Here’s a demo: https://www.youtube.com/watch?v=QVyc-x-isjI. The product is live at https://app.teamout.com/ai and does not require signup.
We went through YC in 2022 but did not launch on HN at the time. Back then, the product was more traditional, closer to an Airbnb-style search marketplace. Over the past two years, after helping organize more than 1,200 events, we rebuilt the core system around an agent architecture that directly manages the planning process. With this new version live, it felt like the right moment to share it here since it represents a fundamentally different approach to planning events.
The problem: Planning a company retreat usually means choosing between three imperfect options: (1) Hire an event planner and pay significant fees and venue markups; (2) Do it yourself and spend dozens of hours on research, emails, and negotiation; or (3) Use tools like Airbnb that are not designed for group logistics or meeting space.
The difficulty is not just finding a venue. Even for 30 to 50 people, planning turns into weeks of back-and-forth emails for quotes, comparing inconsistent pricing across PDFs, and tracking budgets in spreadsheets. It becomes an ongoing coordination problem with evolving constraints and slow, asynchronous vendor responses. Most existing software is form-driven, but the real workflow is conversational and stateful.
Offsites are expensive and high stakes. A single event can represent a significant chunk of a team’s annual budget, and mistakes show up directly as cost overruns or poor experiences. Founders and operators often end up spending time on event logistics instead of their actual work.
I ran into this while organizing retreats at a previous company. Before TeamOut, I worked as an AI researcher at IBM on NLP and machine learning systems. Sitting inside long email threads and cost spreadsheets, it did not look like a marketplace gap to me. It looked like a reasoning and state management problem. As large language models improved at multi-step reasoning and tool use, it became realistic to automate the coordination layer itself.
Our Solution: The core agent relies on a combination of models such as Gemini, Claude, and GPT. A central LLM-based agent maintains planning context across turns and decides which specialized tool to call next. Each tool has a specific responsibility: - Venue search and filtering - Cost estimations (accommodation + flights) - Budget comparisons - Quote and outreach flows - Communication tool with our team
For venue recommendations across more than 10,000 venues, we do not rely purely on the language model. We embed both user requirements and venues into vector representations and retrieve candidates using similarity search. Hard constraints such as capacity and dates are applied first, and results are ranked before being presented.
On the interface side, we use a split layout: conversation on the left and structured results on the right. As you refine the plan in chat, the event updates in real time, allowing an iterative workflow rather than a static search experience.
What is different is that we treat event planning as a stateful coordination problem rather than a one-shot search query. The agent orchestrates tools, manages evolving constraints, and surfaces trade-offs explicitly. It does not invent venues or fabricate pricing, and it is not designed to replace human planners for very large or highly customized events.
We make money from commissions on venue bookings. It is free for teams to explore options and plan. If you’ve organized an offsite or large meetup before, I’d genuinely value your perspective. Where would you expect this to fail? What edge cases are we underestimating? Where wouldn’t you trust an agent to handle the details?
My engineering team and I will be here all day to answer questions, happy to go deep on architecture, tradeoffs, and lessons learned. We’d really appreciate your candid feedback.
1. Hoofddorp, Noord-Holland, Netherlands (actually ok location) 2. Marysville, Ohio, United States 3. Lisboa, Portugal 4. Nashville, Tennessee, United States 5. Kenmore, Washington, United States 6. Golden, Colorado, United States
I would expect there to be some reviewer agent that ensures that all found locations are at least within the same country?
We are actually pushing an update on that, we want to make the distinctions between Exact Matches (respecting destination criteria) and Non Exaft Matches , that. are suggestions.
The below options were suggestions (because we have limited supply in Netherlands ) but it not clear at all for the user:
2. Marysville, Ohio, United States 3. Lisboa, Portugal 4. Nashville, Tennessee, United States 5. Kenmore, Washington, United States 6. Golden, Colorado, United States
Thank you for your help
"I want to have a two day offsite for a team of 12 in Cambridge in April."
It then started pulling up results in Cambridge UK. I meant Massachusetts. I didn't say that in the prompt, but I figured since there are two equally famous Cambridges, it would ask me for clarification.
I redid it specifying Massachusetts and it worked pretty well (although all the options it found were about double the price of what we actually booked).
An interesting idea!
BTW I didn't continue, but I assume you manage the whole booking process? How do deal with questions from the venue and other human in the loop issues?
Another challenge is travel, e.g: scheduling an event in Europe for a distributed team of U.S. people during bad weather leads to people stranded at airports, missing the event.
I think this is a great idea, but I am surprised to learn that organizers are spending most of their time communicating with hundreds of venues. Once you have a location and budget, finding a venue is straightforward.
The algorithm is quite smart about that because it has legacy data from ~1500 events. IT has been shown a lot of example of" When a team is located there, they have VISA issues --> they should actually go there because it worked in the past for XYZ client"
For example the algorithm will know that Dominican Republic is usually VISA frienly and can send larger groups there etc.
For the second part: Finding a venue with the requirements is hard, our clients really have a pain point, but what it is even harder tis to agree on terms, prices, food, meeting space, transportation coordination etc, it is a logistical nigthhmare
Huh this surprised me as a forgone opportunity.
I heard second-hand about the process for organizing our last offsite. Searching for venues was not the time-consuming part.
The time-consuming part was actually engaging with the venues to confirm specific details not available online. Our teammate who did this engaged with _hundreds_ of venues. It was a lot of work on their part ... and probably not the most fun part of their job.
