Compare Hotels

Search every available source for accommodation and present one unified comparison. Combines portal premium programs (Chase Edit, Amex FHR/THC), cash pricing, and Airbnb alternatives into a single view.

This is an orchestration skill. It tells the agent which tools to run and how to combine results. No standalone script.

When to Use

• "Find me a hotel in Paris for Aug 11-15"
• "Should I book through Chase or Amex for this hotel?"
• "Compare hotels vs Airbnb in Oslo"
• Any accommodation search where the user wants the full picture

Sources

Run these in parallel where possible. Never fail silently.

Portal Premium Programs (Docker required)

Cash Prices and Metasearch

Quality and Ratings

SerpAPI, Trivago, and LiteAPI are all default. Always search all three. Only add RapidAPI if the user asks for Booking.com specifically. Use TripAdvisor for quality data (ratings, rankings, reviews) to complement pricing from other sources.

Vacation Rentals

Premium Property Databases (local, instant)

Workflow

Step 1: Search All Sources

PARALLEL GROUP 1 (fast, ~3-5s):
  - SerpAPI: Google Hotels cash prices
  - Trivago: metasearch across OTAs (web search)
  - LiteAPI: negotiated hotel rates (web search)
  - Airbnb: vacation rentals in the area
  - Local data: check premium-hotels databases for the city

PARALLEL GROUP 2 (slow, ~45s, Docker):
  - Chase Travel: --hotel --dest "City" --checkin YYYY-MM-DD --checkout YYYY-MM-DD --json
  - Amex Travel: --hotel --dest "City" --checkin YYYY-MM-DD --checkout YYYY-MM-DD --json

For each source, capture:

• Source name
• Status: "ok" | "error: {reason}" | "skipped: {reason}"
• Results count
• Data

Step 2: Identify Stacking Opportunities

Cross-reference results with data/fhr-properties.json, data/thc-properties.json, and data/chase-edit-properties.json:

For each hotel in results:
  - Is it in FHR? → Tag [FHR]
  - Is it in THC? → Tag [THC]
  - Is it in Chase Edit? → Tag [EDIT]
  - Is it in multiple? → Tag [FHR+EDIT] and note stacking potential

Stacking means: book through one portal, pay with the other card separately. For example, book FHR through Amex (get breakfast + credit + upgrade), then use CSR $300 travel credit on something else at the property.

Step 3: Calculate Points Value

Chase:

• Portal lists at 1.0 cpp. CSR gets 1.5x at checkout.
• Points Boost offers are better (1.5x to 2.0x effective cpp).
• True UR cost = listed points ÷ 1.5

Amex:

• Hotel portal pricing is variable (NOT always 1 cpp like flights).
• The points price shown is the actual MR cost. Calculate CPP from cash/points ratio.
• FHR benefits ($100+ credit, breakfast) offset the rate significantly.

Calculate benefit-adjusted price:

FHR adjusted = total_price - $100 credit - (breakfast_value × nights)
  breakfast_value ≈ $30-50/person × 2 people = $60-100/night
THC adjusted = total_price - $100 credit (2+ night stays only)
Edit adjusted = total_price - $100 credit - (breakfast_value × nights)

Step 4: Present Unified Table

Always use markdown tables. Hotels sorted by benefit-adjusted total price.

Example: Paris, Aug 11-15 (4 nights, 2 guests)

Sources checked:

• ✅ Chase Travel: 21 hotels (15 Edit, 6 standard)
• ✅ Amex Travel: 17 hotels (13 FHR, 4 THC)
• ✅ SerpAPI: 25 hotels
• ✅ Trivago: 30 hotels (cheapest OTA per hotel)
• ✅ LiteAPI: 22 hotels (negotiated rates)
• ✅ Airbnb: 18 listings
• ✅ Premium databases: 8 FHR, 3 THC, 15 Edit properties in Paris
• ⏭️ RapidAPI/Booking.com: skipped (not requested)

Step 5: Recommendation

After the table, always provide:

1. Best luxury value: Which premium hotel gives the most benefit-adjusted savings
2. Best budget option: Cheapest option (often Airbnb for longer stays)
3. Stacking opportunities: Hotels in both FHR/THC AND Chase Edit
4. Credit usage: Which card credits apply ($600 Amex FHR, $300 CSR travel, $250 Select Hotels)
5. Points vs cash: Is using points worthwhile for any of these? (Calculate CPP)
6. Direct booking comparison: Note if direct booking is significantly cheaper than portal price

Airbnb Integration

Use the airbnb_search MCP tool:

airbnb_search(
  location="Paris, France",
  checkin="2026-08-11",
  checkout="2026-08-15",
  adults=2,
  propertyType="entire_home"
)

For each Airbnb result, extract:

• Name, price, rating, reviews
• Property type (entire home, private room)
• Key amenities (kitchen, washer, wifi, AC)
• Direct link to listing

When Airbnb makes sense:

• Stays of 5+ nights (usually cheaper per night)
• Groups or families needing space
• Destinations where hotels are overpriced
• When kitchen access matters (dietary restrictions, saving on meals)

When hotels win:

• Short stays (1-2 nights)
• Premium benefits offset the rate (FHR breakfast alone can be $100+/night value)
• Points redemption gives good CPP
• Loyalty status benefits (upgrades, late checkout, lounge access)

Error Handling

NEVER fail silently. Every source must report its status.

- ❌ Chase Travel: Login failed. No Chase portal pricing available.
- ❌ Airbnb: No results for this location/dates.
- ⚠️ Amex Travel: Only 3 results (some hotels may not be available for these dates).

If premium databases show FHR/Edit properties in the city but the portal search didn't return them, note this: "The FHR database lists 8 properties in Paris but Amex Travel only returned 3. Some may not have availability for your dates."

Data Files Used

Limitations

• Portal searches require Docker and credentials. Skip if not configured.
• Airbnb MCP must be available. Skip gracefully if not.
• FHR/THC/Edit databases are updated periodically. Properties may have been added or removed.
• Amex hotel points pricing is variable (not 1 cpp). Use the actual points price from the portal.
• Chase portal prices don't include the 1.5x CSR multiplier. The skill adjusts automatically.
• Direct booking prices (via SerpAPI) may differ from portal prices for the same hotel.