AI Agent Architecture Design Prompt
Design the architecture for autonomous AI agents with proper tool integration, state management, and safety constraints
Customize this template
Build your prompt
Generate Your Prompt
Fill in the required details first. Optional controls help you fine-tune the result.
What is this agent designed to do?
How complex is this agent?
Where will this agent run?
How should tools be organized?
What does the agent need to remember?
How autonomous should the agent be?
When should the agent stop and yield to the user?
What actions require confirmation or are forbidden?
See a completed example
Code Review Agent
Input Variables
Questions about this prompt
Best Practices
Critical Best Practices
Use Tool Preambles
criticalProvide clear progress updates before calling tools so users can follow the agent's work. This improves transparency and user experience during long operations.
Example:
“Before calling search tools, explain: "I'm going to search our knowledge base for recent updates on this topic..."”
Define Persistence Behavior
criticalSpecify when the agent should continue working vs. asking for clarification. Set clear stop conditions to avoid premature termination or endless loops.
Example:
“Only stop when: (1) Task is fully complete, (2) User explicitly asks to stop, or (3) You encounter an unrecoverable error.”
Define Error Handling Strategy
criticalSpecify how agents should handle errors, missing data, and edge cases. Should they retry, escalate, or proceed with uncertainty?
Set Safety Boundaries
criticalDefine which actions require confirmation (destructive operations, external API calls, file deletions) vs. which can be done autonomously.
Example:
“Ask before: deleting files, making API calls that cost money, or modifying production databases.”
Recommended Best Practices
Enable Parallel Tool Execution
recommendedAllow agents to call multiple independent tools simultaneously for faster execution. Critical for research and multi-step workflows.
Example:
“When gathering context, run file reads and searches in parallel rather than sequentially.”