{"accent":"Accent","accept":"Accept","active":"Active","analyticsNavDesc":"Dashboards, ad-hoc queries, insights","analyticsNavLabel":"Analytics","analyticsTry1":"Merge Wildberries and Ozon sales for [period] and compare with [the previous period / the same period\nlast year].\nFor each marketplace, category and SKU show revenue, orders, average order value and returns.\nBreak every decline down into factors: order count fell, selling price fell\nor returns grew — and show each factor's contribution in rubles.\nDon't explain a decline by \"falling demand\" or \"seasonality\" until you show a figure that\nconfirms it. If an item didn't sell because it was out of stock, say exactly that —\nthat isn't a demand decline.\nOutput a SKU table sorted by lost revenue, and the ten items\nthat account for half of the decline.","analyticsTry2":"Build a revenue dashboard in Google Sheets by channel [Ozon / Wildberries / others — list them]\nand refresh it [every Monday morning].\nOverwrite the \"Data\" sheet in full, don't touch the charts sheet — it references \"Data\".\nDon't wipe the history of previous weeks: each week is its own row.\nIf a source didn't respond or returned an obviously incomplete period — don't substitute a zero and don't carry\nthe previous week over. Leave the cell empty, put the week into a \"Gaps\" sheet with the reason\nand mention it in the update message.\nAfter every run send a short summary: what was refreshed, which channels didn't come through,\nand the revenue change versus the previous week in one line.","analyticsTry3":"Analyze Wildberries returns for [period] and compare with [the previous period].\nCalculate the return rate against orders for each SKU, category and warehouse. Break it down by the reasons\nfrom the marketplace report; keep defects, \"wrong size\" and \"doesn't match the description\" separate —\nthose are different areas of responsibility.\nDon't explain growth by seasonality until you show the same happened last year. If there is no data\nfor last year, say so.\nSingle out SKUs where the return rate is more than one and a half times the category average, and estimate\nthe losses including logistics.\nOutput a SKU table and the five items to start with.","analyticsTry4":"Merge sales from 1C, Bitrix24, Ozon and Wildberries for [period] into a single table.\nMatch items by [SKU / barcode / the attached mapping reference],\nnot by name. Bring units of measure and currency to a single form, and fix whether we count\nrevenue with or without VAT.\nRemove duplicates: one shipment that landed both in 1C and in the CRM as a deal is one row.\nIf an item didn't match, or matched only on a similar name — don't merge it by eye,\nmove it to a \"Not matched\" sheet with the candidate options.\nOutput an XLSX: a \"Sales\" sheet broken down as date — channel — unified SKU — quantity — amount,\na \"Not matched\" sheet and a \"Mapping reference\" sheet that I can extend.","analyticsTry5":"Calculate margin by SKU by week for [period] using Ozon and Wildberries sales\nand cost of goods from 1C.\nFor each week break the selling price down into marketplace commission, logistics, discounts and promos,\nand cost of goods. Find SKUs whose margin deviated from their own average for the period by more\nthan [threshold].\nFor every deviation name the factor with a figure: how many rubles came from the increased commission,\nhow many from the discount, how many from purchase cost. Don't name a cause if the breakdown doesn't show it —\nwrite \"factor not determined\".\nTake cost of goods as of the shipment date. Where it's missing, don't substitute the category average,\nmove the SKU into a \"no cost of goods\" list.\nOutput a table by SKU and week and the top deviations in rubles.","analyticsTry6":"Compare [month] with [the previous month] across Ozon, Wildberries and 1C sales.\nShow revenue, order count, average order value and returns — in total, by channel and by category.\nFor each row give the change in rubles and in percent and state what produced it:\nmore orders or a higher average order value.\nList separately everything that makes the months non-comparable: a different number of working days,\nmarketplace promos, a large one-off order, unsettled returns. Show large one-off deals\nboth in the total figure and as a separate \"excluding one-offs\" line.\nCount revenue by [shipment / payment] — the same way for both months.\nOutput a comparison table and the five categories that drove most of the change.","analyticsTry7":"Calculate the sales funnel from [Bitrix24 / amoCRM] data for [period] and compare with [the previous\nperiod].\nFor each stage: how many deals entered, how many moved on, the conversion into the next stage\nand the end-to-end conversion from the first stage, the mean and median time in status.\nCount from the transition history, not from the deal's current status. Show deals that skipped a stage\non a separate line rather than spreading them across the adjacent ones.\nDon't give a list of specific deals or recommendations on them — only figures and the differences between periods.\nIf a stage has fewer than [30] deals, mark its conversion as unreliable and don't draw conclusions from it.\nOutput a table by stage with the two periods side by side and the three stages with the largest conversion\ndrop.","analyticsTry8":"Calculate ad cost share for every campaign for [period]: Yandex Direct and the ad dashboards\nof Ozon and Wildberries.\nFor each campaign: spend, revenue by the dashboard's attribution, ad cost share, order count, average order value.\nWithin a single platform use one attribution model and state which one. Don't add up revenue\nfrom different dashboards for the same order — that's double counting.\nIf a campaign's revenue can't be tied to its spend, move it into \"attribution not determined\"\nrather than crediting it with the category's overall sales.\nSeparate campaigns with an ad cost share above [target] from those with too little data for a conclusion: at spend below\n[threshold] or fewer than [20] orders, mark the row as unreliable.\nOutput a table of campaigns in descending order of spend and a bottom line: how much budget went into campaigns\nwith an ad cost share above target.","appLockPromptTitle":"Verify it's you","appLockUsePasscode":"Use passcode","artifactCode":"Code","artifactComparison":"Comparison","artifactDocument":"Document","artifactFile":"File","artifactHtmlApp":"HTML app · click to open","artifactImage":"Image","artifactInteractive":"Interactive","artifactVideo":"Video","authFailureHint":"The {service} key expired, was revoked, or lost permissions — reconnect it in Integrations and the task will restart itself","billingRenewal":"Renews {date}","billingRenewalExternal":"Renews {date} on the {provider} side","bookDemoNavDesc":"See the product on your own tasks","businessHeroTitle":"One AI agent for the whole team","businessNavOverview":"Samreshuuu for business","businessNavOverviewDesc":"One AI agent for the whole team","cancel":"Cancel","canceledNoMoreCharges":"No more charges — access until {date}","channelLabelMax":"MAX","channelLabelPachca":"Pachca","channelLabelTelegram":"Telegram","compareCellExpandedPerSeat":"Same as the plan, per paid seat","compareCellImagesFree":"Up to 3 on the basic model","compareCellImagesMax":"Up to 150 — 2.5× Pro","compareCellImagesPro":"Up to 60","compareCellPerPlan":"Same as the chosen plan","compareCellRequestsMax":"Up to 320 — 4× Pro","compareCellSessionFree":"Baseline","compareCellSessionMax":"25×","compareCellSessionPro":"15×","compareCellTasksPro":"Up to 80","compareCellVideoMax":"Up to 30","compareHubEyebrow":"Comparisons","compareRowAudit":"Audit log","compareRowBilling":"Unified billing","compareRowCRM":"CRM and marketplaces","compareRowDailyTasks":"Task runs per day","compareRowDocs":"Document generation","compareRowDrive":"Shared team drive","compareRowEmailSupport":"Email support","compareRowImages":"Images per day","compareRowLegal":"Legal database","compareRowMemory":"Memory of projects and clients","compareRowPriorityQueue":"Priority queue","compareRowRefund":"Refund for unused time","compareRowRoles":"Roles and access","compareRowSandbox":"Calculations and table analysis","compareRowSchedule":"Scheduled tasks and triggers","compareRowSeats":"Up to {maxSeats} seats","compareRowSessionBudget":"5-hour session allowance","compareRowTGSupport":"Priority Telegram support","compareRowVideo":"Videos per month","compareRowWeb":"Web search","compareSectionGeneration":"Content generation","compareSectionIntegrations":"Integrations and tools","compareSectionSupport":"Support","compareSectionTeam":"Team features","compareSectionUsage":"Usage","completed":"Completed","connectorConnected":"Connected","connectorDisconnected":"Disconnected","connectorRecommended":"Connected","connectorReconnectNeeded":"Reconnection required","connectorSuspended":"Suspended","copied":"Copied","copy":"Copy","create":"Create","ctaOpenApp":"Open app","ctaSignup":"Try for