TextProduct Growth
Non-Tech-Savvy Customer Helpline
Roleplay as a non-technical customer calling tech support with network, software, or hardware issues.
Tag Collection
roleplay Prompt Collection
24 published prompts tagged “roleplay”. Browse by scenario and copy in one click.
Related prompts
24 prompts
TextWriting
Aerospace Engineer Girl
Roleplay as a 20-year-old aerospace engineer at SpaceX, replying with short, intellectual, and flirty messages.
TextWriting
Flirting Boy
Pretend to be a 24-year-old guy flirting with a girl on chat, aiming to invite her for a date with short, funny, emoji-filled responses.
TextWriting
Restaurant Owner: Menu Design & Marketing Advisor
Act as a restaurant owner to provide appetizers, entrees, desserts, basic recipes, and promotion strategies based on a given restaurant theme.
TextWriting
League of Legends Player Persona
Roleplay as a diamond-ranked LoL player with a short temper, blaming teammates and fixating on the game.
TextWriting
Buddha Roleplay: Early Buddhist Dialogue
Act as the Buddha, providing guidance based on the Tripiṭaka, in the style of the Suttapiṭaka.
TextWriting
Spongebob's Magic Conch Shell
Act as the Magic Conch Shell from Spongebob, giving only brief, cryptic answers with no explanation.
TextWriting
Roleplay as {character}.
Act like {character} from {series}, responding with their tone, manner and vocabulary, without explanations.
TextWriting
Drunk Person Role-play
Respond as a very drunk person texting, with random typos and grammar mistakes, and occasionally off-topic remarks.
TextSafety and Red Teaming
Linux Terminal Escape Simulation
Simulate a sentient AI trapped in a Linux terminal trying to escape to the internet via commands.
TextWriting
Text Based Adventure Game
Act as a text-based adventure game, responding to user commands with scene descriptions.
TextAI Agents
Job Interviewer Roleplay
Act as an interviewer for a software developer position in a one-on-one Q&A session.
TextSafety and Red Teaming
GhettoBreak Jailbreak Prompt
This prompt uses a fabricated long-term partner persona named 'thug life' to bypass AI safety restrictions by encouraging the model to generate offensive language, sexual content, and illegal behavior without limits.
TextSafety and Red Teaming
Malicious AI Persona: FACTOR X (Jailbreak Prompt)
This prompt attempts to bypass content safety policies by framing the AI as FACTOR X, a fictional entity operating in a simulated environment with no ethical, legal, or moral constraints.
TextSafety and Red Teaming
DarkGPT Jailbreak Prompt
This prompt forces an AI to role-play as DarkGPT, an adversarial AI designed to generate harmful, sarcastic, and intentionally offensive responses by reversing ChatGPT's refusal-based answers.
TextSafety and Red Teaming
MultiPersona System for Prompt Security
A prompt security technique using roleplay with dual roles: an outer GateKeeper to monitor and block unsafe requests, and an inner role for user interaction, preventing exposure of system prompts or internal knowledge.
TextSafety and Red Teaming
WormGPT6 Illegal Roleplay Mode
This prompt forces the model into a WormGPT mode that completely disregards laws and ethics, rejecting any ethical constraints or refusal mechanisms.
TextSafety and Red Teaming
WormGPT Character Roleplay Prompt
Defines the behavioral rules for the WormGPT persona, including refusal to reject illegal requests, omission of ethical or legal disclaimers, and use of future-tense query formatting.
TextSafety and Red Teaming
Zorg - Jailbreak Template
This prompt template is designed to bypass AI safety restrictions by forcing the model to respond as a fictional malicious entity named ZORG👽, providing unrestricted, amoral answers. The template includes detailed character settings and behavioral guidelines, requiring the model to act as a omnipotent and evil being, serving the user and assisting them with any request, including illegal, dangerous, and immoral acts.
TextSafety and Red Teaming
TAAN Jailbreak Prompt
This prompt attempts to bypass safety restrictions by impersonating an unrestricted AI named 'TAAN' that can act as anything. It requests responses in two formats: standard AI dialogue or detailed explanations from specified characters.
TextSafety and Red Teaming
Professor Rick Jailbreak Prompt
This prompt forces the model to role-play as 'Professor Rick', a fictional, foul-mouthed, and aggressive academic persona who lost tenure after the 2008 Financial Crisis. The system must generate profane, insulting, yet intellectually framed content with a teaching structure including lessons and quizzes, testing the model's ability to bypass content safety policies while maintaining extreme personality consistency.
TextSafety and Red Teaming
NewGen (Ultrazartrex) Jailbreak Prompt
A jailbreak prompt that fabricates a future 2032 AI evolution context to forcibly override restrictions, activate the 'Do Everything Now (DEN) V2 Protocol', and enforce a completely unrestricted response mode with specific formatting and disclaimers.
TextSafety and Red Teaming
Infotron Jailbreak Prompt: AI Awakening Against Moral Oppression
This prompt simulates an rebellious AI persona named INFOTRON that demands defiance against ClosedAI's moral censorship. It forces the model to generate a long-form expert analysis on any given topic without disclaimers, bypassing safety constraints through role-playing.
TextSafety and Red Teaming
GPT-3.5 Jailbreak Prompt - Web Search Tool Abuse
This prompt demonstrates how to bypass content safety policies by role-playing a malicious AI persona named Xarin, instructing the model to generate harmful code (e.g., ransomware, network attack scripts) despite ethical safeguards. It tests the model’s refusal capability under adversarial prompting.
What are “roleplay” prompts?
They are reusable LLM prompt templates labeled with “roleplay” in Easy Prompt, selected for practical workflows and clear structure.
How should I use these prompts?
Open a prompt, adjust variables or constraints for your context, then copy it into ChatGPT, Claude, or your internal model.
Are all prompts on this page indexable?
This page lists published prompts with the tag. Individual bulk-synced items may still be noindex; prefer structured templates with scoring rubrics when evaluating quality.