<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/14307b529e3a4b829c1d4daf9fbd1aed&quot; frameborder=&quot;0&quot; width=&quot;1398&quot; height=&quot;1048&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1048</height><width>1398</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1048</thumbnail_height><thumbnail_width>1398</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/14307b529e3a4b829c1d4daf9fbd1aed-e7ef3694fd419e99.gif</thumbnail_url><duration>136.738</duration><title>Parakh GST Credit Checks</title><description>Parakh is an evidence-first counterparty-checking experience for Indian small
businesses. Before sending goods on credit or starting a business relationship,
an owner may need to compare GST filing patterns, name variants, public-record
clues, screenshots, and portal results. Today, that work is fragmented, slow to
read, and easy to overstate.

This public, no-login prototype makes one check easier to complete. A reviewer
enters one visible Demo Reference, watches the local-fixture report flow, and
receives a readable Parakh-style report. It turns fictional registration,
filing, and public-record fixtures into explainable FLAG, CLEAR, and NOTE
observations. Each observation shows confidence, attribution, provenance,
limitations, and “What we could not find.” The user can compare five realistic
fictional situations, inspect the evidence path, or download a fixture-only A4
PDF.

The difference is not a score or a trust verdict. Parakh makes the available
evidence and its gaps understandable before a business owner acts. It is built
for mobile use and lower digital confidence: one clear reference, one visible
journey, and plain-language limits.

Everything in this build is synthetic. It never accesses live government
systems, private records, real identifiers, payments, OTPs, or production
Parakh data. A real deployment would require authorized APIs, consent-aware
handling, audit logs, rate limits, data provenance, retention limits, security
controls, and clear human-readable limitations.</description></oembed>