Launch HN: TeamOut (YC W22) – AI agent for planning company events

Source: Hacker News

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.
3. Use tools like Airbnb that are not designed for group logistics or meeting space.

Even for 30–50 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 encountered this while organizing retreats at a previous company. As an AI researcher at IBM working on NLP and machine learning systems, I saw the problem not as a marketplace gap but as a reasoning and state‑management challenge. With large language models improving at multi‑step reasoning and tool use, automating the coordination layer itself became realistic.

Solution

TeamOut’s 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.

Tools and Responsibilities

• Venue search and filtering – retrieve candidates from a database of >10,000 venues using vector similarity search; hard constraints (capacity, dates) are applied first, then results are ranked.
• Cost estimations – accommodation + flights.
• Budget comparisons – evaluate options against the team’s budget.
• Quote and outreach flows – automate vendor communication.
• Communication channel – chat interface for the user to interact with the system.

Interface

A split layout shows the conversation on the left and structured results on the right. As the plan is refined in chat, the event updates in real time, enabling an iterative workflow rather than a static search experience.

Key Differentiator

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 intended to replace human planners for very large or highly customized events.

Demo: https://www.youtube.com/watch?v=QVyc-x-isjI
Live product (no signup required): https://app.teamout.com/ai

Business Model

TeamOut earns commissions on venue bookings. Exploration and planning are free for teams.

Call for Feedback

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 and dive deep into architecture, trade‑offs, and lessons learned.

We’d really appreciate your candid feedback.