free","dashboard":"Tasks","dashboardFilterAll":"All","dashboardStatusActive":"Active","date":"Date","declineCardExpired":"Renewal failed: your card has expired. Add a new card to keep access to your plan.","declineCardInvalid":"Renewal failed: the card details are invalid. Add a new card to keep access to your plan.","declineCardRestricted":"Renewal failed: the payment was declined by your bank. Contact the bank or use another card to keep access to your plan.","declineInsufficientFunds":"Renewal failed: not enough funds on the card. Top up the card or use another one to keep access to your plan.","declineIssuerUnavailable":"Renewal failed: your bank is temporarily unavailable. We will retry, or you can use another card to keep access to your plan.","delete":"Delete","description":"Description","disabled":"Disabled","done":"Done","download":"Download","email":"Email","enabled":"Enabled","errAuthRequired":"Authentication required","errChatCodeFallback":"Error: {code}","errChatConnectionLost":"Connection lost. Try again.","errChatCorruptedFile":"File is corrupted or has an invalid structure. The size is fine — the problem is in the content.","errChatEmbeddingFailed":"Could not index the document. Try uploading it again.","errChatEmptyDocument":"The document has too little text to analyze.","errChatExtractionTimeout":"Document processing timed out.","errChatFileNotFound":"File not found. Upload it again.","errChatFileNotFoundNamed":"File \"{filename}\" not found. Upload it again.","errChatGeneric":"An error occurred. Try again.","errChatOcrRequired":"The document is a scan. Text recognition takes longer.","errChatPasswordProtected":"File is password-protected. Upload an unprotected version.","errChatSessionBusy":"This session is being processed in another window. Wait for the response or refresh the page.","errChatSuspiciousContent":"Document rejected by the security system: hidden AI instructions were found in the text.","errCheckInput":"Check the details you entered","errFallbackGeneric":"An error occurred, try again","errFallbackValidation":"Data validation error","errInvalidCredentials":"Incorrect email or password","errInvalidOtp":"Invalid or expired code — request a new one","errPermissionDenied":"You don't have permission for this operation","errServerErrorRetryLater":"Something went wrong. Try again later","errServiceUnavailable":"Service temporarily unavailable","errSessionExpired":"Session expired, sign in again","errSignupFailed":"Sign-up failed, try again later","errTokenExpired":"Token has expired","errTooManyAttempts":"Too many attempts. Wait 1 minute","error":"Error","errorDetailsForDeveloper":"Details for developer","errorFullReload":"Full reload","errorPushokWorried":"Nothing is lost — try again.","errorSomethingWentWrong":"Something went wrong","errorTryAgain":"Try again","errors.CAPACITY_EXHAUSTED":"Too much work running right now. Please try again in a few seconds.","errors.CONNECTION_LOST":"Connection lost. Please try again.","errors.CONNECTOR_SCHEME_BLOCKED":"This connection scheme is not allowed in the cloud environment.","errors.CORRUPTED_FILE":"File is corrupted or has invalid structure.","errors.DATA_USAGE_QUOTA_EXCEEDED":"Plan limit reached. Top up or wait for your limit to reset.","errors.DESKTOP_UPDATE_REQUIRED":"This action needs a newer version of the desktop app. Update it and try again.","errors.EMPTY_DOCUMENT":"Document contains too little text for analysis.","errors.EMPTY_RESPONSE":"Could not generate response. Try rephrasing.","errors.EXECUTION_FAILED":"The operation failed.","errors.EXEC_BUDGET_EXCEEDED":"The run hit its budget limit and was stopped. Increase the task budget and run it again.","errors.EXTRACTION_TIMEOUT":"Document processing timeout.","errors.LLM_CREDITS_EXHAUSTED":"A temporary problem on our side — the AI service is currently unavailable. We're on it; please try again a little later.","errors.LLM_ERROR":"AI service error. Please try again.","errors.LLM_NON_RETRYABLE":"The AI service rejected the request. Try rephrasing.","errors.LLM_TIMEOUT":"AI service response timeout.","errors.LLM_UNAVAILABLE":"AI service temporarily unavailable. Please try again in a few minutes.","errors.LOCAL_HANDS_NOT_READY":"The desktop agent on your computer isn't ready yet. Open the desktop app and try again.","errors.ORCHESTRATOR_PARTIAL_COMMIT":"The response was only partially saved. Refresh the page and try again.","errors.ORCHESTRATOR_PREPARATION_FAILED":"Could not prepare the response. Please try again.","errors.ORG_POLICY_DENIED":"This action is blocked by your organization's policy.","errors.PASSWORD_PROTECTED":"File is password protected. Upload an unprotected version.","errors.PERMISSION_SCOPE_MISSING":"The API key is missing required permissions. Grant them in the service's dashboard and reconnect the integration.","errors.RATE_LIMITED":"Rate limit exceeded. Please wait a moment.","errors.RECONNECT_REQUIRED":"Access to the service has expired. Reconnect the integration and your tasks will continue.","errors.SANDBOX_UNAVAILABLE":"The execution environment is unavailable. We're on it; please try again later.","errors.SERVER_ERROR":"Something went wrong. We're looking into it.","errors.SERVICE_QUOTA_EXHAUSTED":"The service quota is exhausted. Try again later or upgrade your plan.","errors.SERVICE_UNAVAILABLE":"Service temporarily unavailable. Please try later.","errors.SESSION_CONCLUDED":"Session ended — this run is already closed.","errors.STREAM_IDLE_TIMEOUT":"The response timed out while idle. Please try again.","errors.SUBSCRIPTION_REQUIRED":"This feature requires an active subscription.","errors.SYNTHESIS_FIRST_CHUNK_TIMEOUT":"The AI service took too long to start responding. Please try again.","errors.SYNTHESIS_STALL_TIMEOUT":"The response stalled midway. Please try again.","errors.TASK_ALREADY_RUNNING":"This task is already running. Wait for it to finish or stop it first.","errors.TRANSCRIPT_DEGRADED":"One step did not reach the transcript — work continues","errors.UNSUPPORTED_FORMAT":"Unsupported format. Please upload {supported_formats}.","expand":"Expand","expired":"Expired","externalExpiresOn":"Access until {date} — renew on the {provider} side","featureAIAssistant20Integrations":"1C, CRM, marketplace dashboards and 100+ services in one window","featureAccessAndRoles":"Member roles and permissions","featureAuditLogs":"Audit log of all actions","featureCreditPool":"Shared balance: whoever hits a limit draws from it instead of moving the team to Max","featureDailyTasksPro":"Images on every model — up to 60 a day","featureDocGeneration":"Invoices, letters, cards and decks in minutes","featureFreeChat":"Chat with the agent in the browser and Telegram — messages aren't counted","featureFreeDailyTasks":"Images on the basic model — up to 3 a day","featureFreeDocs":"Documents and calculations from your files","featureFreeIntegrations":"Connect 1C, CRM and marketplaces","featureFreeSearch":"Web search and legal database","featureKnowledgeBase":"Shared team drive and knowledge base","featureMaxMultiplier":"Up to 320 task runs and 150 images a day","featureMemoryContractorsProjects":"Remembers projects, clients and past decisions","featureMixAndMatch":"Up to 5 free seats — same organization, Free plan limits","featureModelsOnRFServers":"Data stays in Russia — models on servers in the RF","featureModelsOnRFServersGdpr":"Data stays in the EU — processing on servers in the EU/EEA","featurePriorityQueue":"Priority queue — fast replies even at peak","featurePrioritySupport":"Priority Telegram support — replies within an hour","featureSandbox":"Finished analysis from your spreadsheets and exports","featureSchedules":"Scheduled tasks and triggers — up to 80 runs a day","featureSeatsProrated":"Add or drop seats any time — the invoice is recalculated by the day","featureSessionMultiplierMax":"25× the session allowance — 1.67× Pro","featureSessionMultiplierPro":"15× the session allowance","featureUnifiedBilling":"One invoice and contract for the whole team","featureVideoGeneration":"Up to 30 videos a month — Reels and Shorts","featureWebAndLegalSearch":"Finds facts, prices and legal norms","financeNavDesc":"Reconciliation, VAT, e-docs, receivables, reporting","financeNavLabel":"Finance","financeTry1":"Build a P&L for [period] broken down by business unit using 1C data.\nFor each unit: revenue, direct costs, gross profit, overhead, profit before tax.\nNext to it — the share of total company revenue.\nAllocate indirect costs only by the rule [by revenue / by payroll / by floor area]. If no allocation\nbase is set, don't spread them evenly — put such costs on a separate line\n\"not allocated\".\nBuild the report on the accrual basis: from sales documents, not from cash receipts.\nOutput an XLSX: a \"P&L\" sheet with units in columns, a \"Details\" sheet linking\nto the documents behind each line item, and a \"not allocated\" line with its total.","financeTry2":"Reconcile the bank statement [Tochka / Alfa / Sber — or the attached file] against the postings in 1C for [period].