> ## 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.

# Planning Agent

> Learn how to create AI agents for trip planning and itinerary generation.

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
flowchart LR
    In[Travel Request] --> Agent[Planning Agent]
    Agent --> Out[Itinerary]
    
    style In fill:#8B0000,color:#fff
    style Agent fill:#2E8B57,color:#fff
    style Out fill:#8B0000,color:#fff
```

Travel planning agent with web search for finding flights, hotels, and creating itineraries.

***

## Simple

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

### Workflow

1. Receive travel request
2. Search for flights and hotels
3. Generate detailed itinerary

### 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="TravelPlanner",
    instructions="You are a travel planning agent. Create detailed itineraries.",
    tools=[duckduckgo]
)

result = agent.start("Plan a 3-day trip to Tokyo")
print(result)
```

### Run — CLI

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
praisonai "Plan a weekend trip to Paris" --web-search
```

### Run — agents.yaml

```yaml theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
framework: praisonai
topic: Travel Planning
roles:
  travel_planner:
    role: Travel Planning Specialist
    goal: Create comprehensive travel plans
    backstory: You are an expert travel planner
    tools:
      - duckduckgo
    tasks:
      plan_trip:
        description: Plan a 3-day trip to Tokyo
        expected_output: A detailed itinerary
```

```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="TravelPlanner",
    instructions="You are a travel planning 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": "Plan a weekend getaway to Barcelona"}'
```

***

## Advanced Workflow (All Features)

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

### Workflow

1. Initialize session for trip tracking
2. Configure SQLite persistence for travel history
3. Search and plan with structured output
4. Store itinerary in memory for modifications
5. Resume session for trip updates

### 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

# Structured output schema
class Itinerary(BaseModel):
    destination: str
    duration: str
    daily_plans: list[str]
    estimated_cost: str
    recommendations: list[str]

# Create session for trip tracking
session = Session(session_id="trip-001", user_id="user-1")

# Agent with memory and tools
agent = Agent(
    name="TravelPlanner",
    instructions="Create structured travel itineraries.",
    tools=[duckduckgo],
    memory=True
)

# Task with structured output
task = Task(
    description="Plan a 3-day trip to Tokyo with budget",
    expected_output="Structured itinerary",
    agent=agent,
    output_pydantic=Itinerary
)

# Run with SQLite persistence
agents = AgentTeam(
    agents=[agent],
    tasks=[task],
    memory=True
)

result = agents.start()
print(result)

# Resume later
session2 = Session(session_id="trip-001", user_id="user-1")
history = session2.search_memory("Tokyo")
```

### Run — CLI

```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
praisonai "Plan a trip to Tokyo" --web-search --memory --verbose
```

### Run — agents.yaml

```yaml theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
framework: praisonai
topic: Travel Planning
memory: true
memory_config:
  provider: sqlite
  db_path: travel.db
roles:
  travel_planner:
    role: Travel Planning Specialist
    goal: Create structured travel plans
    backstory: You are an expert travel planner
    tools:
      - duckduckgo
    memory: true
    tasks:
      plan_trip:
        description: Plan a 3-day trip to Tokyo with budget
        expected_output: Structured itinerary
        output_json:
          destination: string
          duration: string
          daily_plans: array
          estimated_cost: string
          recommendations: array
```

```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="TravelPlanner",
    instructions="Create structured travel itineraries.",
    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": "Plan a trip to Paris", "session_id": "trip-001"}'
```

***

## Monitor / Verify

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

## Cleanup

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

## Features Demonstrated

| Feature           | Implementation              |
| ----------------- | --------------------------- |
| Workflow          | Multi-step travel planning  |
| DB Persistence    | SQLite via `memory_config`  |
| Observability     | `--verbose` flag            |
| Tools             | DuckDuckGo search           |
| Resumability      | `Session` with `session_id` |
| Structured Output | Pydantic `Itinerary` model  |

## Next Steps

* [Research Agent](/agents/research) for destination research
* [Shopping Agent](/agents/shopping) for price comparisons
* [Memory](/features/advanced-memory) for persistent context