The job Demos Tour Why not a chatbot Product Pricing Download

Multi-channel e-commerce · TikTok Shop · Amazon · Temu

An AI e-commerce operator that runs your shop's day-to-day

Hire it like an e-commerce operator. Every day it pulls the numbers, writes the profit report, and checks customer messages, refunds, ads and competitors — in the seller centers, in your own logged-in browser. Routine work it does on its own; before changing anything in your shop — a price, a refund, a reply to a buyer — it brings you options to pick from, and once you've decided, it remembers. No training, no days off.

Download Yogent Read the job description

The role

Job description: E-commerce Operator (AI)

Reports to the shop owner. Does the routine work on its own, every day, on schedule; checks with you before changing anything in the shop. One AI operator per shop, on TikTok Shop, Amazon or Temu. Pick the level you need.

When	Duties
Before work, 4 a.m.	Pulls yesterday's orders, payouts, refunds and ads, and sends a per-SKU profit report — loss-makers in red
Every 30 minutes	Checks customer messages and refund requests; drafts replies and decisions for you to approve
Every day	Reviews ad spend and ROAS, and flags what to raise or cut for you to decide
Every day	Watches rival shops and best-seller lists; reports price cuts and new hits the same day
When a call is needed	Brings you the question with options to pick from — and remembers your answer, so it doesn't ask twice

Example: what an Amazon Operations Associate does each day

Two rules. Reading, checking and drafting it does by itself. Anything that changes your shop or spends money comes to you as a card with options — one card per item, on your computer or phone. You decide; it carries it out.

Every day · on its own

Checks and reports

Sales and profit report: yesterday's orders, ad spend, fees and refunds become profit per SKU, loss-makers in red
BSR and keyword rank for every main ASIN, with an alert on sharp drops
Ad check: spend, ACOS and search terms that burn money without orders; drafts bid, budget and negative-keyword changes
Account health: ODR, late shipments and policy warnings
Listings: suppressed or inactive listings, lost Buy Box, hijackers
Buyer messages answered within 24 hours, each reply drafted
Returns, A-to-Z claims and new 1–3 star reviews
FBA inventory: days of cover per SKU, with stockout and long-term storage warnings
Competitors: price, coupon, rating and rank changes on rival ASINs

Every week

Analysis and plans

Brand Analytics (ABA): which search terms are gaining or losing share
Listing and keyword suggestions: title, bullets, backend search terms
Promotions calendar: Coupons, Lightning Deals, Best Deals, Prime exclusive discounts
FBA replenishment plan and a draft shipment
Weekly report: sales, ACOS/TACOS, conversion rate, inventory health

Your call

Comes to you with options

Ad bids, budgets and negative keywords — no silent auto-rules
Replies to buyers, refunds, A-to-Z responses, review follow-ups
Any edit to titles, bullets, images or A+ content
Signing up for promotions and changing prices
Sending FBA shipments and placing restock orders
Opening cases and appeals with Seller Support

Measured the way a human Amazon operator is: ACOS/TACOS, sales growth per SKU, conversion rate, staying in stock and account health. The Amazon job pack is in testing; TikTok Shop and Temu (semi-managed) versions are next.

On the job

Four parts of the job, up close

Each one is a standing role with its own tools, skills and memory — not a prompt someone retypes. They run on a schedule and escalate to a person when judgement is required.

Scenario 01

Which product should we sell next?

Collects TikTok and Temu best-seller leaderboards daily, in the seller's own Chrome
Tracks price, GMV, daily sales, creators, videos and commission per product
Flags follow-sell fit and IP risk before anyone spends on stock
One click copies a winner into My products; the rival shop goes to Competitors

Scenario 02

A rival cut its price overnight. Did we notice?

By hand, a dozen rival listings get checked a few times a week — price cuts are noticed days late, after the sales are already lost.

Visits chosen rival shops every day in an isolated browser profile
Logs price changes, promotions, new SKUs and review swings
Spots their best-performing videos and creators
Suggests a response: match price, bundle, or push our own video

Scenario 03

An 11-page report, ready at 4 a.m.

Built from seven seller-center pages: orders, finance, returns, reviews, shop health, analytics and ads.

Profit per SKU after shipping, fees, ads and cost of goods — losers in red
Refunds with time left to act, and new 1–3 star reviews
Shop health score and violations, with a warning before the score drops
Today's to-dos: must-fix items in red, suggestions in green

Scenario 04

Videos and comments, from an iPhone

Publishing agents post product videos to TikTok and Instagram from a phone, as a person would
Replies answer buying questions using facts from My products, so nothing is invented
Works the first hour after posting: pin good comments, reply fast, start a discussion
Every reply is drafted for the seller to approve in a batch; complaints and refunds go to a person

TikTok and Instagram engagement agents are built; live-account pilots are next.

Demos

See it working, in under a minute each

Screen recordings from the real app, with bilingual subtitles. Swipe or use the arrows to see more.

0:33

Pick a fingerprint browser by its profile allowance

How many browser profiles the free version gives you, and the profile list we use day to day.

0:46

Browser groups: one sign-in, many pages

Several windows share the same signed-in session, each working on a different page.

0:45

Create a browser with one sentence

Tell the assistant what it is for, what to call it, and direct or proxy — it sets up the profile and opens it.

0:26

Sign in to TikTok once, stay signed in

Open a profile, sign in to TikTok, and keep using the same session next time.

Tour

Yogent in six pictures

What it does, one picture at a time. Swipe or use the arrows; click a picture to enlarge it.

Free fingerprint browser, AI staff included

One app for multi-shop, multi-account cross-border sellers.

