You're tuning a customer-service LLM to stop suggesting refunds in cases where refunds aren't allowed. Which directive is more reliably effective? · Zenaique

Attempt it

Quick reference

TL;DR

Positive 'do this' beats negative 'don't do that' because the model has an action to execute instead of an action to suppress.

Memory aid

Sign in for the mnemonic that makes this stick. See Pro pricing.

Easy to grasp

Imagine telling a toddler 'don't think about a red balloon.' What do they think about? Models behave the same way when you say 'do not suggest refunds.' To follow the rule, the model has to model the prohibited action first, then try to suppress it. Sometimes it works, sometimes the prohibited thing slips through. The fix is to give the model something to do instead. 'For refund requests outside policy, redirect the user to the support portal.' Now there is a clear action attached to the trigger, and the model just executes it. No suppression required.

Key concepts

Instruction Following Directive Design

Detailed answer & concept explanation

~5 min read

Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example. Click to expand.

Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example.

Sign in for 5 free unlocks/day or go Pro for unlimited. See Pro pricing.

Quick scan · 2–4 min

Everything important, quickly.

3 min: asymmetry of positive vs negative directives + suppression as the failure mode + priming risk of repetition + policy as action map pattern + expected lift from a positive rewrite.

Real-world examples

Real products, models, and research that use this idea.

Anthropic's Constitutional AI and Claude Opus 4.7 prompting guide both recommend positive framing over prohibitions for behavioral steering.
OpenAI's GPT-5.5 prompt engineering docs advise replacing 'do not' instructions with 'instead' patterns to improve compliance.
Customer-support assistants on platforms like Intercom Fin and Zendesk AI ship system prompts built around 'when condition, do action' templates rather than long prohibition lists.

Interviewer follow-ups

What an interviewer would ask next. Try answering before peeking at the approach.

QHow would you reframe a stack of six negative directives without losing coverage?

Sign in or go Pro to see the approach for this follow-up.

QWhen is a negative directive actually justified?

Sign in or go Pro to see the approach for this follow-up.

QHow do you measure the lift from a positive rewrite?

Sign in or go Pro to see the approach for this follow-up.

Don't say this

Red flags and common mistakes that signal junior thinking. Click to expand.

Most common mistake

Strengthening a negative directive with capitalization or repetition instead of replacing it with a positive substitute action.

Sign in or go Pro to see all red flags and common mistakes. See Pro pricing.

60-second cheat sheet

The night-before-the-interview bullets. Scan these on the way to the call.

Sign in for 5 unlocks/day or go Pro for unlimited revision sheets. See Pro pricing.

References

Primary sources. Skim if you want the original framing.