Airial Travel - Plan dream trips instantly from ideas or travel videos
by•
Just imagine your trip and Airial it! Simply describe your trip to Airial, or drop in your favourite TikToks / IG and see your dream trip come to life instantly. Airial's one-of-a-kind AI picks out every last detail so that you can start packing, stress-free!
Replies
Hey guys,
Just in time! Using it to plan our spring break in Spain, love how it suggested watching La Liga game :).
Airial Travel
@vkullu Glad that you're using Airial to plan your next trip. Precisely the magic of Airial is that it can plan trips to the last detail to anywhere in the world tailored for your specific preferences by tying together travel APIs, LLM world knowledge and our reasoning abilities seamlessly. And all of this happens in seconds! Happy traveling! :)
Airial Travel
Thanks for the continued support everyone. To share some learning from my experience I'll post thoughts about two questions which I often get from founders looking to build something new with Gen AI or integrate Gen AI into their existing products. Hopefully it adds some value to everyone here who is building with AI. This comment poses and answers the first question. All civil debate is appreciated, feel free to agree or disagree in the comments.
Will foundational models be able do everything of commercial value in a few years' time?
The generative AI revolution is one of most significant revolutions in all of human history. It is comparable to the advent of electricity or the internet. However, it is quite absurd to think that foundational models will be able to capture all commercial value soon or to think that ChatGPT is the only app you will ever need. Ironically, and with no shade intended, this question nearly always comes from people who don't have much experience working first-hand in AI research or applied AI. Those who have worked in AI have seen first hand just how much there is still to be solved, regardless of whether or not they believe in some notion of AGI emerging in a few years' time.
I'm going to answer this from the perspective of my field of research, Reliable Deep Learning. This is one of the most important fields of AI research today since this is where all deep learning models really struggle. Every commercially engineered system to ever exist consists of several modules each of which has to highly reliable, at least under a set of assumptions. The fundamental challenge of building with Generative AI is that of building with a tool that is in many ways far more powerful than anything before it but is unreliable.
Reliability of Deep Learning models is quite simply unsolved although there has been a lot of incredible research work around mitigating or reducing the unreliability of Neural Networks. There are four fundamental unsolved problems in Reliable Deep Learning research:
Miscalibration: Neural networks are overconfident on their mistakes. As state-of-the-art models have become more accurate, they have actually become quantifiably more overconfident on their mistakes.
Out-of-distribution examples: Neural networks are prone to mistakes, and overconfident ones, when they encounter data which is unlike the distribution of the data from their training dataset.
Adversarial Examples: Neural networks are susceptible to adversarial attacks on carefully crafted examples which are meant to deceive them. Adversarial examples crafted for one model are often transferrable to other models trained on the same dataset, which opens up the possibility of blackbox adversarial attacks.
Lack of explainability: Decisions made by Neural Networks are largely black boxes, unexplainable. This practically makes model trustworthiness even worse, since they are confidently wrong without any justification.
The Generative AI revolution has not addressed any of these. The incredible success of LLMs is about phenomenal engineering achievement, scale, training tricks, some new loss functions and even some smart architectural improvements such as sub-quadratic attention mechanisms, but it hasn't fundamentally changed the transformer architecture which continues to suffer from these unsolved problems.
To conclude, just from the perspective of reliability there is a lot to be solved. All commercial value hinges on reliability.
Airial Travel
Here is the second question, building on the first one from my previous comment.
What will remain to be solved as foundational models improve?
In the context of agentic AI, apart from reliability, there are three other problems that are seminal to building a useful solution.
Contextualization: Getting access to and understanding information from the environment in the context of the user query.
Reasoning: Thinking through the user query to understand the actions that need to be taken.
Agency: The final step of creating the action in a format which can be plugged into the system.
In the context of engineering, there is plenty to be solved in terms of optimizing cost, latency and accuracy in each of these steps. No complex task that a human agent does can be achieved by just writing one big prompt with the best model available. Such a solution will be infeasible by just inspecting the cost of the attention mechanism, even ignoring the huge accuracy barrier. The RAG approach to reduce this cost has several limitations of its own within its similarity-based lookup mechanism and does not suffice to fix the need for huge prompts for a single-agent system.
