> ## Documentation Index
> Fetch the complete documentation index at: https://docs.praison.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Shopping Agent

> Learn how to create AI agents for price comparison and shopping assistance.

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
flowchart LR
    In[Product Query] --> Agent[Shopping Agent]
    Agent --> Out[Price Comparison]
    
    style In fill:#8B0000,color:#fff
    style Agent fill:#2E8B57,color:#fff
    style Out fill:#8B0000,color:#fff
```

Shopping assistant with web search for price comparison across stores.

***

## Simple

**Agents: 1** — Single agent with search tool handles product research and comparison.

### Workflow

1. Receive product query
2. Search multiple stores
3. Compare prices and generate report

### Setup

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
pip install praisonaiagents praisonai duckduckgo-search
export OPENAI_API_KEY="your-key"
```

### Run — Python

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent
from praisonaiagents import duckduckgo

agent = Agent(
    name="ShoppingAssistant",
    instructions="You are a shopping agent. Compare prices in table format.",
    tools=[duckduckgo]
)

result = agent.start("Compare prices for iPhone 16 Pro Max")
print(result)
```

### Run — CLI

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
praisonai "Compare MacBook Pro prices" --web-search
```

### Run — agents.yaml

```yaml theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
framework: praisonai
topic: Price Comparison
roles:
  shopping_assistant:
    role: Shopping Specialist
    goal: Find the best prices across stores
    backstory: You are an expert at finding deals
    tools:
      - duckduckgo
    tasks:
      compare_prices:
        description: Compare prices for iPhone 16 Pro Max
        expected_output: A price comparison table
```

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
praisonai agents.yaml
```

### Serve API

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent
from praisonaiagents import duckduckgo

agent = Agent(
    name="ShoppingAssistant",
    instructions="You are a shopping agent.",
    tools=[duckduckgo]
)

agent.launch(port=8080)
```

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
curl -X POST http://localhost:8080/chat \
  -H "Content-Type: application/json" \
  -d '{"message": "Find best deals on Sony headphones"}'
```

***

## Advanced Workflow (All Features)

**Agents: 1** — Single agent with memory, persistence, structured output, and session resumability.

### Workflow

1. Initialize session for shopping history
2. Configure SQLite persistence for price tracking
3. Search and compare with structured output
4. Store results in memory for price alerts
5. Resume session for ongoing comparisons

### Setup

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
pip install praisonaiagents praisonai duckduckgo-search pydantic
export OPENAI_API_KEY="your-key"
```

### Run — Python

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent, Task, AgentTeam, Session
from praisonaiagents import duckduckgo
from pydantic import BaseModel

class PriceComparison(BaseModel):
    product: str
    stores: list[str]
    prices: list[str]
    best_deal: str
    recommendation: str

session = Session(session_id="shop-001", user_id="user-1")

agent = Agent(
    name="ShoppingAssistant",
    instructions="Compare prices and return structured results.",
    tools=[duckduckgo],
    memory=True
)

task = Task(
    description="Compare iPhone 16 Pro Max prices across stores",
    expected_output="Structured price comparison",
    agent=agent,
    output_pydantic=PriceComparison
)

agents = AgentTeam(
    agents=[agent],
    tasks=[task],
    memory=True
)

result = agents.start()
print(result)
```

### Run — CLI

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
praisonai "Compare iPhone prices" --web-search --memory --verbose
```

### Run — agents.yaml

```yaml theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
framework: praisonai
topic: Price Comparison
memory: true
memory_config:
  provider: sqlite
  db_path: shopping.db
roles:
  shopping_assistant:
    role: Shopping Specialist
    goal: Find best prices with structured output
    backstory: You are an expert at finding deals
    tools:
      - duckduckgo
    memory: true
    tasks:
      compare_prices:
        description: Compare iPhone 16 Pro Max prices
        expected_output: Structured price comparison
        output_json:
          product: string
          stores: array
          prices: array
          best_deal: string
          recommendation: string
```

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
praisonai agents.yaml --verbose
```

### Serve API

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent
from praisonaiagents import duckduckgo

agent = Agent(
    name="ShoppingAssistant",
    instructions="Compare prices and return structured results.",
    tools=[duckduckgo],
    memory=True
)

agent.launch(port=8080)
```

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
curl -X POST http://localhost:8080/chat \
  -H "Content-Type: application/json" \
  -d '{"message": "Compare laptop prices", "session_id": "shop-001"}'
```

***

## Monitor / Verify

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
praisonai "test shopping" --web-search --verbose
```

## Cleanup

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
rm -f shopping.db
```

## Features Demonstrated

| Feature           | Implementation                   |
| ----------------- | -------------------------------- |
| Workflow          | Multi-store price comparison     |
| DB Persistence    | SQLite via `memory_config`       |
| Observability     | `--verbose` flag                 |
| Tools             | DuckDuckGo search                |
| Resumability      | `Session` with `session_id`      |
| Structured Output | Pydantic `PriceComparison` model |

## Next Steps

* [Recommendation Agent](/agents/recommendation) for personalized suggestions
* [Research Agent](/agents/research) for product research
* [Memory](/features/advanced-memory) for persistent context