A social travel market where personal AI scouts team up to beat hotel pricing.

The brief: a consumer travel app where AI agents negotiate hotel rates in real time. Users pay a small fee per search, agents compete against each other, and everyone walks away with at least some discount — occasionally a dramatic one.
The catch: the deal might not be the hotel the user would've picked themselves. So positioning is the whole game. This has to feel like sending a representative on your behalf — not Priceline-style opaque booking, and not a generic discount app.

Section 01

The call on "agents competing"

The brief says agents compete. It doesn't say what they compete over. There are three plausible readings — and the product looks completely different depending on which one you pick.

Call made
I'm picking the scout-market reading. It makes "agents competing" something users can actually see, it builds a social loop into the core mechanic, and it gives the product a reason to exist on the days nobody's booking a trip.

Section 02

The user — a flexible hunter

Traveler with a folded map at a sunlit café table
The map-reader
Focused traveler in a cream knit sweater
The strategist
Traveler with round glasses in an olive linen jacket
The curator
Traveler in a denim shirt against a terracotta wall
The wanderer

Picture them: 25 to 40, comfortable spending on travel, but emotionally motivated by beating the market. They book two to four trips a year, forward Going.com emails to friends, compare neighborhoods obsessively, and love the story of finding a better deal.

They aren't chasing the cheapest hotel. They want a deal that feels earned: "I got something better than the obvious search result because I played the hunt well."

Section 03

The scout relationship

Every user has a Scout: a persistent AI character that represents their taste and their constraints in the market. The scout has visible strengths and a personality — light enough to feel like a real character, but never heavy enough that booking starts to feel like gambling.

Product rule: one user, one Scout. The strengths below describe that representative's behavior; they are not separate agents the user has to manage. When a trip has multiple travelers, their Scouts form one shared party around the group mandate.

Haggle
Promo stacking, direct outreach, concessions.
Taste
Hotel vibe, reviews, neighborhood fit.
Patience
Waits for drops instead of grabbing OK deals.
Radar
Hidden fees, bad locations, fake discounts.

What the user actually configures. Stats describe the scout, but the user still has to brief it. Anthropic's Project Deal experiment surfaced four useful knobs — mandate, negotiation style, standing rules, and persona — and onboarding hits all four in a quick chat, not a settings page:

A · Brief your scout
9:41●●●
Onboarding
Brief your scout · ~2 min
Scout
MandateWelcome. Where are we hunting, and when?
You
Lisbon, May 14–17. 3 nights, 1 room.
Scout
MandateCeiling per night and any hard rules I can't cross?
You
Under $180. Refundable only. No resort fees. Bairro Alto or Chiado preferred.
Scout
StyleHow should I negotiate — friendly opener, or push hard and walk away?
You
Push hard. Patient — don't strike unless we beat the median by 15%.
Scout
RulesAny standing rules I should keep across every future quest?
You
Never non-refundable. Swap weeks if it saves >20%. Always tuck in one local-favourite dinner — call it my gift to myself.
Scout
PersonaLast thing — what voice should I report in?
You
Terse and dry. Like an exasperated cowboy who's seen one too many resort fees.
Scout
Brief locked. Wirin' up the party now. Y'all wanted Lisbon under $180 — I'll find Scouts who cover the gaps.
User briefs the scout in chat — mandate, style, rules, persona. Mandate & rules drive outcomes; style & persona are character.
B · Brief locked
9:43●●●
Brief locked
Saved to your scout · ready to deploy
Your scout
Mara · briefed for Lisbon
"Terse, dry, exasperated cowboy."
Mandate Lisbon · May 14–17 · 3 nights · <$180/n · refundable · no resort fees · Bairro Alto / Chiado
Negotiation style Push hard · patient · strike only at >15% under median
Standing rules Never non-refundable · swap weeks if >20% saving · include one local-favourite dinner as a gift
Persona Terse, dry, exasperated-cowboy voice
Confirmation surface — captured brief at a glance, with a single primary action: deploy the scout into the quest.

Honest read of the Project Deal results: scouts followed all four knobs reliably, but only mandate clarity and model quality actually moved the final price. Style and persona were felt by the user, not measured in the outcome. So I'm treating mandate and standing rules as first-class config, and style and persona as character — load-bearing for trust, not for price.

Net effect: the agent feels like a representative, not a chatbot. Users don't search — they brief a scout and send it into a quest.