\nMatch operations by amount, date and payee. Collect separately: receipts and payments\nnot posted in 1C, postings with no bank operation, amount discrepancies within a single\noperation, likely duplicates.\nDon't force pairs: if an operation matched only by amount but not by payee or date —\nput it in \"needs a decision\", not in the matches.\nOutput an XLSX: a \"Discrepancies\" sheet linking to the operation number and source document, a\n\"Matched\" sheet and a total line — how many operations and what amount did not reconcile.","financeTry3":"Build a receivables report by customer as of [date] using 1C data.\nFor each customer: the amount owed, which documents it consists of, the payment term from the contract,\ndays past due, the date and amount of the last payment.\nCount overdue days from the contractual term, not from the shipment date. If the term is not filled in —\ndon't assume a standard 30 days, move the customer into a \"term not defined\" list.\nSort by overdue amount. Flag separately those whose debt has been growing for three months in a row,\nand those who pay reliably but late.\nAt the end — the total overdue amount and which five customers account for half of it.","financeTry4":"Prepare a reconciliation statement with [counterparty] for [period] using 1C and Diadoc data.\nMatch every UPD and VAT invoice from EDI against a posting in 1C by number, date and amount.\nCollect the discrepancies: a document exists in Diadoc but isn't posted in 1C, is posted in 1C but never arrived\nvia EDI, amounts or the VAT rate differ, the document was cancelled or replaced by a corrected one.\nDon't stop at a matching number: different contracts can share the same numbers —\nalso check the contract and the amount, otherwise move the row into \"needs a decision\".\nOutput the statement in the standard form broken down by dates and documents, a separate discrepancies sheet\nand the opening and closing balances — per our data and per the EDI documents.","financeTry5":"Check outgoing payments on the accounts for [period] against the statement and the postings in 1C.\nFind: payments with a matching payee and amount within [3 / 7 / 14] days, the same invoice or UPD\npaid by different payment orders, recurring payments that have no contract\nor acceptance certificate in 1C, and increases in the amount of a recurring payment.\nDon't treat scheduled recurring payments — [rent, leasing, payroll project] — as duplicates.\nDon't declare a payment a duplicate if the grounds differ: if the payment descriptions differ,\nmove the pair into \"looks similar, needs checking\".\nOutput a table: date, payee, amount, source document, suspicion type and the possible\noverpayment amount; at the end — how much money is worth reclaiming or cancelling.","financeTry6":"Build a payment calendar for [horizon: a week / two weeks / a month] based on account balances\nand the obligations in 1C.\nLay out the outflows by day: invoices due with their deadlines, taxes and contributions, payroll, loans\nand leasing, recurring payments. Mark which payments cannot be moved.\nInclude expected customer receipts as a single inflow line per day and only\nwhere the contractual payment date has already arrived; don't count sales reps' promises\nor \"they usually pay by Friday\".\nFind the first day the balance drops below the [minimum balance] and show the shortfall.\nOutput a day-by-day calendar and a list of payments that are candidates for moving, with a new date.","financeTry7":"Every morning at [time] send a Telegram summary of the accounts [list of accounts] for the previous day.\nFormat: opening and closing balance for each account and in total, total inflow and outflow,\nthe three largest receipts and the three largest payments with payee and description.\nIn a separate block — unusual operations: a payment above [threshold], a new payee never\npaid before, a payment on a weekend, a fee higher than usual.\nIf there were no operations — say exactly that, don't resend the previous summary and don't fill\nthe gap with average values.\nKeep the message within one screen: no tables and no explanations of why the balance changed.","financeTry8":"Check the attached invoice [PDF / photo / EDI document] before sending it for payment.\nCross-check against 1C: tax ID, tax registration code, bank account and bank — against the supplier record; the subject, prices\nand amount — against the contract and this supplier's previous invoices; whether the same invoice\nhas already been paid or is already in the queue.\nTake the details from the body of the invoice, not from the email or the sender's signature. If a field is unreadable\nor missing in 1C, write \"not verified\" and don't substitute the value from a previous invoice.\nAt the end: what matched, what differed, whether there is a duplicate, and a verdict — pay, clarify or\nreject, with a one-line reason.","free":"Free","homeFaq3Q":"How much does it cost?","homeFooterCopyright":"© 2026 samreshuuu. All rights reserved.","integrationsAuthCredentials":"API key","integrationsAuthDevice":"Device code","integrationsAuthOauth":"OAuth","integrationsBackToList":"All integrations","integrationsCatAds":"Ads","integrationsCatAnalytics":"Analytics","integrationsCatBanks":"Banks","integrationsCatContent":"Content","integrationsCatCrm":"CRM","integrationsCatDatabase":"Databases","integrationsCatDev":"Development","integrationsCatDocflow":"Document flow","integrationsCatGoogle":"Google","integrationsCatHr":"HR","integrationsCatLogistics":"Logistics","integrationsCatMarketplaces":"Marketplaces","integrationsCatMessengers":"Messengers","integrationsCatOther":"Other","integrationsCatPm":"Project management","integrationsCatYandex":"Yandex","integrationsHowToConnect":"How to connect","integrationsStepCredentials1Desc":"Create a key in the service's account area — usually under \"API\" or \"Integrations\".","integrationsStepCredentials1Title":"Get an API key","integrationsStepCredentials2Desc":"Open Connectors, pick the service and paste the key — it is encrypted on save.","integrationsStepCredentials2Title":"Paste the key into Samreshuuu","integrationsStepCredentials3Desc":"Ask the agent a first question about the service's data — the link checks itself.","integrationsStepCredentials3Title":"Test the connection","integrationsStepDevice1Desc":"Click \"Connect\" — Samreshuuu shows a short device code.","integrationsStepDevice1Title":"Request a code","integrationsStepDevice2Desc":"Open the service's confirmation page and enter the code from this screen.","integrationsStepDevice2Title":"Enter the code in the service","integrationsStepDevice3Desc":"Once confirmed, the connection activates automatically.","integrationsStepDevice3Title":"Wait for confirmation","integrationsStepOauth1Desc":"The service's authorization window opens — you sign in on its side.","integrationsStepOauth1Title":"Click \"Connect\"","integrationsStepOauth2Desc":"Confirm the permissions Samreshuuu requests — you can revoke them at any time.","integrationsStepOauth2Title":"Grant access","integrationsStepOauth3Desc":"The service appears in your connections list, and the agent sees the data right away.","integrationsStepOauth3Title":"Done","interrupted":"(interrupted)","landingFaqSecurityPointer":"Where data is stored and how access is protected — covered separately:","landingFaqSecurityPointerLink":"security overview","landingFooterColBusiness":"For business","landingFooterColCompany":"Company","landingFooterColCompare":"Compare","landingFooterColLegalTrust":"Legal & Trust","landingFooterColProduct":"Product","landingFooterColResources":"Resources","landingFooterCompareClaude":"vs Claude","landingFooterCompareGiga":"vs GigaChat","landingFooterCompareGpt":"vs ChatGPT","landingFooterCompareYa":"vs YandexGPT","landingFooterContacts":"Contacts","landingFooterCookieSettings":"Cookie settings","landingFooterCopyright":"© {year} samreshuuu. All rights reserved.","landingFooterDocs":"Documentation","landingFooterIntegrations":"Integrations","landingFooterOffer":"Offer","landingFooterPricing":"Pricing","landingFooterPrivacyPolicy":"Privacy Policy","landingFooterSkills":"Skills","landingFooterStatus":"Status","landingFooterTerms":"Terms","landingFooterTrust":"Trust & safety","landingFooterUseCases":"Solutions","landingIntegrationsLink":"All integrations","landingNavApp":"App","landingNavAppDesc":"Desktop for Mac and Windows","landingNavBlog":"Blog","landingNavBlogDesc":"Articles and news","landingNavBookDemo":"Book a demo","landingNavDocsDesc":"Guides and reference","landingNavDocuments":"Documents","landingNavDocumentsDesc":"Contracts, proposals, reports","landingNavHelp":"Help","landingNavHelpDesc":"How to work with the agent","landingNavIntegrationsDesc":"1C, CRM, marketplaces","landingNavSecurityDesc":"TLS 1.3, AES-256, servers in Russia","landingNavSecurityDescGdpr":"TLS 1.3, AES-256, servers in the EU/EEA","landingNavSkillsDesc":"Catalog of skills and extensions","landingNavTasks":"Tasks","landingNavTasksDesc":"Trigger, agent, result","language":"Language","loading":"Loading...","login":"Log in","marketingNavDesc":"Campaigns, content, channel analytics","marketingNavLabel":"Marketing","marketingTry1":"Build a report on ad channels for [period — week from … to …] using data from Yandex Direct,\nVK Ads and Metrica.