Some other engineering challenges to be solved within multi-agent systems are:
Streaming responses through a system of agents
Parallelizing independent or conditionally independent computation when possible
Explaining and clarifying responses with the user to seek clarification for open-ended choices.
Trading off clarification and turnaround time: How much to clarify before kicking off the main agentic computation?
Interfacing with APIs: How can we integrate with a collection of APIs each of which has their own signature and can return unavailable or unexpected responses which give rise to further challenges to solve.
All the best for the launch @archit_karandikar & @sanjeev_shenoy1 !
Airial Travel
@archit_karandikar @parekh_tanmay Thanks Tanmay! We're excited to see the kind of trips people try. Do try it out for your next trip and we would love to get your feedback!
Surgeflow
🎉 Huge congrats to Archit @archit_karandikar , Sanjeev @sanjeev_shenoy1 , and the Airial team on the launch! As someone who’s spent hours copying TikTok travel ideas into spreadsheets, your “Reels to Itineraries” feature is a game-changer! 🌟 Love how AI handles nitty-gritty details (transit logic ✈️🚂!) while keeping plans flexible via chat.
🚀 Quick idea: A “Export to Google Calendar/TripIt” button would make booking even smoother! Any plans for real-time collaboration? Dying to plan group trips hassle-free. Keep crushing it! 👏
Airial Travel
@rocsheh Exactly! We know that discovery and inspiration are the parts of travel planning that are actually enjoyable and we want people to continue doing that. What's annoying today is taking these and figuring out all the details- transits and transfers being the first one!
Great idea! Export to Google calendar would be extremely convenient indeed!
Collaborative trip planning is something we felt is a must and so we have it fully working at launch! Once a trip is created, you can click on the Share button on the header and that lets you invite people to collaborate!
Cursor
I really like how Airial Travel has reimagined travel using a Gen AI product rather than just adding a chatbot onto the existing interface. As you start using Airial, you will see how thoughtfully it is designed to make the planning experience easy at every stage.
Airial Travel
@benln Thanks for the kind words and for hunting our launch, Ben!
Treblle
Congratulations on the launch @sanjeev_shenoy1
Airial Travel
@savan_kharod1 Thank you so much! :)
Excited about AI-driven trip planning! 😄
Airial Travel
@shenjun So glad you found it helpful! We've put a lot of love into making the AI think more like a human. Our custom-built reasoning engine is designed to plan your trip the way a real person would—carefully connecting all the dots to create an experience that just makes sense.
👍 From the software interface and its overall interaction, I can see that your team has put in a lot of effort compared to using ChatGPT for full text generation. Through your tool, people can have a more intuitive view of the entire itinerary. I have also consulted some human travel planners in the past, but often recommend a bunch of hotels that are not cost-effective just to make money. Using AI like this is indeed better.
Airial Travel
@shenjun Indeed, there is a lot of scope of AI to make a complex optimization task like travel much better. In 5 years' time, we believe that this AI native approach will be the norm for booking travel. People will not go back to the current way of booking once they are used to ultra-convenient AI-powered booking mechanisms.
I am very passionate about being from the PNW. I was looking to plan a trip to Portland and was so Impressed at how local, specialized and niche the trip was based on my desires. It included some things I love about Portland with many ideas I hadn’t thought of. I was impressed at how the trip represented exactly what I would want to do. Super impressed!
Airial Travel
@kieran_mcmonagle Thank you so much! Haha yes, finding hidden gems is something we've invested in quite significantly
Congrats on the launch! 🎉
Seriously, I've been using this thing since the beta and it's been awesome for booking trips. It's a lifesaver, especially with bigger groups – trying to plan that stuff in Google Docs is just the worst. Being able to throw in extra stops and mess with the plan is totally perfect. Plus, it's super fast, and having all my flights and hotels in one spot? Game changer.
Airial Travel
@vinookuri Thanks a lot Vinay. Testimonial from regular users are the best validation for builders.
From finding the best flight and hotel deals to suggesting top attractions and local experiences, everything was streamlined and user-friendly with clean interface.
Airial Travel
@shardul_bargale Thanks for the kind words! We appreciate your feedback. We've spent a lot of time designing the interface so that the planning process is as easy as possible. Of course, there is a lot more still to be done in our quest to reinvent travel planning with Gen AI.