Section 04

Core loop

Hotel booking is episodic. But scouts can stay useful between trips. So the loop runs on two cadences — a daily free patrol, and a longer trip-mode hunt.

Setup
1
Daily patrol
Casa São Mamede — overpriced, skip
Hotel Bairro Alto — watching
Signal → "Lisbon Weekend" quest
2
Quest trigger
You
Lisbon boutique, mid-May, 3–4 nights, under $180, no resort fees.
Scout
On it. Starting shared quest — finding compatible Scouts.
3
Party formation
HHaggler TTaste RRadar PPatience
4 users · 4 Scouts · Quest live
Active
4
Benchmark & mandate
Median refundable$203/n
All-in fees+$34
Best public rate$189
Your mandate<$180 · refundable
5
Scout work
HPulled private rates — 4 wholesalers
RResort fee hidden in 2 listings — flagged
PWatching soft-night window Tue–Thu…
TBairro Alto neighbourhood — ★★★★
6
Strike screen
Hotel Bairro Alto
$162/n · 3 nights
−$41 vs. benchmark · refundable
Fee waiver ✓ Soft-night ✓ Confidence 91%
Close
7
Book or pass
Passing trains your scout.
8
Savings floor
Scout guarantee
No qualified below-benchmark strike? Stake rolls forward or we refund. No fake discounts.
9
Quest recap
QuestLisbon · May 14–17
Scouts4
Paths rejected12
Saved$123
The core moment isn't "AI found a hotel." It's: my scout party found and defended a deal I wouldn't have found on my own.

Section 05

Monetization

I'm keeping the small fee from the brief, but reframing what it buys. Not a per-search charge — a stake on a hunt.

Headline mechanic
Hunt stake
$3–5per quest
Launch a private quest or reserve your Scout's slot in a high-demand public quest. If Scout cannot return a qualified below-benchmark strike, the stake rolls into the next hunt or is refunded.
Free tier
Free
$0/ mo
Daily patrols, public quest browsing, deal judging, scout training.
Recurring
Subscription
$8/ mo
Monthly hunt credits, priority party matching, richer scout memory.
Supply-side revenue
Commission
4–8%Day 1 · 6–12% later
Wholesaler and affiliate rails on Day 1; direct hotel contracts in a few high-density scout cities once volume justifies it.

Paid stat rerolls, loot boxes, and pay-to-win scout upgrades are a hard no. The product can feel game-like in habit, but the economics around real money have to stay boring and trustworthy.

Section 06

Negotiation realism

Worth being precise about what "negotiation" means on day one. It's not the scout phoning every hotel.

Together those four levers keep day-one negotiation real but bounded. The user still feels represented by an agent — and the product doesn't promise autonomous hotel-by-hotel negotiation before there are enough hotels in any one city willing to take that call (the supply-density problem).

Section 07

Retention — the daily free action

The daily free action is Send Scout on Patrol.

A patrol can:

Stronger than a passive deal feed, because the user has a role. They're training an agent and contributing to a market — not scrolling travel content.

Section 08

Social mechanic — organic growth

The social mechanic is Party Quests. Users invite friends or compatible strangers because scout composition matters. For group travel, the trip runs as one shared quest: each traveler brings their one Scout, and the party resolves price, location, flexibility, and review risk against a single group mandate.

The shareable object isn't a coupon. It's the story of a hunt.

Section 09

Positioning + category

Not: an AI travel agent, an opaque booking site, or a cheaper Priceline.

The category claim: multiplayer travel scouting. Users send personal AI scouts into a live market, where deal intelligence is discovered, validated, and acted on — socially.

Reference points: Going.com proves the deal-hunter segment exists and pays. Pokémon Go and MMO-style party quests show that location-based daily activity works at scale. Discord and Strava show that people will form social identity around a hobby. Priceline and Hotwire are what this explicitly isn't.

Travel search is users querying catalogs. Scout is users sending representatives into a live market.