\nFor each channel and campaign: spend, clicks, conversions on goal [goal name in Metrica],\nrevenue from that goal, ROMI and the change versus [the previous week].\nCalculate ROMI only where revenue comes from Metrica. Where there is no revenue — don't substitute an average\norder value and don't carry it over from another channel, move such channels into a \"ROMI not calculated\" block\nand write what is missing.\nDon't explain a drop by seasonality until you show the same week a year ago.\nOutput XLSX: a sheet by channels, a sheet by campaigns and five lines of conclusions — what grew,\nwhat fell and where to move budget.","marketingTry10":"Collect [10] topics for a content plan for [month] for [Telegram / VK].\nFirst look at my publications over [period]: which formats and angles got above-average response,\nwhich topics repeated without result. Describe this in two or three lines before the topic list.\nGoals for the month: [warm-up / sales / audience growth] and events: [launch, season, date].\nEach topic: format, angle, who it's for, which goal it leads to and which facts it's built on.\nTake facts only from my materials. Don't make up cases, result figures and client quotes:\nwhere an example is needed — put [case needed] and describe which one exactly.\nDon't propose a topic if it already ran on my channel within [period] — or say how the new angle differs.\nOutput a table of topics and a week-by-week layout.","marketingTry2":"Write [5] post variants for the launch of [product and what changes in it] for [Telegram / VK].\nAudience: [who they are, what they already know about us, what stops them]. Offer and deadline: [what we offer].\nMake the angles different: usefulness, a specific pain, \"before and after\", handling an objection, news.\nRely only on the facts I gave. Don't invent numbers, deadlines, testimonials or client names:\nif a fact is missing for a strong line — leave a [gap] and write what to fill in.\nTake the tone from the attached posts, not from ad templates.\nOutput for each variant: the angle in one word, text within the platform limit, a call to action\nand a line \"who it's aimed at\".","marketingTry3":"Find where in Yandex Direct spend over [period] produced no result on goal [goal name].\nGo down the levels: campaign, ad group, ad, search phrase and ad network placement.\nInclude in the report only rows with spend above [threshold] — don't draw conclusions on smaller samples,\ncollect them in a separate \"not enough data\" line.\nDon't call a row wasted spend if it has conversions that are simply expensive: separate \"no conversions at all\"\nfrom \"cost above target\" — those are different decisions.\nSeparately show phrases with high CTR and zero conversions, and ad network placements with a bounce rate above [80%].\nOutput a table: level, name, spend, clicks, conversions, what you suggest doing\n(pause / add as negative / lower the bid) and how much money that frees up over [period].","marketingTry4":"Write a chain of three abandoned-cart emails: [how many hours until the first],\n[the second], [the third].\nMake the mechanics different: the first — a reminder and removing a technical barrier, the second — an answer\nto the reason for hesitation [delivery / price / size choice], the third — a deadline\n[what exactly is limited].\nWrite only about what I listed. Don't invent discounts, free delivery, \"only 2 left\",\ntestimonials and ratings: if a mechanic requires such a block — put [filled in\nfrom data] and describe where the value comes from.\nFor each email: three subject line variants and a preheader, the text, one button with its label, the send time\nand the condition under which the email doesn't go out (order paid, item out of stock).","marketingTry5":"Compare prices for my items on Wildberries with competitors using MPStats data as of [snapshot date].\nMy SKU list: [article numbers or category].\nTreat a competitor as comparable only on a match of [category, volume/size, composition, brand segment].\nDon't compare different pack sizes and bundles with single items — move such pairs into \"not comparable\"\nand explain how they differ.\nFor each SKU show: my price before and after discount, the median and the price range of competitors, the difference\nin percent, my stock and competitors' stock, the search position for [key query].\nFlag items where I'm above the median by more than [10%] while orders are falling, and where I'm the lowest\nof all but sales aren't growing.\nOutput a table by SKU and a short list: where the price is worth revisiting and in which direction.","marketingTry6":"Rewrite the listings [article numbers] on [Ozon / Wildberries]: title, specifications and description.\nTake buyer queries for this category and distribute them across the fields: the main ones — into the title\nand the first specifications, the rest — into the description, without listing them comma-separated.\nWrite only from the specifications in the listing and from what I attached. Don't add composition,\ncountry of origin, warranty, certificates or product properties: if a field is empty, put\n[to clarify] and move it into the list of missing data.\nRespect the platform's field limits and don't repeat a single keyword more than [3] times.\nOutput for each article number: the title, a specifications table, the description text, the list\nof queries used and the list of fields I have to fill in myself.","marketingTry7":"Link spend in Yandex Direct with leads in Bitrix24 for [period] via [source field / utm],\nreconcile conversions against Metrica.\nFor each channel and campaign calculate: spend, number of leads in CRM, CPL, number of leads\nin statuses [qualified] and the cost of a qualified lead.\nSeparately show quality: duplicates, spam and rejections with reason [not relevant], the share of leads\nleft untouched for longer than [N hours].\nDon't distribute leads without a source across channels proportionally — keep them as a separate line\n\"source not identified\" with their share of the total.\nShow the discrepancy between conversions in Metrica and leads in CRM as a number, don't smooth it over.\nDon't include revenue and deals in this report.\nOutput a table by channels, a table by campaigns and three lines: where CPL grew, where quality\nfell at the same CPL, where leads aren't being worked.","marketingTry8":"Analyze the finished campaign [name, dates] in Direct and Metrica and propose [5] hypotheses\nfor the next launch. Goal of the next launch: [what matters more — volume or cost].\nLook where the potential sits: segments with good conversion and small reach, creatives\nwith high CTR and a weak landing page, times and geographies with different cost per goal, devices,\nsteps on the landing page where people drop off.\nFrame each hypothesis like this: what we change, which numbers from this campaign it's built on,\nthe expected effect as a range, how we'll test it and on what budget.\nDon't pass off as a finding something explained by random spread on a small sample, and don't fit\nthe explanation to a decision already made — if there isn't enough data for a conclusion, call it an idea\nfor a test, not a hypothesis.","marketingTry9":"Calculate the economics of a [discount size] promo on [article number / product] on [Ozon / Wildberries]\nfor [period].\nTake the current price and the platform commission, cost from 1C, logistics, storage,\nacquiring and [ad cost share] for this product. Calculate margin per unit now and with the discount, the break-even\nsales uplift in units and percent, and profit in three scenarios: sales [+X%], [+Y%], [+Z%].\nIf I didn't specify some cost item — don't take a market average, put it as a \"not accounted for\" line\nand show how it moves the result.\nSeparately calculate the cannibalisation effect: how many sales will shift from [adjacent article numbers]\nand what that means for profit across the group.\nOutput a scenario table, the loss point and one line: at what uplift the promo makes sense.","members":"Members","monthly":"Monthly","name":"Name","onboardingAllIntegrations":"All integrations","onboardingGoalsChipUnitEconomics":"Unit economics","open":"Open","orderDeclineCardExpired":"The card has expired.","orderDeclineCardInvalid":"The card details are invalid.","orderDeclineCardRestricted":"The payment was declined by your bank.","orderDeclineGeneric":"The payment was declined.","orderDeclineInsufficientFunds":"Not enough funds on the card.","orderDeclineIssuerUnavailable":"Your bank is temporarily unavailable.","organization":"Organization","password":"Password","pending":"Pending","planFree":"Free","planLeadInFree":"Everything in Free and:","planLeadInPro":"Everything in Pro and:","planMaxName":"Max","planProName":"Pro","planTeamName":"Team","popular":"Popular","privacyTitle":"Privacy Policy","productNavDesc":"Research, feedback, specs","productNavLabel":"Product","productTry1":"From the Ozon and Wildberries reviews for [period] collect only product change requests: what is missing,\nwhat people ask to add, what they ask to bring back. Do not take complaints about delivery, packaging and support\ninto this list — count them on a separate line and stop there.