Recipe Create

Create AI agent recipes from natural language goals

Create complete agent recipes automatically from a simple goal description.

The AI analyzes your goal and generates optimized agents, tools, and workflows.

Quick Start

praisonai recipe create "Build a web scraper for news articles"

This creates a ready-to-run recipe folder with just 2 files:

agents.yaml

Agent definitions, workflow steps, and optional metadata

tools.py

Custom functions and dynamic variables

The simplified 2-file structure reduces complexity. Metadata for registry publishing is now an optional block inside agents.yaml.

How It Works

Options

Option	Short	Description	Default
--output	-o	Output directory	Current directory
--no-optimize		Skip optimization loop	false
--iterations		Max optimization iterations	3
--threshold		Score threshold to stop	8.0
--agents		Custom agent definitions	Auto-generated
--tools		Custom tools per agent	Auto-selected
--agent-types		Agent types (image, audio, etc.)	Auto-detected

Examples

Basic

Create a simple recipe:

praisonai recipe create "Summarize PDF documents"

Research

Create a research agent:

praisonai recipe create "Research latest AI papers and create a summary report"

Data Processing

Create a data pipeline:

praisonai recipe create "Analyze CSV sales data and generate insights"

Web Tasks

Create a web automation recipe:

praisonai recipe create "Scrape product prices from e-commerce sites"

Custom Agents and Tools

Define your own agents instead of letting AI decide:

Custom Agents

Define agents with roles and goals:

praisonai recipe create "Research AI" \
  --agents "researcher:role=AI Researcher,goal=Find papers;writer:role=Writer,goal=Summarize" \
  --no-optimize

Custom Tools

Assign specific tools to agents:

praisonai recipe create "Research AI" \
  --tools "researcher:internet_search,arxiv;writer:write_file" \
  --no-optimize

Agent Types

Use specialized agent types:

praisonai recipe create "Generate images" \
  --agents "artist:role=Image Creator,goal=Create product images" \
  --agent-types "artist:image" \
  --no-optimize

Combined

Full customization:

praisonai recipe create "Research and visualize" \
  --agents "researcher:role=Researcher;artist:role=Visualizer" \
  --tools "researcher:internet_search;artist:write_file" \
  --agent-types "artist:image" \
  --no-optimize

Format Reference

--agents format

name:role=X,goal=Y,backstory=Z;name2:role=A,goal=B

• Separate agents with ;
• Separate properties with ,
• Use = for key-value pairs

--tools format

agent:tool1,tool2;agent2:tool3,tool4

• Separate agents with ;
• Separate tools with ,

--agent-types format

agent:image;agent2:audio

Available types: image, audio, video, deep_research, ocr, router

---

Skip Optimization

For quick prototyping, skip the optimization loop:

praisonai recipe create "Simple calculator" --no-optimize

Custom Optimization

Fine-tune the optimization process:

praisonai recipe create "Complex research task" \
  --iterations 5 \
  --threshold 9.0

Higher threshold (9-10) produces better quality but takes longer. Lower threshold (6-7) is faster but may need manual refinement.

Specialized Agent Types

The AI automatically selects the right agent type based on your goal:

ImageAgent

For image generation tasks (DALL-E, Stable Diffusion)

praisonai recipe create "Generate product images for store"

AudioAgent

For text-to-speech and speech-to-text

praisonai recipe create "Create podcast narration"

VideoAgent

For video generation (Sora, Runway)

praisonai recipe create "Create promotional video"

DeepResearchAgent

For comprehensive research tasks

praisonai recipe create "Research market trends"

OCRAgent

For text extraction from images/documents

praisonai recipe create "Extract text from receipts"

Quality Rules

The AI follows strict quality rules when generating recipes:

Environment Variables

Only includes env vars that are actually used:

• OPENAI_API_KEY - Always required (for LLM)
• TAVILY_API_KEY - Only if using tavily_search or tavily_extract

Tools like wiki_search, internet_search, read_file do NOT need TAVILY_API_KEY

Concrete Values in Actions

Actions use concrete values, not variables:

✅ Good: "Use wiki_search to find information about Python programming"

❌ Bad: "Use wiki_search to find {{topic}}" (variables don’t substitute!)

Reliable Tools

Prefers reliable, well-tested tools:

Recommended: wiki_search, tavily_search, internet_search, read_file, write_file

Avoid scrape_page, crawl4ai - may have loading issues

Specific Actions

Every action specifies which tool to use:

✅ Good: "Use tavily_search to find the top 5 AI trends in 2024"

❌ Bad: "Research AI trends" (too vague)

No Empty Fields

Omits unused fields entirely:

• No knowledge: []
• No memory: false
• No handoffs: []

Verified Quality Scores

Recipes generated with these rules achieve high judge scores:

Task Type	Tool Used	Judge Score
Wikipedia Research	wiki_search	9.83/10 ✅
AI Trends Research	tavily_search	7.25/10 ✅
Data Analysis	read_csv, write_csv	8.0+/10 ✅

For best results, use wiki_search for factual research and tavily_search for current events.

Output Structure

After creation, your recipe folder contains just 2 files:

my-recipe/
├── agents.yaml      # Agent definitions + optional metadata
└── tools.py         # Custom functions and dynamic variables

agents.yaml Example

# Optional: Metadata for registry/sharing
metadata:
  name: web-scraper
  version: "1.0.0"
  description: Scrape news articles from websites
  author: your-name
  license: Apache-2.0
  tags:
    - web
    - scraping
  requires:
    env:
      - OPENAI_API_KEY

framework: praisonai
topic: "Web Scraper for News"

agents:
  scraper:
    role: Web Scraper
    goal: Extract news articles from websites
    backstory: |
      Expert at web scraping with years of experience
      extracting structured data from websites.
    tools:
      - scrape_page
      - extract_links
      - my_custom_tool  # Defined in tools.py

steps:
  - agent: scraper
    action: "Scrape news from {{url}}"
    expected_output: "List of article titles and summaries"

tools.py Example

"""Custom tools for this recipe."""

def my_custom_tool(url: str) -> str:
    """A custom tool for processing URLs."""
    return f"Processed: {url}"

# Dynamic variables
DEFAULT_URL = "https://news.example.com"

The metadata block is optional. It’s only needed if you want to publish your recipe to the registry.

Run Your Recipe

After creation, run your recipe:

praisonai recipe run my-recipe

Or with input:

praisonai recipe run my-recipe --input '{"url": "https://news.example.com"}'

Testing Your Recipe

After creating a recipe, test it with the workflow command:

1. Run with trace

   cd my-recipe
   praisonai workflow run agents.yaml --save
   
2. Judge the run

   praisonai recipe judge <trace-id> --context
   
3. Review scores

   The judge evaluates:

   • Task Achievement: Did agents complete their goals?
   • Context Flow: Did information pass between agents?
   • Output Quality: Was the output useful?

Use --save to capture traces, then recipe judge to get AI feedback on your recipe’s performance.

Next Steps

Optimize Recipe

Further improve your recipe with AI feedback

Recipe Registry

Share and discover recipes