That seems like an ideal agent scenario?
What is time consuming is the communication with the venue to agree on "terms" , this is exactly why if you click on "Request Quote" you will have a real quote process with the venue that will share all the details and cost estimate with the client , we also offer to talk directly with the venue manager to talk about the final details and close the deal, that is where the value is at --> end to end booking process (not just aggregating results)
We do support day event and day activities and we plug this supply in the AI in the coming weeks to make the supply stronger and cover more usecases
Haven't organized large meetups, but for regular enterprise companies this could be a difficult to buy decision, because you have ChatGPT + bunch of connectors which can get company policies.
This could be good idea for event companies who regularly schedule things, but even for them, probably difficult to justify the value when you have access to ChatGPT and other connectors
For the second part, ChatGPT only could potentially aggregated options but It will not get quotes, booking etc, it will stay shallow. The value here is that it gives you good venues vetted by our network but you can also book them and continue organizing your event with process and credibility of a real company.
A retreat is $$$ expensive, you need a real company in the background to insure the booking and finance safety, ChatGPT won't do that.
It’d be cool to offer one-off event suggestions, but I understand that’s probably not as easily monetizable.
Right now the AI flow is optimized for multi-day events where people stay at least one night, like offsites, retreats, and conferences. When you shifted it to a same-day “what should we do tonight after work” use case, you basically stepped outside its current planning model, so the refusal you saw is on us.
We do support day events and activities on the supply side, but they are not yet fully integrated into the AI agent flow. Over the next few weeks, we are plugging that inventory into the system so it can handle more one-off and shorter formats.
Monetization is part of the equation, but it is also a product focus decision. We started with the higher-friction, higher-stakes planning problem. Expanding into lighter-weight, single-day coordination is definitely interesting and your comment is a good nudge in that direction.
Booking.com and similar moving into this space with their own generic AI tool.
Or even Gemini improving their UI so it presents search results more neatly.
Important distinction: we are not in the same segment as Booking.com. Most hotel platforms support small group bookings, usually up to around 10 rooms. We operate in MICE, where you are negotiating room blocks, meeting space, F&B minimums, contracts, and attrition clauses. That is a very different workflow from self-serve booking.
LLMs can make search look nicer, but getting an actual group quote still requires going through property sales teams and contracts. That is operational and relationship-driven, not just a UI problem.
Over 1,200+ events, we have also built proprietary data around pricing patterns, responsiveness, and contract structures. That is not publicly accessible today.
Also our proprietary data is unique to us for now.
How would you make it more defensive? I take any idea
Globally, meetings, incentives, conferences, events, and group travel together represent a 500B+ market all in. Almost every mid-sized or large US company runs some form of in-person event each year, whether that is a retreat, sales kickoff, or team meetup. Since COVID, distributed teams have made these gatherings more important, not less.
Corporate offsites are just our entry point because the pain is clear and budgets are structured. Almost every mid-sized or large company runs in-person events every year, and since COVID those gatherings have become more important for distributed teams.
Long term, we are not limiting this to corporate. The underlying problem is group coordination with real budgets, contracts, and logistics. That applies to associations, communities, weddings, large friend trips, and more. Our ambition is to expand into every type of group travel and event where planning is complex and high stakes.
Filtering UI: Also agree. We leaned heavily into conversation because planning is iterative and constraint-driven, but that doesn’t mean everything should require typing. A hybrid approach (chat + explicit filters/sliders/toggles) probably makes more sense for power users. We already have structured results on the right adding faster, direct manipulation controls there is a logical next step.
Appreciate you calling it out. If you were using this for real, what filters would you expect to be immediately clickable instead of typed?
Aren't you scared that we will have 2 concurent ways to control the experience:
- Chat - Buttons
We may have the syndrom "too many cooks in the kitchen" don't you think?
> (2022)
Has there been a rebrand as of late? What was the product pitch before that? I guess "AI for planning company retreats" (and possibly SaaS for company retreats before that)
This capacity to pivot into these buzzwords shows that at least sometimes they are more phenomenons with marketing (or at least UX) definitions rather than technological ones.
On TAM, corporate retreats and offsites in the US alone represent roughly a 500M+ venue booking market by our estimates, and that is just one slice, not counting flights, activities, or international events. Since COVID, distributed teams have made in-person gatherings more important, not less. Almost every company does some form of corporate event, whether it is an annual retreat, sales kickoff, leadership offsite, or team meetup.
Almost all US company do corporate event and retreats, every year.
The bigger bet for us is not just that events are a sizable market. It is that this is exactly the kind of messy, coordination-heavy workflow that AI can now handle. Two years ago this would not have worked. With current multi-step reasoning and tool use, it finally does.
If we were just a ChatGPT wrapper with a Booking API, we’d be already dead.
Our value isn’t the interface it’s the supply. We have direct relationships with hotels that log in daily to quote, adjust pricing, negotiate, and close deals. That’s not something you get with an API key.
You can vibe-code an Airbnb clone in an afternoon. Without supply, contracts, and operational execution, it’s useless. Marketplace take time to build network effect
LLMs can display data. They can’t negotiate, contract, invoice, manage edge cases, or execute group bookings end-to-end.
We’ll distribute via all major LLMs. But the defensibility is in our network and operations and date, not the UI that everyone could replicate
no problem for me!