ASAPPrompt AI to be "verifiable": principles of prompt design
The core of using AI well is to ask in a verifiable form. Andrej Karpathy said in 2026 that "traditional computers automate what you can specify in code, and LLMs automate what you can verify." So a prompt gets more accurate the more it makes the output verifiable. ASAP organizes this principle into prompt design.
Why verifiability is the core
Where an LLM is strong versus weak is split by verifiability. Models are trained by reinforcement learning in environments where answers can be graded (tests, scores, proofs), so they spike in capability on such tasks. Asking in a verifiable form draws out that strength and lets people catch the result too.
Three design principles
A verifiable prompt is built from 3 design principles, in the spirit of Karpathy's point. Apply them in order.
- State the correctness bar — pin down what counts as "right" with tests, examples, or a format.
- Require output in a verifiable form — ask for checkable output like code-plus-tests, a table, or a checklist.
- Require a self-check step — have it review and look for counterexamples before giving the answer.
All three are devices that make the result checkable.
Bad prompt vs good prompt
The same task is split by verifiability, with LLM output diverging sharply. The following contrast is the key.
| Bad prompt | Good prompt |
|---|---|
| "Fix this function" | "Make this input produce this output, and write that case as a test too" |
| "Write marketing copy" | "Output each of the 5 items below as one sentence, in a table" |
| "Analyze this" | "Give the conclusion in one line first, then the basis as 3 numbers" |
The right column draws out the model's strength and makes the result verifiable.
When the task is not verifiable
Tasks that are hard to verify are risky under any prompt. With no way to grade the answer, the model can produce a plausible wrong answer that people miss too. Such tasks should be split into small verifiable pieces, or have human judgment explicitly inserted.
Wrap-up
A good prompt is a verifiable prompt. State the correctness bar, require output in a checkable form, and ask for a self-check. Engraving "LLMs automate what you can verify" into your prompts is the key.
Source: ASAP synthesis grounded in Andrej Karpathy, "From Vibe Coding to Agentic Engineering" (Sequoia AI Ascent 2026; specify-able to verify-able automation).
AI & tech,
delivered fastest
Beyond the headlines — into the context and the structure
Ai Soon As Possible · asapai.co.kr