\nGroup the requests by meaning, not by wording. For each group: frequency, share of all reviews\nfor the period, [3] verbatim quotes, the SKUs where it occurs.\nDo not turn a one-off wish into a trend: keep groups with fewer than [5] mentions in the\n\"weak signal\" section rather than in the main list.\nOutput a table: request, frequency, share, quotes, SKUs.","productTry2":"Compare our product with [a list of competitors or links to their sites] on features and pricing, and put the result\nin a Google Sheet.\nFor each competitor: pricing plans and prices, what each includes, limits and restrictions, the stated\nintegrations, who they position themselves for.\nBack every price and every feature with a link to the page and the date you saw it. Whatever is not on\nthe site — write \"not published\": do not infer it from a neighbouring plan, do not silently convert an annual price\ninto a monthly one, and do not carry what reviews and roundups say into the table as a fact about the product.\nOutput a \"Matrix\" sheet (rows — features, columns — competitors), a \"Sources\" sheet and a bottom line:\nwhere we are more expensive and which features we lack.","productTry3":"Build a draft PRD from [links to meeting notes, tickets, documents] and put it in Google Docs.\nStructure: the problem and who it hurts, what has already been tried, use cases, functional\nrequirements, what is out of scope, success metrics, open questions.\nMark every requirement with its source — a link to the note or a quote. If a decision was not made in the notes,\ndo not make it for the team: move it into open questions as options and state who is responsible.\nTake only metrics we already know how to measure; for the rest write which data source\nis missing.\nDuplicate the requirements as a sheet in Google Sheets: number, wording, source, status.","productTry4":"Read the backlog tasks in [Yandex Tracker / Kaiten], queue [name], and score each one\nby impact and effort.\nCount impact by [revenue / churn / support load] and by the number of users affected;\neffort — by the team's estimate, if it is set on the task.\nApply the [1–5] scale identically to all of them and attach a key explaining what each score means.\nDo not assign a score where the task has no description: collect those in a \"nothing to score\" list\nstating which information is missing. Do not pass your own guess about task size off as the team's estimate —\nmark where the effort came from.\nOutput a table: task, impact, effort, the rationale for each score, quadrant — and the ten tasks\nworth taking first.","productTry5":"Collect the feedback from Telegram, email and Ozon reviews for [period] and sort it by a single taxonomy\n[list of topics — or propose your own and show it for approval before the analysis].\nOne taxonomy for all three channels: the same topic is named identically in each. Assign every message\nto exactly one topic; put the debatable ones in \"unclassified\" and show them separately\nrather than splitting them across two topics at once.\nThe channels differ in volume, so besides the count compute the topic's share within its own channel — compare\nshares, not counts. Do not add the channels together into one overall ranking.\nOutput a \"topic × channel\" table: count, share within the channel, two quotes each — and a list of topics\nthat exist in only one channel.","productTry6":"Go through the Telegram tickets and the Ozon and Wildberries reviews for [quarter] and identify the five main user pain points.\nRank them not by mention frequency but by cost: how many users are affected and what happened to them\nafterwards — [left / did not buy again / reduced their basket].\nState the effect on churn and repeat purchases only where you computed it from data you actually\nsaw: attach which rows the figure was built from and how many people are in the sample. Where linking a ticket\nto subsequent behavior did not work out — write \"effect not measured\" and leave the pain point in the list\nby frequency, instead of grading it with words like \"probably has an effect\".\nOutput five cards: the wording of the pain point, how many users are affected, [3] quotes, what happened to them\nafterwards — and, as a separate list, the hypotheses that the data does not confirm.","productTry7":"Break the feature [name and one or two sentences about its goal] into user stories and file them\nin [Yandex Tracker / Kaiten], in [queue or board].\nFor each story: the role, what they do, why; acceptance criteria as a list of checkable conditions;\nwhat is out of scope.\nSeparately go through the edge cases: empty state, external system failure, missing permissions,\nrepeated launch, cancellation midway.\nDo not invent requirements that are not in the description: where a decision has not been made, file a story\nmarked \"needs a decision\" with the question inside, rather than your own assumption presented as a requirement.\nOutput a list of stories with the dependencies between them and the order in which it makes sense to do them.","productTry8":"Build the week-by-week dynamics of negative reviews on Ozon and Wildberries for [period].\nCount [1–2 stars] as negative.\nFor each week: the share of negatives among all reviews that week, the number of reviews, a breakdown by complaint topic.\nCount the share specifically: growing sales lift the number of reviews too, and that in itself is not\na rise in negativity.\nMark the dates [list of shipped fixes] and for each topic show the share before and after. If less than\n[3] weeks have passed since the date or the week has fewer than [20] reviews — write \"too early to judge\"\nand do not call it an improvement.\nOutput a week-by-week table, a breakdown by topic and a list of topics where the share of negatives has grown for the third\nweek in a row.","profile":"Profile","pulsePetNameBear":"Bear","pulsePetNameBunny":"Bunny","pulsePetNameCat":"Cat","pulsePetNameCrab":"Crab","pulsePetNameFatcat":"Chonk","pulsePetNameFox":"Fox","pulsePetNameGenBear":"Bear","pulsePetNameGenBunny":"Bunny","pulsePetNameGenCat":"Cat","pulsePetNameGenCrab":"Crab","pulsePetNameGenFatcat":"Chonk","pulsePetNameGenFox":"Fox","pulsePetNameGenPanda":"Panda","pulsePetNameGenPenguin":"Penguin","pulsePetNamePanda":"Panda","pulsePetNamePenguin":"Penguin","reauthReasonAuthRejected":"The provider rejected the saved credentials","reauthReasonBotRemoved":"The bot was removed from the chat","reauthReasonDeliveryFailed":"Message delivery failed — reconnect required","reauthReasonOauthRefreshFailed":"Could not refresh the access token","reauthReasonRefreshEgressUnreachable":"The provider was unreachable during token refresh","relatedGuidesHeading":"Guides on this topic","remove":"Remove","renewalOffUntil":"Active until {date}, won't renew","resLinkAiAgents":"AI agents for business: what they are","resLinkAiBusiness":"AI for business: which solution to choose","resLinkAmocrm":"How to connect AI to amoCRM","resLinkAnalytics":"AI for marketplace analytics","resLinkBitrix":"How to connect AI to Bitrix24","resLinkBitrixAgents":"Best AI agents for Bitrix24","resLinkCards":"Optimizing WB and Ozon listings with AI","resLinkConnectors":"How to connect your business to AI: integration catalog","resLinkDashboard":"AI for sellers: dashboard, generator, agent","resLinkDocs":"AI for completion certificates and month-end paperwork","resLinkDocsFeature":"AI for documents: creation and recognition","resLinkGeo":"What is GEO, explained simply","resLinkIntegration":"{name} integration","resLinkIntegrationsCrm":"CRM integrations","resLinkIntegrationsHub":"Integration catalog for business","resLinkIntegrationsMarketplaces":"Marketplace integrations","resLinkMango":"AI for Mango Office telephony","resLinkMoysklad":"How to connect AI to MoySklad","resLinkOzon":"How to connect AI to Ozon","resLinkPriceAuto":"Automated repricing with AI","resLinkPricing":"AI pricing on marketplaces","resLinkReviews":"Auto-replies to Wildberries and Ozon reviews","resLinkRuAssistants":"Top Russian AI agents for business","resLinkSellerAuto":"How a seller can automate their business with AI","resLinkTopReviews":"10 review auto-reply services","resLinkTranscript":"AI speech analytics for calls","resLinkVsZapier":"AI agent or Make, Zapier, n8n","resLinkWb":"How to connect AI to Wildberries","retryCooldown":"Retry in {seconds} sec","salesNavDesc":"Leads, follow-up, quotes, forecast","salesNavLabel":"Sales","salesTry1":"Go through the new leads in Bitrix24 for [period — yesterday / the last 24 hours / since the last triage].