Research Agent
Pulls LLM-ready context from the web, folds in live weather so rainy days become indoor days, and checks real-time exchange rates.
- web_search
- get_weather
- get_exchange_rate
Multi-agent · Human-in-the-loop
Plan a trip worth taking.
Our agents research your destination, draft a day-by-day itinerary with a budget breakdown, then pause for your approval. Approve, reject, or refine — you stay in control.
- Live research & weather-aware days
- Transparent budget allocation
- Review gate before anything is final
- Interactive route maps with distance & time estimates
Start a plan
Your plan
- Researching
- Planning
- Your review
- Finalizing
- Finalized
Awaiting your review
The draft below is ready. Optionally pick a flight or hotel, then approve — or skip to keep sightseeing only.
A pipeline you can trust
Five focused nodes. One clear flow. You sit in the loop.
1
Orchestrate
Validates your request and frames the task for the agents.
2
Research
Web search and live weather gather grounded context.
3
Plan
Drafts day-by-day with a transparent budget split.
4
Your gate
Approve, modify, or reject. Nothing finalizes without you.
5
Finalize
Locks in your approved itinerary, ready to go.
Meet the agents
Planner Agent
Turns findings and budget into concrete days, complete with smart packing lists dynamically generated for your trip duration and interests.
- allocate_budget
- build_day_schedule
- generate_packing_list
Human Gate
A real pause in the graph (LangGraph interrupt) that resumes exactly where it stopped — with your decision.
- approve
- modify
- reject
Finalize Agent
Expands your approved draft into a rich itinerary, then geocodes every stop and computes walking/driving legs on an interactive map.
- build_route_map
- leg time estimates
- total km traveled