Review-intelligence digest → weekly reputation report
Pull normalized reviews for a property on a schedule and deliver a weekly digest — average rating, recurring themes, and the latest complaints to act on.
What it does
The job it gets done
Reputation is spread across platforms and scored on different scales, so problems surface late. This workflow pulls normalized reviews for a property (native rating scales preserved, never silently rescaled), summarizes the average, the recurring themes, and the most recent low ratings, and delivers a weekly reputation digest. On the AI-agent path the agent reads the reviews and writes the sentiment summary itself; on the n8n path the aggregation is plain JavaScript, so no LLM key is required — add an LLM node only if you want richer narrative.
How it works
Step by step
- 1
Choose the property to monitor
Give the workflow a platform and the platform-native listing id (from a prior /v1/search), how many reviews to pull, and a sort order (recent is the default for a reputation watch).
- 2
Pull the normalized reviews
It calls GET /v1/reviews, which returns reviews in one schema with each native rating scale preserved and echoed (5 for Airbnb/Vrbo/TripAdvisor, 10 for Booking.com/Expedia/Hotels.com).
- 3
Summarize sentiment and themes
The agent reads the reviews and writes the summary; the n8n transform aggregates an average on the native scale, a theme-frequency table from the text, and the most recent low ratings — no LLM key needed.
- 4
Deliver the weekly digest
A reputation digest (average, top themes, recent complaints) is posted to Slack or email on your cadence — swap the last node or add an LLM node for a more narrative write-up.
What you'll need
Two ways to run it
Using an AI agent
Just your ScoutingAPI key. Your agent is the brain — it calls the endpoint and reports the result itself, so there's no separate AI key to buy. Install the SKILL.md below.
Using n8n
A running n8n instance, the workflow JSON below, a ScoutingAPI Header Auth credential, and a delivery credential (e.g. Slack) — or swap the last node. The transform is plain JavaScript, so no LLM key is required.
Try it live
Run the core call now — sandbox, 0 credits
Exercise the endpoint this workflow is built on against the deterministic sandbox — a real 200, zero credits, no sign-up.
/v1/reviewsRuns against the deterministic Booking sandbox fixture — a real 200, zero credits.
Run the call to see a live, deterministic sandbox response.
curl -sS "https://api.scoutingapi.com/v1/reviews" \
-H "Authorization: Bearer $SCOUTINGAPI_KEY"Code samples
The same call, every way that matters
curl -sS "https://api.scoutingapi.com/v1/reviews?platform=booking&listingId=abramovic2&limit=40&sort=recent" \
-H "Authorization: Bearer $SCOUTINGAPI_KEY"Get it for your platform
Download & import
Typical cost
from 5 credits per call per run — scales with the results returned (v3 per-result).
reviews· from 5 credits per calllisting· 3 credits per call
Failed & empty calls are always free; sandbox calls cost 0. Live costs are on the pricing page.
FAQ
Common questions
Get your free key — no card
300 credits, the full API, the sandbox, and the native MCP server. Power this workflow and more.
No credit card · failed calls cost 0 credits