One account, one browser profile

Each profile keeps its own fingerprint and sign-in, so accounts never mix.

Say it once, the AI staff finish it

Each job becomes a workflow that runs on schedule and only asks you when it needs a decision.

The daily report is ready before you are

Built at 4 a.m. — loss-making SKUs in red, to-dos sorted by urgency.

Rival price cuts and new listings, watched daily

Rival shops are checked every day; anything cheaper than ours is highlighted.

The Free plan has every feature

Fingerprint browser, AI staff and workflows — nothing held back.

Competition

Why not just use a general AI assistant?

Large models are the engine. Merchant Agent is the workbench sellers actually use.

General AI agents today	Merchant Agent
Every task is a back-and-forth chat, and the right window is hard to find	Tasks run as scheduled workflows; results land in the Inbox and Dashboard
Sessions are grouped by conversation, not by agent	Each agent has one home: its tasks, history and output together
Sessions don't map to the roles a store actually has	Agents mirror real roles: daily reporter, ads optimizer, notifier
A chat window can't show the many signals an e-commerce call needs	Screens built for e-commerce: shops, SKUs, ads, profit and to-dos side by side

Product

Built for how multi-shop sellers actually work

Browser control. Many seller-center tasks have no API at all. The agent works the web pages directly, inside sessions that are already signed in.
IP and profile isolation. Shops sharing a device or IP risk being linked. Each shop runs in its own browser profile and IP.
Posting from a phone. Videos and comments go out from an iPhone, the way sellers already do it.
Roles accumulate. Every correction becomes a new version of that role, so the asset compounds per store instead of resetting each session.

Automation

The morning routine finishes before anyone sits down

Agents are chained into workflows that run on a schedule: pull the data, write the report, post it to the warehouse group — done. Risky steps wait for approval, and anything that fails lands in the Inbox with its context instead of disappearing.

The Merchant Agent Hub lets a seller install a role that already works for someone else, rather than building every agent from scratch.

Shops

Every store, one place

All stores on all platforms, with each agent scoped to what it may touch.

My products

One catalog

Published in each platform's own format.

Dashboard

Real profit per SKU

After shipping, fees and ads — not gross revenue.

Inbox

The human queue

Refunds, bad reviews, failed labels and approvals as to-dos.

Research

Daily best-sellers

TikTok and Temu leaderboards, with IP risk flagged.

Competitors

Rival tracking

Listings and prices watched automatically.

Videos

Short video anyone on the team can make

Scripts, voiceover, subtitles and finished cuts.

Chats

Ask in plain words

"Why did ROI drop yesterday?" — answered from the store's own data.

My Agents

Role-based agents

Daily reporter, ads optimizer, notifier, and the rest.

Workflows

Scheduled runs

Chained agents that finish on their own.

Agent Hub

Ready-made roles

Install agents and workflows in one click.

Mobile

From your phone

Check results, give feedback, send product videos.

Pricing

Free to start. Top up as you go

No subscription · 1 point = ¥1

Free trial

Every feature, plus our model allowance

^¥0

100 points of model allowance for 30 days

Download and try

5 shops across every platform
5 team seats
Every AI employee, their jobs and the agent store
Product research, competitors, order labels, invoices
Fingerprint browser with browser groups
100 points of model allowance, good for 30 days
After that, connect your own model and keep going

Top up

Pay as you go, nothing resets monthly

^¥9.9first top-up

20 points for your first top-up, then from ¥50 or any amount you like, up to 15% bonus points

Models: points are charged by actual use
AI video by the second, from 0.7 points a second (below)
A 4-second 480p sample is just 2.8 points
Leftover trial points carry over on your first top-up
Shared by your whole team, valid for a year
More shops and team seats on request

AI video, priced by the second

Real-person and scene videos, with voice-over if you want it

480p

0.7point / second

Samples and quick tests

4 s sample2.8 pts8 s5.6 pts15 s10.5 pts

Most used

720p

1point / second

Most product videos

4 s4 pts8 s8 pts15 s15 pts

1080p

1.5point / second

Ads and hero videos

4 s6 pts8 s12 pts15 s22.5 pts

Review the prompt before it is madeNothing is charged if a video failsEvery video is checked against your product photo

Free to start. First top-up ¥9.9 for 20 points, then from ¥50 with Alipay; points are shared by your team and valid for a year. Questions? Contact support: help@yogent.ai

Download

Install the desktop app

Yogent runs on your own computer. Install the desktop app and you're set: it comes with its own fingerprint browser, extension included. Sign in after installing to sync your team's agents, workflows and data.

macOS

Apple silicon (M1 and later) · v6.4 · 328 MB

Download for Mac

SHA-256 fa89ad8822f7278a84e4efa344e387636f0dee364888b40a945100161c00cdcc

Windows

Windows 10 / 11 · 64-bit · v6.4 · 266 MB

Download for Windows

If Windows shows “Windows protected your PC”, click More info → Run anyway.

SHA-256 0a784b20378c61d362cd35aea22180cbac7d035ceded4309749e858b9a0e2d5c

Chrome extension (optional)

Yogent Extension · Chrome / Edge · Chrome Web Store · may need a VPN in mainland China

Add to Chrome

Optional — only needed if you want agents to work in your own Chrome; the built-in fingerprint browser already has it. Opens the Chrome Web Store — click Add to Chrome; updates install automatically. Works in Edge too — install guide. No Chrome yet? Download Chrome.

Seeing it

The honest version of this is a screen share

Slides flatten the part that matters. What is worth looking at is the running operation: the agents that went out this morning, the runs that finished, and the ones sitting in the queue because they needed a person. We would rather show that than describe it.