Three businesses. Three adapters. One engine.
ryvl serves three kinds of business. A local business is read from its Google reviews; a D2C brand from its ASIN reviews; a mobile app from its App Store and Google Play reviews. Each enters through its own input adapter, and all three feed the same analytical engine that turns real reviews into a competitive advantage.
One product, three input adapters
An adapter is how a business enters ryvl. Each one takes a different input and a different review source, then normalizes to a single shape the engine can read.
Local Business
SMBReads Google reviews
- Input
- Paste a Google Maps link
maps.app.goo.gl/… - Subject
- A local business and its nearby same-type competitors.
- Ingest
- Resolved against Google Places, then a same-type Nearby Search scores and selects the competitors. Their real reviews become the corpus.
D2C Brand
D2CReads Amazon reviews
- Input
- Paste an Amazon ASIN
B0XXXXXXXX - Subject
- An Amazon product and its competing listings.
- Ingest
- Parsed from an ASIN or product URL, then the review corpus is pulled from the live listings, weighted toward critical reviews.
Mobile Apps
AppsReads App Store / Google Play reviews
- Input
- Paste an App Store or Play link
apps.apple.com/…/id123 - Subject
- A mobile app and its competitor apps.
- Ingest
- Parsed from an App Store or Play link, then a recent review window is pulled from Apple's RSS feed or google-play-scraper, weighted toward detractors and scoped to that window.
Different inputs, identical engine
The adapters are the only part that differs by business type. Everything past the normalized corpus runs the same way, which is why a coffee shop, a water bottle, and an app get the same depth of report.
ReviewSetReal review text, normalized. The engine never knows or cares which adapter produced it.
The weakness as a campaign angle and ready ad copy.
The same weakness as a tactical action plan with success criteria.
Nine modules, whichever way you came in
Every module is grounded in the review text, never mocked. They run identically for a local business, a D2C brand, and a mobile app. Open one to see it on a real report.
Intelligence
Action
Marketing campaign
The weakness turned into a campaign angle and ready ad copy.
Action plan
The same weakness turned into clear steps you can act on.
Campaign studio
The campaign turned into ready-to-post social creative.
Operational punch list
The gaps turned into a prioritized owner to-do list.
Review reply drafts
Ready-to-paste replies to your own reviews. Draft only.
One insight, two outputs
The single sharpest competitor weakness is selected in code, then written up twice, for the person who markets and the person who operates. Both are pinned to the same weakness, so they never drift apart.
The weakness becomes a campaign
A target frustration, a campaign angle, and two to three ad variations with copy and rationale. Written from the exact language real customers used about your rival.
The same weakness becomes an action plan
The problem, who it affects, the evidence quotes, and a proposed fix, plus clear next steps with success criteria. Pinned to the same weakness in code.
Built for the people who act on reviews
Local owners and operators
See exactly where the shop down the street is losing customers, and get the moves to win them, traceable to the quotes that justify them.
D2C brands and sellers
Read what buyers complain about on a rival ASIN and turn it into listing angles and a product fix-list, before the next launch.
App developers and PMs
See what a rival app's recent reviewers keep naming, with pricing and release noise separated out, and turn the real gap into store positioning and a product action plan.
Marketers and agencies
A campaign angle and ad copy grounded in real customer language, for a storefront or a listing, not a blank brief.
Pick your way in
Same engine, same depth of report. Start from a local business, an Amazon listing, or an app.