AI Agents AI prompts
Agentic workflows, multi-agent systems, MCP tools, Claude Code and autonomous AI assistants. Best for designing reliable single and multi-agent systems, wiring tools, MCP servers, and coding agents like Claude Code, adding evaluation and guardrails before agents touch production.
20
In this category
All of them
Free to copy
5
Subcategories
3
Difficulty levels
Every prompt below is open. Copy it straight into ChatGPT, Claude, or Gemini.
Guide
AI agents guide
Open the guide that shows how this prompt category fits into a broader workflow.
Role path
Agent builder path
See how this category fits into a role-based AI workflow instead of using prompts in isolation.
Generator
Generate prompt variants
Use the prompt generator when you know the job to be done but not the exact prompt structure yet.
Course path
Course library
Move into structured lessons when you want a repeatable system, not only a single prompt.
Choose the closest workflow
Filter by subcategory and difficulty first. That usually gets you to the right prompt faster than scrolling the full list.
Filtered prompts
4 prompts match the current filters
Create an evaluation set for a customer-support agent
An evaluation dataset specification and scoring sheet. Start with your own evidence and finish with a reviewable next step.
Best for
Produce an evaluation dataset specification and scoring sheet from the supplied inputs.
Build an Eval Suite for an Agent Before You Trust It
Create a structured evaluation set with test cases, scoring rubric, and pass thresholds so you measure an agent instead of vibe-checking it.
Best for
Replace "it seems to work" with repeatable evals that catch regressions when you change the prompt, model, or tools.
Add Guardrails Before an Agent Gets Write Access
Design layered guardrails — input filters, action confirmation, output checks, and kill switches — for an agent that can take real actions.
Best for
Make an action-taking agent safe to deploy by adding controls around what it can do, when, and with what oversight.
Diagnose Why an Agent Keeps Failing in Production
Analyze an agent's failing traces to classify root causes — prompt, tools, model, or data — and prescribe the highest-leverage fix.
Best for
Turn a pile of bad runs into a ranked list of root causes and concrete fixes instead of guessing what to tweak.
Every prompt here is free. The course teaches the thinking behind them.
Copy as many prompts as you like. When you want to move from single prompts to a repeatable AI workflow, Learn AI in 30 Days walks through it, one day at a time.
Buy the course once ($20), or choose $10/month or $100 lifetime access.
Related categories
Explore adjacent prompt libraries that support ai agents workflows.
AI Automation
n8n/Make workflows, AI agents, backoffice automation and customer service automation
Programming & Dev
Code, debugging, architecture, DevOps and AI-powered development
Personal Productivity
Organization, automation, focus, efficient meetings and decision-making
Data Analysis
Excel, SQL, data visualization, KPIs and AI-powered reporting
How to use AI Agents prompts well
Start with the prompt closest to your workflow, replace any placeholders with your own context, and tell the model what a good output looks like. The fastest improvement usually comes from clearer context, tighter constraints, and a more specific deliverable.
This category is especially useful for designing reliable single and multi-agent systems. Treat the prompt as the execution layer, then refine it into a reusable workflow once you know it solves a real recurring problem.