Agent Planner
Plan and configure AI agents with tools
Agent Configuration
{
"name": "Research Assistant",
"goal": "Help users research topics and answer questions",
"tools": [
{
"name": "web_search",
"description": "Search the web for information"
},
{
"name": "wikipedia",
"description": "Search Wikipedia articles"
},
{
"name": "calculator",
"description": "Perform mathematical calculations"
}
],
"system_prompt": "You are Research Assistant. Your goal is to Help users research topics and answer questions.\n\nYou have access to the following tools:\n- web_search: Search the web for information\n- wikipedia: Search Wikipedia articles\n- calculator: Perform mathematical calculations\n\nWhen you need to use a tool, respond with:\nAction: tool_name\nAction Input: your input\n\nAfter receiving the observation, continue reasoning until you have a final answer."
}Related Tools
RAG Chunking Calculator
Visualize how different chunk sizes and overlaps affect text splitting
AI Architecture Diagrammer
Create system architecture diagrams for LLM applications (RAG, Agents)
LLM Integration Checklist
Checklist for deploying LLMs into production (Caching, Logging, Eval)
LangChain Chain Builder
Visual builder to prototype LangChain sequences and prompts
Chunk Overlap Optimizer
Determine optimal overlap percentage to maintain context between chunks
RAG Pipeline Planner
Plan your RAG architecture: Embeddings, Vector DB, and Retrieval method
What is an AI Agent?
AI agents are LLM-powered systems that can use tools, make decisions, and complete multi-step tasks autonomously. Unlike simple chatbots, agents reason about which tools to use, execute actions, observe results, and iterate until they achieve their goal.
This planner helps you design agent configurations—defining the agent's purpose, available tools, and the system prompt that guides its behavior.
Agent Components
Goal
The agent's primary objective. Should be specific and actionable.
Tools
Functions the agent can call: web search, calculators, APIs, databases, code execution.
Common Agent Tools
| Tool | Use Case |
|---|---|
| web_search | Real-time information retrieval |
| calculator | Mathematical computations |
| code_executor | Run and test code snippets |
FAQ
How is this different from function calling?
Function calling is one-shot. Agents loop: they call tools, observe results, then decide what to do next until the task is complete.