inject a new complication. Never solve for me. After I say END, debrief: where
my prioritisation failed, what critical question I didn't ask, what I did well.
Keep a simple event log.
The Tell
You know this method has flipped when you narrate beautiful protocols and never make a timed call.
Un-timed crisis talk is still a seminar.
Keep the clock and the complications.
Principle evidence
Strength of the underlying learning idea, not a claim about AI products.
The underlying learning idea is rated moderate. Crisis drills under time pressure draw on simulation-based training and stress inoculation in professional education. Principle moderate; chat crisis fidelity limited, speculative.
AI delivery evidence
Whether an AI tutor delivers this method well is a separate question.
The learning principle may be moderate, but that does not prove an AI session delivers it well. Treat AI delivery as speculative unless a study of tutoring with this method is named, and none is claimed here.