The setting
connects guests with hosts who offer places to stay. is the host side of the marketplace, with tools, guidance and programs that help people and businesses list, price and run stays.
A general answer is fast, but an active stay needs the right next action.
The assistant must move property managers forward without making policy or safety decisions it cannot support.
Who you’d be doing this for
“The guest was already outside, and I got three articles instead of the next thing to do.”
Frederick Mueller · Property Manager · a character in this brief
Manages a portfolio of short-term rental listings and responds when guests report problems during a stay.
What is at stake
Property managers reopen active-stay conversations because general answers miss the immediate operational need. You must weigh faster next-action guidance against the risk of unsupported policy or safety advice.
Why it isn’t already fixed
Every obvious fix costs something else. That’s the part you’d have to decide.
- fast next actions vs. grounded guidance
- higher issue recall vs. stable routing queues
- host self-service vs. human safety review
- model usefulness vs. inference latency
Why AirBnB
Chat AI assistant conversations shape how property managers handle guest disruptions across their listing portfolios.
Written with these in mind
Not your kind of problem? 69 more at AirBnB, or browse every organization.
Where the organization context comes fromThe postings this brief was written from, and the reporting read before it.
The organization context comes from public information. The situation and characters are written for the brief.
Job postings it was written from
Public descriptions of the work at AirBnB. They are listed as sources, not as openings. The lines under a posting are its own words, where it meets this brief.
- Senior Machine Learning Engineer, Assistance Engineering (opens in a new tab)
- The Community Support Products (CSP) Machine Learning team is the core team responsible for driving CSxAI (Customer Support x Artificial Intelligence) initiatives by adopting the Generative AI technologies to enable an intelligent, scalable and exceptional service experience.
- Senior Machine Learning Engineer, Payments (opens in a new tab)
- At the Payments modeling team, our goal is to empower the mission by introducing intelligences and personalizations that optimize Airbnb’s massive daily transaction volume to best collect payments from guests, distribute payouts to hosts while preventing fraudulent transactions from happening.
- Machine Learning Engineer, Assistance Engineering (opens in a new tab)
- We are responsible for developing the Chat AI assistant, Voice AI Assistant and more!
- Senior Staff Machine Learning Engineer, Trust (opens in a new tab)
- We constantly work to fight against online fraud (such as monetary loss, compromised accounts, spam and scam in messages, fake inventory, etc.) as well as offline fraud (theft, property damage, personal safety, etc.).
- We also work on onboarding and screening of users, and think about complex topics like identity and reputation to ensure that every interaction with Airbnb helps build trust in us and our community.
- Staff Data Scientist, Guest & Host (opens in a new tab)
- Your work will help enable the next generation of AI-powered search experiences at Airbnb
- You will join the Guest and Host Data Science organization, which powers products and data-driven decisions over Airbnb’s marketplace of Guest and Hosts.
This is the setup. The work is inside.
Running it puts you in the room: the full situation and its constraints, stakeholders who push back in their own words, and the decisions that are yours to make. What you produce becomes a Day One Plan — work you can show someone instead of describing.
Where similar work appears
Other live briefs connected to this one, and what connects them.
Similar problems at other organizations
Like this one, each of these turns on deciding on evidence that's still thin.
In a sample of 2,000 service conversations, 18% of customers returned within 48 hours, but only some still needed help.
You must weigh a useful signal of unfinished service against unnecessary follow-ups and labels that confuse a new question with an old problem.
Routine order-status conversations still consume human capacity despite approved answers being available.
You have to weigh broader autonomous resolution against the confidence needed to keep replies within approved language.
Engineers keep rebuilding the same deployment, trace and feature-flag context each time a rule-matching failure comes back.
You have to decide at which step the AI's brief ends and an engineer's own reading of the traces and flag history begins.
The same setting, from another role
Each is set around AirBnB’s Airbnb Hosting, written for a different role. They’re separate briefs, not the same scenario.
New co-hosts are completing onboarding but still asking peers how to handle their first guest handoffs.
You have to weigh faster confidence for new co-hosts against the time and boundaries of experienced hosts.
Property managers are leaving fee sessions with conflicting answers for the owners they represent.
You must weigh open host conversation against a boundary that prevents pricing guidance.
Property managers are repeating registration questions because useful local guidance is buried in a crowded discussion.
You have to protect open conversation while making the verified next step easy to find.
Other problems with a similar purpose
In each of these, as in this one, the aim is to build machine-learning systems that earn trust by staying explainable where their errors carry real consequences.
An audit found sensitive fields in 7% of shared artifacts that manual review missed, and the classifiers disagree on the edge cases.
You have to build evidence for a production commitment you cannot easily reverse.
One threshold sends very different numbers of drivers into coaching in each region, and reviewers there agree less often.
You have to balance fair treatment of drivers against enough coverage to improve coaching.
In testing, the new service looks coherent, but reviewers disagree on whether its cited evidence is enough for high-impact cases.
You have to weigh consistency gains against a wrong call that is costly to unwind.