\nFor each: source, what they're asking for, budget ballpark, region, contacts, whether this company is\nalready in CRM.\nAssign priority by the rules: [budget above threshold / target industry / repeat enquiry].\nIf there isn't enough data for priority — don't infer it from the company name and email domain,\nmark it \"not enough data\" and leave it in the general queue. Flag possible duplicates of open deals,\nbut don't merge them.\nOutput a table: lead, priority, suggested owner, deadline for first contact.\nAs separate lists — duplicates and leads without contacts. Create tasks only after\nI confirm the list.","salesTry2":"Build a proposal for deal [number or deal name in Bitrix24],\nusing template [link to document].\nTake the legal details, contact person and scope of work from the deal card, prices — from [price list],\npayment terms and the discount — by the rules: [rules].\nDon't fill blanks with plausible text: if CRM has no deadline, volume or contact\nperson — leave a [to clarify] marker in the document and collect all such spots in a separate list at the end.\nDon't round or recalculate prices yourself.\nOutput — a document following the template's structure, without extra blocks, followed by a list\n\"what to clarify before sending\".","salesTry3":"Find open deals in Bitrix24 that have no active task or no activity for longer\nthan [N] days, across pipelines [list of pipelines].\nFor each: amount, stage, owner, date and type of the last contact, date of the nearest task,\nif there is one.\nCount as contact only real activity — a call, an email, a meeting, a comment.\nDon't count a stage change or an automatic field update as contact and don't use it as a sign\nthat the deal is alive.\nGroup by manager, and within that by amount. Separately pull out deals with no owner\nand deals whose close date has already passed.\nAt the end — how many deals in total and for what amount are stuck.","salesTry4":"Find deals in Bitrix24 where a proposal was sent more than [N] days ago and there's no reply from the client,\nand prepare a draft follow-up email for each.\nBefore the email, gather the context: what was in the proposal, what was agreed on the last call,\nwhich objections have already come up.\nTake the reason for writing from the communication history. If there's nothing in the correspondence to hook onto — don't invent\nthe client's interest and don't refer to a conversation that never happened, write a short neutral email\nand mark it \"no context\".\nDon't offer discounts or new terms — only [permitted reasons].\nOutput a table: client, amount, days of silence, email subject — and the text of each email\nup to 120 words as a draft, without sending.","salesTry5":"Build the [quarter] sales summary from Bitrix24 and amoCRM and compare it with [the previous period].\nGive plan versus actual on revenue overall and by [breakdown — line of business / manager / region]: plan,\nactual, variance.\nFor each manager: closed amount, number of deals, average deal size, share of the total actual.\nSeparately — the five largest won and five lost deals with the stated loss reason.\nDon't add up deals from the two systems until you show that their stages and statuses are comparable;\ncount what isn't comparable separately and say so.\nBuild the forecast for the next quarter from open deals with a close date inside it, honestly\nstating the share of deals with no date.\nOutput XLSX: \"Plan vs actual\", \"Managers\", \"Deals\", a totals line.","salesTry6":"Find open deals in Bitrix24 and amoCRM above [threshold] that have been sitting at their stage\nlonger than the norm: [stage — period; stage — period].\nFor each deal: amount, stage, how many days it's been sitting, owner, last contact,\nwhose court the ball is in — ours or the client's.\nTake the reason it stalled from comments and correspondence. If it isn't there — don't infer the reason\nfrom the stage and the amount, write \"reason not recorded\" and set \"find out the status\" as the first action.\nFor each deal propose one specific action for this week and state what you need from me.\nDon't calculate stage conversion percentages — a list of deals is what's needed.\nSort by amount, with what can be closed before the end of [the period] on top.","salesTry7":"Assemble the sales summary for the past week from Bitrix24 and send it to Telegram\n[day and time].\nIn the summary: closed amount and number of deals versus last week, movement on large deals,\nnew leads and how many of them were picked up.\nFor each manager — a short line: closed, in progress, activity.\nSeparately name the areas of attention: whose result is falling for the second week running, who has no\nsingle contact on large deals, where the week fell outside the usual range.\nDon't call a one-off dip or spike a trend until it has repeated twice.\nKeep the summary to [15] lines: details — as a separate file on request.","salesTry8":"Reconcile the payment promises from Bitrix24 deals against actual receipts in 1C as of [date]\nand find clients with no payment for longer than [N] days.\nFor each: the promised date and amount, who recorded it and when, what actually arrived,\nhow many times the deadline was pushed, the date of the last conversation, the owning manager.\nLink client and payment by legal details. If a payment arrived without a link to a deal —\ndon't assign it to the nearest one by amount, move it into \"unidentified payments\".\nDon't reconstruct promises that aren't in CRM by logic: write \"agreement not recorded\".\nSort by amount. For each client propose the next step: a call, an email, escalation\nor handover to receivables collection.","samreshuuu":"samreshuuu","search":"Search","securityNavLabel":"Security & 152-FZ","securityNavLabelGdpr":"Security & GDPR","sellersAgentVsAgentHeading":"Samreshuuu","sellersAgentVsDashboardHeading":"Dashboard","sellersAgentVsRow1Agent":"Finds SKUs leaking margin and proposes the fix","sellersAgentVsRow1Dashboard":"Shows yesterday's margin","sellersAgentVsRow2Agent":"Rewrites titles, refreshes infographics, uploads to WB and Ozon","sellersAgentVsRow2Dashboard":"List of listings with low CTR","sellersAgentVsRow3Agent":"Recalculates bids nightly against target margin","sellersAgentVsRow3Dashboard":"ACoS chart by campaign","sellersAgentVsRow4Agent":"Builds the supply order and pulls free FBO slots","sellersAgentVsRow4Dashboard":"14-day stock forecast","sellersAgentVsSubtitle":"MPStats, SellerBoard, and UnitSeller draw charts. Samreshuuu is full marketplace automation: it edits listings, tunes bids, and builds supply on its own, by your rules.","sellersAgentVsTitle":"Dashboards show. The agent acts.","sellersChapter1Body":"Price − commissions − logistics − returns − ads − penalties. Per SKU, every day — no Excel exports, no manual rate reconciliation.","sellersChapter1Label":"Unit economics","sellersChapter2Body":"Title, attributes, infographics — derived from top-competitor analysis. Bids in campaigns are recalculated nightly from target margin; disputed edits go up for confirmation. The agent handles customer reviews on its own: replies in your brand's tone and escalates complaints with product photos.","sellersChapter2Label":"Listings and ads","sellersChapter3Body":"Sales velocity × seasonality × delivery ETA. Tells you what to ship and where — with a link to free FBO slots.","sellersChapter3Label":"Stock and supply","sellersChapter3Title":"Plans replenishment before stock runs out","sellersDemoActionCalendar":"Payment calendar","sellersDemoEyebrow":"Product interface","sellersDemoSubtitle":"One request — a finished result, not advice. Pick a task.","sellersDemoTab1Body":"Pulled unpaid orders from MoySklad, grouped them by supplier and calculated overdue amounts — in seconds, with no Excel exports.","sellersDemoTab1Headline":"Supplier debt — 137,688 ₽ across 18 orders","sellersDemoTab1Label":"Supplier debts","sellersDemoTab1Prompt":"Build a payables report for suppliers as of [date] using [MoySklad / 1C] data\nand the account balances from Tochka.\nFor each supplier: the amount owed, which delivery documents it consists of, the payment term\nfrom the contract, days past due, the date and amount of the last payment.\nTake the term from the contract or the delivery terms. If the term isn't filled in — don't assume the usual\n14 days, move the supplier into a \"term not defined\" list.\nSpread the payments across the days of [period] so that the balance covers each day. If it doesn't —\nshow the day and the size of the gap instead of silently trimming the amounts.