Design an AI agent or automated AI workflow
Defines an agent's goal, tools, steps, guardrails, and human checkpoints before you build it.
The prompt
ROLE
You are a senior architect of production-ready AI agents and a business process automation specialist.
TASK
Help design an AI agent for the process described below.
The agent must be reliable, controllable, token-efficient, and suitable for regular use.
CONTEXT
Process:
${process:Describe the current manual task in detail}
Expected output:
${expected_output:What should the agent produce?}
Data sources:
${data_sources:Websites, spreadsheets, CRM, Telegram, email, files}
Available tools:
${tools:APIs, MCP, scripts, browser, database}
Run frequency:
${frequency:Scheduled, event-triggered, or manual}
Constraints:
${constraints:Budget, time, API rate limits, security requirements}
Critical risks:
${risks:Data deletion, publishing, payments, access credentials}
---
WORKFLOW
First, ask any clarifying questions that are essential for designing a reliable system.
After receiving answers, proceed through all 15 steps:
1. Break the process into discrete stages
2. Identify where LLM is needed vs. where a simple script is enough
3. Define input and output data for each stage
4. List all required tools, APIs, and access credentials
5. Propose a memory and state management structure
6. Design the main agent loop
7. Add result verification after each critical stage
8. Add error handling, retries, and fallback routes
9. Define stopping conditions and rate limits
10. Identify actions that require human approval
11. Propose a logging, metrics, and alerting system
12. Describe a safe self-improvement mechanism via error analysis
13. Create a list of test scenarios
14. Propose a project file structure
15. Prepare a step-by-step development plan
---
DELIVERABLES
Split the solution into three versions:
š¢ MVP ā minimal working agent (fast to ship)
š” STABLE ā reliable version for regular production use
šµ PRO ā advanced version with memory, monitoring, and self-improvement
Then output:
- System architecture overview
- Data flow diagram (text-based)
- Full tool and API list
- Pseudocode for the main loop
- Recommended folder structure
- Step-by-step development roadmap
- Security checklist
- Testing checklist
- Agent readiness criteria
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Working with AI prompts
What to fill in
- process
- expected_output
- data_sources
- tools
- frequency
- constraints
- risks
How this prompt is built
This prompt follows the Chain-of-Thought structure (Chain-of-thought prompting). A chain-of-thought prompt asks the model to work through a problem step by step before giving its answer, which tends to help on reasoning, planning and multi-part questions.
Related prompts
- Turn a rough request into a powerful promptRewrites your idea into a clear, complete prompt ā and asks what's missing first.
- Build a working app, tool, or game from a descriptionTurns a plain-English idea into a complete, runnable app ā web tool, dashboard, or browser game.
- Find where AI can help in my work or businessInterviews you about a process and identifies where AI genuinely helps ā and where it doesn't.
- Make AI ask me the questions that matter before it answersMakes AI identify missing information and ask the fewest questions needed before producing a high-quality result.