REPUUL turns a worker's scattered reputation — across every platform they've ever worked on — into one portable, explainable trust score, delivered straight into your product via API.
Reputation doesn't travel. Reviews aren't reliable. Regulators are starting to require proof that platforms are doing something about it.
The signal every platform already leans on to gauge trust is compromised at the source — and most platforms have no independent way to check it.
A worker with five years of five-star history on one platform starts over from scratch the moment they join another — regardless of their actual track record.
The FTC and the UK's DMCC Act 2025 now require platforms to actively police fake reviews — turning trust verification from a nice-to-have into a compliance obligation.
The same pipeline runs behind every trust report REPUUL generates.
Pull public reputation signals — reviews, ratings, tenure, completion history — across every platform a worker touches.
A weighted engine converts raw signals into a 0–1000 trust score, tuned per platform to what actually predicts risk.
An AI layer reads the underlying reviews and writes a plain-English trust summary — not just a number.
Platforms query a single API endpoint and get score, summary, and red flags back as JSON in real time.
The full pipeline — scraping, scoring, AI summaries, and API delivery — is live end-to-end on real marketplace data.
Trust-in-home is a different risk category than freelance trust. A bad hire on a design gig costs money. A bad hire in someone's home is a safety issue — which is exactly why identity verification and background-check status matter far more here than review volume alone.
REPUUL's scoring engine is designed to be reweighted per vertical. The live pilot proves the pipeline works end-to-end — a platform pilot is how we calibrate the same engine to the signals that matter most for in-home and staffing risk.
A free, no-risk pilot — live demo, real scoring, honest results.