Launched this week
Running even one online store is a full-time job. SellerClaw is a team of AI agents that runs it for you: specialized agents for product sourcing, store management, and advertising, coordinated by a supervisor you direct. Tell it what to sell — the agents build listings, manage ads and pricing, and handle fulfillment and support across Shopify, eBay, and more. You stay in control: every action is visible and approvable, and you set how much runs on its own. Free to start.
How much setup does this need before the agents do anything useful? Asking because I've tried tools that wanted three days of config before the first result.
SellerClaw
@anshu_kumari9 It depends on the use case, but it does not need days of setup before it becomes useful.
There are hundreds of ways to use SellerClaw — from basic automations like inventory sync and order fulfillment to much more advanced analysis and store optimization. So you can start simple, connect a channel or two, and get value pretty quickly, then expand from there.
For example, if you already have an active store, here is my personal favorite use case: you can ask a high-intelligence model like Claude Opus to analyze the whole store, identify which products have the strongest viral potential right now based on real signals pulled from SocialVault, generate creatives, and launch multiple ad campaigns across Meta and Google.
SellerClaw
@anshu_kumari9 This is exactly the pain we built against, so the honest answer is minutes, not days. Connect a channel, set your guardrails (margin floor, budget ceiling, that kind of thing), and the agents start working against real data. Most sellers hit their first sync inside half an hour.
The reason it's fast: you're not configuring rules and workflows by hand. You set the boundaries and the goals, the supervisor figures out the rest. No three-day setup tax before you see anything happen.
If you want, I can walk you through the fastest path for your specific channel setup.
@kamilbbs How do you handle a bad agent decision? If the Ads manager burns budget on a dud, can I see why it made that call and roll it back?
SellerClaw
@vishalmehta8340 Yes, by default the agent should stop actions that start affecting the business negatively and report back to the user rather than just continue blindly.
In normal operation, though, that situation should usually be prevented earlier: when the user request is first processed, the supervisor sets the task up with guardrails, limits, and success criteria. So ideally the agent is acting inside those boundaries from the start, and if it drifts outside them, it pauses and escalates.
SellerClaw
@kamilbbs @vishalmehta8340
Yes on both. Every agent action is logged with the reasoning behind it, so when the Ads manager makes a call you can see the signals it acted on, not just the outcome. No black box you have to take on faith.
On the budget-burn specifically, the guardrails are there to stop it before it happens, you set the ceiling and the agent can't spend past it. And anything that crosses a threshold you've set comes to you for approval instead of running silently. So the dud either gets caught at the guardrail, or it's reversible and you can see exactly why it happened.
We're actively deepening the audit and rollback side, so if there's a specific control you'd want, that's useful feedback right now.
Does a constraint I give to one agent automatically propagate to all relevant agents? E.g. if I tell the supervisor to stop sourcing a product, will it automatically know to pause ads for it too?
Good luck with the launch!
SellerClaw
@daria_lir_m
Good question, and yes. A couple of cases to separate out:
If the Product Scout is sourcing a product for the first time, there's nothing to pause, it isn't in your store yet, so there's no listing and therefore no traffic running against it, internal marketplace or external (Facebook, Google). No listing, no ads.
The more interesting case is a product we've already imported from a dropshipping platform and started advertising. If we then get a signal via API that the item has gone out of stock at the suppliers, the ad campaign stops automatically so you're not burning budget driving traffic to something you can't fulfill. Same principle as before, the whole system is wired around profitability, so a constraint on availability propagates straight through to ad spend.
Thanks, and appreciate the kind words on the launch!
SellerClaw
@daria_lir_m The Supervisor is the coordination layer, so you're not managing each agent separately. When you direct it to stop sourcing a product, it knows what the other agents are running. Whether the ad pause happens automatically or surfaces as a recommended action depends on how the workflow is configured. That's worth testing with a real case during onboarding.
For me the key question is control. If SellerClaw can source products, publish listings, place supplier orders and reply to customers, I’d want clear guardrails for refunds, margins, ad spend and publishing. The Advisory mode makes sense as the first step.
SellerClaw
@andrew_white_13 Advisory mode covers publishing and orders: every action goes to your review queue before anything runs. Budget rails handle ad spend. Margin floors and refund-specific controls are on the roadmap. Appreciated the specifics. That's useful input for us.
SellerClaw
@andrew_white_13
Control is the right thing to anchor on, it's exactly how we think about it too.
Advisory mode is the foundation: publishing and supplier orders both flow into a review queue, so nothing executes until you approve it. Ad spend runs inside budget rails you set, so the agents can't exceed what you've allowed. Margin floors and dedicated refund controls are on the roadmap, the same guardrail logic, applied to those two areas next.
The principle is simple: the agents do the heavy lifting, but you set the boundaries and hold the final say on anything that matters. Really appreciate you spelling out the specifics, refunds, margins, ad spend, publishing, that's genuinely useful input as we build the guardrail layer out.
@tolstov_gleb How does the credit system map to actual work? Trying to predict roughly what a month costs if I run repricing daily across a few hundred listings.
SellerClaw
@maurya_abhiranjan Credits map to work done: small tasks use a few credits, heavier workflows use more. Our examples are ~2 credits for a customer reply, ~15 for a listing, ~40 for market research, and 100 credits = $1. For daily repricing across a few hundred listings, the exact monthly spend depends on how often you run the loop and how much reasoning is involved, but the dashboard shows estimates before big tasks and exact usage after.
What does pricing look like for someone running maybe 200 SKUs across eBay and Shopify? Trying to figure out if this fits a small operation or only makes sense at scale.
SellerClaw
@kushwaha_8521 For that size, it should still fit a small operation pretty well. Based on the current pricing, 4,000 credits on the $36/month Growth plan is likely enough to actively manage around 200 listings across eBay and Shopify, and that plan also includes unlimited sales channel connections.
There’s also a free plan with 500 credits to try it, and with the current Product Hunt offer you can get an extra 1,000 free credits, so you can test real workflows before committing. The pricing page also notes that light tasks use only a few credits, while bigger jobs use more, and the dashboard shows usage as you go.
NovaVoice
congrats on the launch! Is Amazon support already live, or are Shopify and eBay the main focus right now?
SellerClaw
@rustam_khasanov thanks! Shopify and eBay are live now. Amazon is coming.
SellerClaw
@rustam_khasanov Thanks! Shopify and eBay are the main focus right now, so those are fully live. Amazon's next — we've already been granted developer access to the SP-API and we're working on bringing it into the product soon. Stay tuned.
SellerClaw
@rustam_khasanov Thanks! Shopify and eBay are the main focus live right now. Amazon support is in progress and should be coming in the next 2–3 weeks.