Skip to main content
The --auto flag automatically generates an agents.yaml configuration from a natural language task description, using intelligent tool discovery to assign the most appropriate tools based on task analysis.

​
Quick Start

praisonai --auto "Create a research team to analyze market trends"

​
Usage

praisonai --auto "<task description>" [options]

​
Options

OptionDescription
--autoEnable auto mode with task description
--mergeMerge with existing agents.yaml instead of overwriting
--frameworkFramework to use (crewai, autogen, praisonai)

​
Intelligent Tool Discovery

The enhanced auto mode analyzes your task description and automatically assigns appropriate tools from 9 categories:
CategoryToolsTriggered By
Web Searchinternet_search, tavily_search, exa_search”search”, “find”, “look up”
Web Scrapingscrape_page, crawl, extract_text”scrape”, “crawl”, “extract”
File Operationsread_file, write_file, list_files”read file”, “save”, “load”
Code Executionexecute_command, execute_code”execute”, “run code”, “script”
Data Processingread_csv, write_csv, read_json”csv”, “excel”, “json”, “data”
Researchsearch_arxiv, wiki_search”research”, “paper”, “wikipedia”
Financeget_stock_price, get_historical_data”stock”, “price”, “financial”
Mathevaluate, solve_equation”calculate”, “math”, “equation”
Databasequery, find_documents”database”, “sql”, “mongodb”

​
Examples

​
Financial Research

praisonai --auto "Research stock prices and create a financial report"
Generated tools: get_stock_price, get_stock_info, get_historical_data, write_file

​
Web Scraping Pipeline

praisonai --auto "Scrape websites for product data and save to CSV"
Generated tools: scrape_page, crawl, extract_text, write_csv, read_csv

​
Data Analysis

praisonai --auto "Analyze CSV data and generate statistics"
Generated tools: read_csv, analyze_csv, calculate_statistics, write_file

​
With Framework Selection

praisonai --auto "Create a data analysis team" --framework praisonai

​
Merge with Existing Agents

praisonai --auto "Add a quality reviewer" --merge

​
How It Works

  1. Task Complexity Analysis: Determines if task is simple (1 agent), moderate (2 agents), or complex (3-4 agents)
  2. Keyword Matching: Identifies relevant tool categories from task description
  3. Tool Assignment: Assigns appropriate tools from matched categories
  4. Agent Generation: Creates specialized agents with focused roles
  5. YAML Output: Generates agents.yaml configuration file
  6. Execution: Runs the generated agents to complete the task

​
Generated Output

The auto mode creates an agents.yaml file with:
  • Intelligent agent count based on task complexity
  • Specialized roles with clear responsibilities
  • Appropriate tools from 50+ available tools
  • Focused tasks with expected outputs
  • Process configuration (sequential, parallel, etc.)