AI Travel Planner

• Key points are in the visual diagram above.

Classic constraint-satisfaction + tool orchestration capstone. Proves you can coordinate APIs, maintain itinerary state, and handle user iteration.

A travel agent juggling six browser tabs who remembers you hate 6am flights and need vegetarian restaurants.

Scenario

Tokyo April, $3K, vegetarian. Agent finds HND flights $680, hotel Shinjuku $900, schedules Fushimi Inari day with metro times, highlights vegan ramen spots, total $2,840 with booking URLs.

Solution

In Capstone Projects, apply AI Travel Planner to this scenario: Tokyo April, $3K, vegetarian. Identify the inputs, run the technique, validate the output, and note one thing you would monitor in production.

Do this before moving to the next module — reading alone is not enough.

Open the Code Walkthrough below and run it locally. Change one parameter related to AI Travel Planner (e.g. model, temperature, top_k, or tool name), observe the difference in output, and write 2–3 sentences explaining what changed.

Highlighted lines show where AI Travel Planner happens in the code.

1# AI Travel Planner — minimal example2from openai import OpenAI3
4client = OpenAI()  # create API client5
6# Ask the model to explain this topic7response = client.chat.completions.create(  # core API call for AI Travel Planner8    model="gpt-4o-mini",9    messages=[10        {"role": "system", "content": "You explain ai travel planner clearly."},11        {"role": "user", "content": f"What is ai travel planner?"},12    ],13    temperature=0,14)15print(response.choices[0].message.content)  # show output for debugging

• Hallucinated confirmation numbers
• Ignoring transit time between activities
• No budget sum validation

Quick recap — the most important points from this module.