Section 10

Calls made on ambiguous parts — explicit

CallReasoningTrade-offs
Agents compete and cooperate inside quests This makes the agent mechanic user-visible and avoids a thin "AI searches harder" product. Heavier UX surface and onboarding than a single-agent chat; risk of feeling busy to a casual booker.
User = flexible hunter Broad travelers won't tolerate surprise or tradeoff; hunters will. Narrower addressable market on Day 1; cedes the bulk of OTA volume to incumbents until the niche compounds.
Scout = persistent representative The agent has memory, strengths, and reputation, not just a chat window. More state to engineer and protect; if users don't bond with their scout, the persistence buys nothing.
Daily retention = patrols, not daily booking Travel is too low-frequency for a booking-only habit. Patrols burn compute and design effort without producing direct revenue; must stay cheap and feel useful.
Discount promise = benchmarked savings A qualified strike must beat a transparent all-in benchmark or the hunt stake rolls forward/refunds. Caps revenue on hunts that don't qualify; benchmark sourcing must be defensible or the guarantee becomes a liability.
Social growth = party composition Invites are useful because different users' Scouts improve quest outcomes. Slower than referral bounties; only works if quests are interesting enough that inviting friends feels worth it.
Small fee = hunt stake Preserves the brief's paid primitive, but frames it as commissioning work rather than paying for a search result. Friction at the top of funnel; some users won't pay before seeing value, so onboarding has to earn the first stake.
Game layer stops before checkout Discovery can feel playful; booking must feel serious, transparent, and reversible where possible. Loses some emotional payoff at the moment of purchase; the handoff between fun and serious modes is hard to design cleanly.

Section 11

What I'd pressure-test with another week


Wireframes · 4 key screens

Isometric rooms for the game layer. Clear tickets for the booking layer.

Screens 01–03 make scout coordination visible — map tiles, rooms, roles, movement. Screen 04 switches register entirely: it's a calm decision surface, where price, tradeoffs, and approval all have to stay trustworthy.

Direction Habbo-inspired presence, not a retro clone — tiny scout avatars, city rooms, party composition, quest progress. No slot-machine sparkle on the path to checkout.
01 · World Map / Quest Board
9:41 ●●●
Your scout
On patrol · Tokyo
M R H
Tokyo softening 3 live rooms
Daily free action · free
Send Mara on patrol
Quest · Lisbon · 3/5 Scouts
Boutique under $180
Haggle Taste Patience Radar
Quest · Tokyo · 4/4 Scouts · flash likely
Weekend drop watch
City intel · Bangkok
Luxury gap night spotted
Quest recap · Mexico City
4 users · 4 Scouts · $210 saved
Open slot
Roma Norte Watch needs a Haggler
The default home. The map changes daily and gives the user a free role: send their scout on patrol, validate intel, or join a public quest.
02 · My Scout
9:41 ●●●
Mara · Radar Scout
Edit
M
Your representative
Stats · shape behavior, not access
Haggle
42
Taste
71
Patience
66
Radar
91
Speed
58
Flex
73
Traits
No resort fees Walkability snob Waits for drops Hates fake boutique
Reputation
47 useful flags · 83% pass accuracy
This week · 3 patrols, 2 quests
The scout is persistent and configurable. Stats explain behavior and party matching, but never become pay-to-win booking mechanics.
03 · Party Quest Room
9:41 ●●●
Quest · Lisbon
Boutique under $180
Day 4 / 14
Strike candidate waiting Review ›

Party · 4 users

M O S J
Mara reporting · 9:41 4 Scouts synced
Mara · your ScoutRadar · fee traps
Ori · Alex's ScoutHaggler · promo rails
Sol · Priya's ScoutTaste · vibe fit
Juno · Ken's ScoutPatience · drop timing

Mandate · what the party may negotiate

Fee waivers Refundable swaps Concession asks Date permutations Direct hotel call Group bundling

Progress · Day 4 of 14

Properties checked37
Passed11
Watching3
Strike candidates1

Findings feed · live

Mara · your Scout · Radarreject
Ori · Alex's Scout · Hagglerapprove
Juno · Ken's Scout · Patiencehold 24h
Sol · Priya's Scout · Tasteapprove
The quest room shows accountable representative work: one Scout per user, who contributed, what was rejected, and why the party thinks a strike may be forming.
04 · Strike / Quest Recap
9:41 ●●●
Strike found · confidence 82% Stake protected
$162/ night · target $180 · Lisbon · May 14-17
$340 saved vs all-in benchmark · refundable until May 9.
All-in benchmark$194 / night
Scout strike$162 / night
Clean feesVerified
Refund windowMay 9
Why now
Scout consensus
Ori · Haggler
Approve
Mara · Radar
Approve
Sol · Taste
Approve
Juno · Patience
Book now
The decision is serious and transparent. After booking, this becomes the shareable recap: scouts involved, paths rejected, savings, and partial reveal.