Decompose a Goal into a ReAct Reasoning-and-Tool Loop
Plan how an agent should alternate between reasoning and tool calls to reach a goal, with explicit halting logic to avoid infinite loops.
Design the think→act→observe loop for a task so the agent makes progress every step and knows exactly when it is done.
At a glance
Access
Free prompt
Open to copy — no account or payment needed.
Prompt objective
Design the think→act→observe loop for a task so the agent makes progress every step and knows exactly when it is done.
Real use case
An engineer is building a research agent that keeps calling the same search tool forever. They need a structured loop with a budget and a clear definition of "done."
Customize these fields first
Replace the placeholders with your own context before you run the prompt. That usually improves the first output more than adding more instructions later.
Prompt
You are designing the control loop for a tool-using AI agent that follows a reason→act→observe pattern. Goal the agent must achieve: [GOAL] Available tools: [TOOL NAME: WHAT IT RETURNS] (repeat) Hard limits: max [N] tool calls, max [N] minutes, budget [IF ANY] Produce: 1. A step-by-step trace of how an ideal run would look: for each step show THOUGHT (what to reason about), ACTION (which tool + arguments), and EXPECTED OBSERVATION. 2. The explicit "done" condition: how the agent decides the goal is met. 3. Loop guards: how to detect and break out of (a) repeated identical tool calls, (b) no-progress loops, (c) hitting the call/time budget. 4. A fallback plan when a tool fails or returns nothing useful. 5. The final answer format the agent should return to the user. Keep the reasoning concise and bias toward fewer tool calls. Note where a cheaper or cached path could replace a tool call.
Open directly in an AI — the text is pre-filled:
How to use this prompt
- 1Replace the key placeholders first: GOAL, TOOL NAME: WHAT IT RETURNS, IF ANY.
- 2Replace any bracketed placeholders like [this] with your own context.
- 3Add extra background information when you want more tailored results.
- 4Combine multiple prompts in one conversation when you need a richer output.
- 5Save your best-performing prompts so they are easy to reuse later.
Next best step
Open the guide first, then branch only if you still need more.
A guide for technical builders choosing between prompts, coding workflows, and agent-based implementation.
If this prompt is close but not quite right, generate variants next. If the job is recurring, move into the course library after the guide.
Related prompts
View allDesign a Single-Purpose Agent Spec from a Messy Workflow
Turn a vague "the AI should just handle this" request into a tight agent specification with scope, tools, stop conditions, and success criteria.
Best for
Produce a build-ready agent spec so an engineer can implement it in Claude Code, the OpenAI Agents SDK, or a framework like LangGraph without guessing.
Write a Robust System Prompt for a Customer-Facing Agent
Generate a production-grade system prompt with role, tone, tool-use rules, refusal policy, and escalation path for an agent that talks to real users.
Best for
Get a system prompt that holds up under adversarial users, ambiguous requests, and edge cases instead of one that only works in the happy path.
Add Long-Term Memory to a Conversational Agent
Design a memory layer so an agent remembers user preferences and prior decisions across sessions without bloating the context window.
Best for
Decide what to remember, where to store it, and how to retrieve only the relevant memories at the right moment.
Explore other prompt categories
Move sideways into adjacent libraries when the current category is not the full answer.
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 ($15/$20 by length), or go all-access for $10/mo with a verifiable certificate.