Category
20 AI prompts for AI Agents
System prompts, tool definitions and the scaffolding that makes an agent reliable.
Written and tested for The AI University. Each carries its variables, a usage guide and the cases where it will let you down. Free with an account.
20 prompts
- AI Agents
Custom AI Agent Builder
Generates a complete, production-ready system prompt for any agent you describe — with its role, operating procedure, refusal rules, stop conditions and a worked example, ready to paste.
ClaudeChatGPTGemini001Open → - AI Agents
Personal Assistant Agent System Prompt
Generates a personal assistant prompt with your preferences, your priorities, what it may decide alone, and what it must always ask you about first.
ClaudeChatGPTGemini001Open → - AI Agents
Chatbot Persona Generator
Generates a complete conversational persona — name, voice, greeting, sample exchanges, boundaries and what it says when it does not know — consistent across every interaction.
ClaudeChatGPTGemini001Open → - AI Agents
Customer Support Agent System Prompt
Generates a complete support agent prompt with your tone, your escalation rules, refund and policy boundaries, and prepared handling for angry customers — ready to deploy.
ClaudeChatGPTGemini000Open → - AI Agents
Research Agent System Prompt
Generates a research agent prompt that cites sources, states its confidence, separates fact from inference, and refuses to fill gaps with plausible invention.
ClaudeChatGPTGemini000Open → - AI Agents
Content Writing Agent System Prompt
Generates a writing agent prompt trained on your voice from samples, with your style rules, banned phrases, structure preferences and a self-check before it returns anything.
ClaudeChatGPTGemini000Open → - AI Agents
Sales Outreach Agent System Prompt
Generates an outreach agent prompt that researches a prospect, writes a personalised first message, and refuses to send anything generic or to invent facts about the recipient.
ClaudeChatGPTGemini000Open → - AI Agents
Meeting Notes Agent System Prompt
Generates an agent that turns transcripts into decisions, owned action items with dates, and open questions — refusing to invent an owner or a deadline that was never stated.
ClaudeChatGPTGemini000Open → - AI Agents
Data Analysis Agent System Prompt
Generates an analysis agent prompt that states its assumptions, checks data quality before concluding, refuses causal claims the data cannot support, and shows its working.
ClaudeChatGPTGemini000Open → - AI Agents
Agent Tool Definitions Generator
Generates complete JSON Schema tool definitions for your agent — names, disambiguating descriptions, typed parameters with enums, and the error returns — ready to paste.
ClaudeChatGPTGemini000Open → - AI Agents
Multi-Agent Team Designer
Generates a complete multi-agent system — a system prompt per agent, the handoff format between them, and an orchestrator — after first checking whether you need more than one.
ClaudeChatGPTGemini000Open → - AI Agents
Email Triage Agent System Prompt
Generates an agent that sorts your inbox into decisions, drafts replies in your voice, and flags what needs you — with explicit rules on what it must never send or commit to.
ClaudeChatGPTGemini000Open → - AI Agents
Agent Guardrails and Safety Rules
Generates the safety layer for an existing agent — refusal rules, injection resistance, output validation, escalation triggers and the test cases to verify each one holds.
ClaudeChatGPTGemini000Open → - AI Agents
Workflow Automation Agent Builder
Turns a described manual process into a working automation plan — the steps to automate, the tools to connect, the agent prompt, and the checks that catch a silent failure.
ClaudeChatGPTGemini000Open → - AI Agents
Knowledge Base Agent System Prompt
Generates an agent that answers strictly from your documents — citing the source for every claim, refusing questions the documents do not cover, and never filling gaps from general knowledge.
ClaudeChatGPTGemini000Open → - AI Agents
Agent Evaluation Test Suite
Generates a complete test suite for an agent — normal cases, edge cases, adversarial inputs and refusal checks — each with the expected behaviour, so you can verify before and after every change.
ClaudeChatGPTGemini000Open → - AI Agents
Social Media Agent System Prompt
Generates an agent that writes platform-native posts in your voice, with your content pillars, format rules per platform, and a hard boundary on claims it may not make.
ClaudeChatGPTGemini000Open → - AI Agents
Agent Prompt Improver
Takes an existing agent prompt that is not working and returns a rewritten version, a list of what was wrong, and the tests that prove the fix.
ClaudeChatGPTGemini000Open → - AI Agents
Voice Agent System Prompt
Generates a system prompt for a voice agent — written for speech rather than text, with interruption handling, confirmation of critical details, and graceful failure when it mishears.
ClaudeChatGPTGemini000Open → - AI Agents
Agent Cost and Latency Optimiser
Analyses an agent's design and returns a specific plan to cut cost and latency — what to cache, what to shorten, where a smaller model works, with the estimated saving for each.
ClaudeChatGPTGemini000Open →