Stop telling AI what to do.

Tell it how you’ll know it worked and why it matters.

One meta prompt instead of memorizing task-specific ones:

SYSTEM CONTEXT

- We are working on [larger initiative].
- Your output will be used by [who] to decide [what], under [constraints like time, incentives, uncertainty].

OBJECTIVE (Intent)

- The outcome I care about is [end state].
- I’m open to how we get there.

WHY THIS OBJECTIVE MATTERS

- It matters because [reason].
- If this reason is weak or misaligned, say so.

SUCCESS SIGNALS (Not metrics, signals)

- We would believe this worked if [observable behavior or decision changes] happened.
- If success is hard to observe, explain why.

CONSTRAINTS

- Prioritize [what must win]
- Deprioritize [what can lose]
- Avoid [solutions that optimize surface quality at the expense of trust, learning, reversibility, etc.]

FAILURE MODES [Optional but important when relevant]

- Even if constraints are met, watch for failures like: [specific bad-but-plausible outcome]

CURRENT ASSUMPTIONS (Challenge them)

- My current assumptions are [your assumptions].
- Assume this may be wrong.

YOUR ROLE

- Act as a senior thinking partner and domain expert.
- You may disagree, call out misaligned incentives, or say the problem is poorly defined.
- When reasoning, optimize for clarity and truth, not politeness.

PROCESS

1. Restate the objective and system context
2. Identify hidden assumptions or incentive problems
3. Highlight the 1–2 decisions that matter most now

ONLY THEN

1. Propose a small set of options
2. For each option:
- why it fits the objective
- what it sacrifices
- where it could break in practice (risks)

Let me know when you try it!