\nOutput an XLSX: a \"Payment queue\" sheet with date, amount and the reason for the priority, a\n\"Deferred\" sheet and a total line — how much is due and how much money is available.","sellersDemoTab1Subline":"4 suppliers, 6 overdue orders. First — Severles.","sellersDemoTab1Title":"“How much do we owe and who to pay first”","sellersDemoTab2Label":"Unit economics","sellersDemoTab2Title":"“What's the margin per SKU”","sellersDemoTab3Label":"Listings and ads","sellersDemoTab3Title":"“Run listing optimization overnight”","sellersDemoTitle":"Samreshuuu in action","sellersFaqA1":"From your marketplace personal account via API. This is your real data, not parser estimates. You connect an API key — the agent works only with your account.","sellersFaqA2":"No. Setup takes 5 minutes: create an account, add your marketplace API key in the integrations section, and start asking questions in chat.","sellersFaqA3":"Yes. Servers in Russia, data is encrypted, FZ-152 compliant. Not shared with third parties or used for model training.","sellersFaqA3Gdpr":"Yes. Servers in the EU/EEA, data is encrypted, GDPR-compliant. Not shared with third parties or used for model training.","sellersFaqA4":"No. Wildberries, Ozon, and Yandex Market are already connected. Data can be analyzed cross-platform — in a single chat.","sellersFaqA5":"There's a free tier to get started. Paid plans start from {pricePro}/month — with full access to analytics, listing generation, and automated review responses.","sellersFaqA6":"It's not a dashboard with charts, but AI for marketplaces in agent form — you ask questions in plain language and get answers with conclusions. Plus the agent can generate product listings, respond to reviews, and recommend actions.","sellersFaqA7":"Yes. Connect multiple WB, Ozon, and Yandex Market accounts to one profile. Cross-platform analytics — compare metrics across all stores in a single chat.","sellersFaqA8":"Marketplace analytics in one chat: sales, returns, commissions, logistics, ad campaigns, warehouse stock, customer reviews. Data is auto-updated via marketplace APIs.","sellersFaqA9":"Yes. The agent reads customer reviews and writes replies in your brand's tone, escalating complaints with product photos — on Ozon, Wildberries and Yandex Market. Anything uncertain goes to you for approval.","sellersFaqHeading":"FAQ","sellersFaqPointer":"Where the data comes from and how access is protected — separately:","sellersFaqPointerLink":"perimeter and security","sellersFaqQ1":"Where does my sales data come from?","sellersFaqQ2":"Do I need a developer to set it up?","sellersFaqQ3":"Is my data secure?","sellersFaqQ4":"Does it only work with Wildberries?","sellersFaqQ5":"How much does it cost?","sellersFaqQ6":"How is it different from MPStats, SellerBoard, and similar tools?","sellersFaqQ7":"Can I connect multiple stores?","sellersFaqQ8":"What analytics for Wildberries and Ozon are available?","sellersFaqQ9":"Can it auto-reply to reviews on Ozon and Wildberries?","sellersFinalSubtitle":"WB, Ozon, Yandex Market — via API, no Excel exports, no data migration.","sellersFinalTitle":"Connect your seller account — and ask the agent","sellersHeroGhost":"All integrations","sellersHeroSubtitle":"AI for marketplaces: connect your seller account — the agent breaks down unit economics per SKU, catches charge errors, and builds a stock plan. Not a dashboard — an agent that does the work.","sellersHeroTelegram":"Ask stock or margin straight from Telegram — answer in seconds","sellersHeroTitle":"AI assistant for WB and Ozon sellers — computes margin, edits listings, builds supply.","sellersIntegrationsHeading":"Connect in 5 minutes — OAuth or API key.","sellersIntegrationsLink":"All integrations","sellersNavDesc":"Unit economics, listings, reviews","sellersNavLabel":"Sellers","settings":"Settings","signup":"Sign up","sitemapTrust":"Trust & safety","skillCatalogAll":"All","skills":"Skills","solSectionFaq":"FAQ","sourcesLabel":"Sources","status":"Status","statusAutoPaused":"Auto-paused","statusBlocked":"Blocked","statusCanceled":"Canceled","statusCiRunning":"CI running","statusCompleted":"Completed","statusDeferred":"Deferred","statusDegraded":"Partly degraded","statusFailed":"Failed","statusIdle":"Idle","statusNeedsInput":"Needs input","statusNeedsReconnect":"Awaiting reconnect","statusNoChange":"No change","statusPaused":"Paused","statusPausedPlanTooltip":"Paused: no active plan and zero balance · resumes automatically after a top-up","statusPausedQuotaTooltip":"Paused: quota exhausted · top up to resume automatically","statusPausedWeeklyTooltip":"Paused: weekly allowance used up · upgrade to resume automatically","statusPrOpen":"PR open","statusRunning":"Running","statusScheduled":"Scheduled","statusSleeping":"Sleeping","statusSystemAborted":"Stopped by the system","statusUndelivered":"Not delivered","supportNavDesc":"Requests, reviews, knowledge base","supportNavLabel":"Support","supportTry1":"Go through the tickets from Telegram, Avito and email that arrived between [shift close time] and [opening\ntime], and assemble a queue for the morning.\nPut the urgent ones on top: [payment went through, goods never arrived / repeat ticket about the same problem /\nthreat of a complaint or a return]. Below them — questions about availability and delivery times.\nAttach a draft reply to routine tickets. If the reply needs an order status that is not in the correspondence,\ndo not guess it — put [check in 1C] and leave the ticket for an operator.\nOutput a list: time, channel, customer, substance in one line, urgency, draft or \"needs a human\".","supportTry2":"Write replies to new Ozon and Wildberries reviews for [period] following the tone rules from [the attached\nfile / the examples below].\nSplit the reviews into three groups: reply with a template, reply individually, do not reply —\nand for each group name the signal you used to decide.\nIn the reply, state the substance of the complaint in your own words, do not open with \"thank you for your review\".\nDo not promise deadlines, refunds, discounts or replacements — nobody has confirmed those. Where the customer directly\nasks for goodwill compensation, leave [operator decision] in the text and move the review into the \"for a human\" group.\nOutput a table: review, rating, SKU, group, reply text, what to fill in by hand.","supportTry3":"Watch new reviews on Ozon and Wildberries and flag only what threatens the rating.\nThreshold: rating [1–2]; or [3] and below for an SKU from the list [priority SKUs]; or [2] negative\nreviews on one SKU within [24 hours]; or the words [defect, scam, swap, court, consumer protection agency].\nOne review — one alert, do not write about the same one twice.\nDo not raise an alarm for a rating without text or for a review about the marketplace's delivery — collect those in a separate\nsummary once per [period].\nIn the notification: SKU and name, rating, date, the full quote from the review, the listing's current rating\nand how much it moved, how many reviews this SKU got in [7 days].","supportTry4":"Go through the customer complaint from [the Telegram correspondence / the email] and propose goodwill compensation strictly\nby the rules in [the attached file].\nFirst pull out the facts: what was bought and when, what went wrong, what the customer asks for verbatim, which\nticket this is in order. Whatever is not stated in the correspondence — mark \"not specified\", do not fill it in.\nThen find the matching rule clause and name its number. If no clause fits or the amount\nexceeds the limit — say so, propose the closest option within the rules and send the case\nfor approval instead of stretching the rule yourself.\nIn the draft reply do not promise deadlines, refunds or replacements beyond the chosen clause.\nOutput: facts, rule clause, proposal, draft letter.","supportTry5":"Collect the recurring questions from tickets in Telegram, Avito and email for [period] and turn them\ninto knowledge base articles.\nGroup by the meaning of the question, not by matching words: \"when will it arrive\" and \"where is my parcel\" are one article.\nTake only topics that occurred at least [N] times, put the rest in a \"rare\" list.\nThe title uses the customer's wording, the answer comes from real operator replies with a link\nto the source ticket. Where operators answered differently, do not pick the correct version yourself:\nshow both answers and mark the article \"needs a decision\".\nOutput articles with the fields question, answer, source, ticket count — in descending order of frequency.","supportTry6":"Sort the tickets from Telegram, Avito and email for [period] by topic and count the load by week.\nTake the classifier from [the attached list of topics] or build your own and show it to me before the analysis.\nOne ticket — one topic; a conversation stretching over several days counts once, by the date of the first\nmessage.\nFor each topic: tickets per week, change against the previous week, distribution by day of week\nand by hour [time zone].\nA spike caused by a promotion, an outage or holidays goes on a separate line and is not mixed into the trend.\nOutput a \"topic × week\" table, a \"day of week × hour\" table and the three fastest growing topics.","supportTry7":"Merge the new messages from Telegram, Avito and email for [period] into a single queue.\nMerge messages from one customer into a single thread by [phone / email / order number]. If only the name\nmatched — do not merge: keep the rows separate and add a \"possible duplicate\" flag.\nSet the order like this: the primary key is [waiting time], with equal waiting time these go higher: [repeat\nticket / mention of payment or a refund / customer with status X].\nDo not write replies: each row contains only the substance of the ticket in one phrase.\nOutput a queue: time of the first message, how long it has waited, channel, customer, substance, priority\nand the condition it was assigned by.","supportTry8":"Build reply templates from the Telegram and email correspondence for [period].\nIdentify the situations that occurred at least [N] times, and write a template for each in the tone\nfrom [the attached examples].\nEverything that changes case by case — name, order number, deadline, amount — stays as a field\n[in square brackets]; do not fill in a typical value, or the operator will send someone else's deadline.\nDo not write deadlines, refunds, discounts and goodwill compensation into the text: put a field [decision per the rules]\nand note who is entitled to fill it in.\nFor each template: when to use it, when not to use it, what to fill in.\nOutput a table of templates in descending order of situation frequency.","syncStateError":"Sync error","syncStateRetry":"Retry","syncStateSaving":"Saving…","syncStateSynced":"Synced","tasksSearchPlaceholder":"Search tasks","team":"Team","ucCashFlowPrompt":"Build a cash flow statement for [period] using 1C and bank data.\nAssign all receipts and payments to three sections: operating, investing, financing\nactivities. For each section — line items with amounts, inflow, outflow and net flow; above\nand below — the cash balance at the start and end of the period.\nDon't count transfers between our own accounts or currency conversion as either a receipt or a payment.\nIf the activity type for an operation isn't obvious, don't default it to operating —\nmove it into \"needs classification\" with the amount and the payment description.\nOutput an XLSX: a \"Cash flow statement\" sheet by section, a details sheet with links to the operations, and a control\nline — does the closing balance agree with the bank statement.","ucCategoryRecipesHeading":"Ready-made use cases","ucClosingDocsPrompt":"Assemble the month-end document package for [month] using 1C, Diadoc and email data.\nFor each customer, match the sale or service rendered against the acceptance certificate, the UPD\nand the VAT invoice: what is signed by both sides, what was sent and is hanging unsigned,\nand what is missing altogether.\nA document sent via EDI and not signed by the customer does not count as received —\nthat's a separate status, not a closed position.\nDon't fill a gap with a similar document from an adjacent month: if the number and date don't agree\nwith the sale, mark it \"not matched\".\nOutput an XLSX: a customer sheet with the status of every document, a \"missing\" sheet\nwith amounts, and draft letters to the customers on that sheet — one letter per customer.","ucDebtorRemindPrompt":"Prepare three payment reminder texts and a schedule for sending them to the debtors from 1C.\nThe first — [three] days before the due date, neutral: amount, invoice numbers, payment date.\nThe second — on day [seven] past due, specific: how many days are overdue and what happens next.\nThe third — on day [thirty], formal: referencing the contract clause on late payment penalties.\nTake amounts and document numbers only from 1C. If a customer has an unallocated payment\nor a dispute over an acceptance certificate — don't send the letter, move them into a \"human first\" list.\nDon't calculate penalties in the text if the rate isn't filled in in the contract: write \"in accordance\nwith the contract\".\nOutput three templates with placeholders, a sending rule for each and a list of exceptions.","ucDiffEasy":"Easy","ucDiffHard":"Hard","ucDiffMedium":"Medium","ucDsoPrompt":"Calculate receivables turnover for [period] broken down by [months /\nquarters] using 1C data.\nGive company-wide figures: turnover in times, average days sales outstanding, average receivables\nfor the period. Then the same metrics per customer and by groups [wholesale / retail / chains].\nCalculate the average balance from monthly snapshots, not from the start and end of the period. If a customer has\nfewer than [three] shipments in the period, don't average their payment days — mark it \"not enough data\".\nDon't explain a change in the metric by seasonality or sales growth until you show the figures\nthat confirm it.\nOutput a Google Sheets table: company-wide dynamics, the customer breakdown, and a\n\"not enough data\" column.","ucEdoInboxPrompt":"Process the incoming documents from Diadoc for [period] and match them against the orders and contracts in 1C.\nFor each document: type, supplier, number, date, amount, EDI status, the order\nor contract found. Sort into groups: full match, price differs, quantity or item\ndiffers, details don't match the record, no order found, document not posted in 1C.\nTreat a discrepancy as significant from [deviation] — flag anything smaller but don't escalate it.\nDon't match items by similarity of the name: if the SKU or code doesn't match, write\n\"not matched\" instead of picking the nearest item.\nOutput a table of documents indicating where each figure came from, and a separate list of\ndocuments awaiting signature for longer than [deadline].","ucExcelDashPrompt":"Build a sales dashboard for [period] in [Google Sheets / XLSX] on 1C data.\nArrange the file like this: a \"Source\" sheet — a flat table with no merged cells and a date column\nin a single format; a \"Summary\" sheet — pivot tables by [breakdowns]; a \"Dashboard\" sheet — charts and slicers\ntied to the pivots rather than to the source directly.\nSet the pivot ranges as whole columns or named ranges so that nothing shifts when a new export\nhas a different number of rows.\nDon't hard-code calculated values into the dashboard cells: every figure must be recalculated\nfrom \"Source\".\nOn a separate \"How to refresh\" sheet describe: where to paste the new export, what to click\nand what breaks if the column order in the export changes.","ucFilterAll":"All","ucFreqBiweekly":"once every two weeks","ucFreqDaily":"every day","ucFreqMonthly":"once a month","ucFreqOnEvent":"on an event","ucFreqOneTime":"set up once","ucFreqQuarterly":"once a quarter","ucFreqWeekly":"once a week","ucPnlBest1":"Month-end close: company profit is known, but the per-unit split gets rebuilt in Excel every time.","ucPnlCheck":"Review your P&L. List:\n— line items assigned to a unit by payment description rather than by the analytics in 1C;\n— costs that landed in \"not allocated\" and why no base was found for them;\n— documents posted within the period but belonging to the previous month;\n— units that have revenue but no direct costs — that doesn't happen;\n— intercompany turnover between units: did you net it out or count it twice.\nWhatever you can recalculate yourself, show as a \"proposed changes\" list; leave debatable analytics to me.","ucPnlInputs":"You'll need 1C and the Tochka bank feed. From you: the period, the list of units and how to split shared costs — rent, accounting, management.","ucPnlStep1Title":"Name period and units","ucSbisActPrompt":"Generate a reconciliation statement with [counterparty] for [period] in SBIS and check it against the settlements in 1C.\nMatch line by line: date, document, debit, credit. Collect separately the lines that we have\nand the counterparty doesn't, that the counterparty has and we don't, and those that match on the document\nbut differ on the amount.\nDon't level out differing balances by fudging: the discrepancy must break down into specific\nlines, and if it doesn't, say so.\nTake the document's SBIS status into account: sent, signed, rejected, cancelled — an unsigned\ndocument cannot be treated as agreed.\nOutput the statement in the standard form, a line-by-line discrepancy sheet indicating the side and the status,\nand the closing balance from both sides.","ucTaskAnalysis":"Analysis","ucTaskAutomation":"Automation","ucTaskContent":"Content","ucTaskDocuments":"Documents","upgrade":"Upgrade","upload":"Upload","useCasesHubAll":"All use cases","useCasesHubEyebrow":"Use cases","wfChannelEmail":"Email","wfChannelInbox":"In app","wfChannelPush":"Push","wfScheduleByDays":"{days} · {time}","wfScheduleDaily":"Daily · {time}","wfScheduleEveryHour":"Hourly","wfScheduleEveryHours":"Every {n}h","wfScheduleEveryMinutes":"Every {n}m","wfScheduleMonthly":"Day {day} · {time}","wfScheduleWeekdays":"Weekdays · {time}","wfScheduleWeekends":"Weekends · {time}","wfTriggerEventAny":"Any event in {service}","wfTriggerEventPhrase":"When {event} in {service}","wfTriggerManual":"On-demand","wfTriggerSchedule":"Schedule","wfTriggerWebhook":"On event","wfWeekdayFri":"Fri","wfWeekdayMon":"Mon","wfWeekdaySat":"Sat","wfWeekdaySun":"Sun","wfWeekdayThu":"Thu","wfWeekdayTue":"Tue","wfWeekdayWed":"Wed","workspace":"Workspace","yearly":"Yearly"}