Learn

Seller cases, product stories, and how-tos — all in one place

All

Post

Release

Case

Press

All topics

Marketplaces

CRM & calls

AI trends

PostSamreshuuuSeptember 15, 2026

How to choose an AI agent for your business without giving it too much: a checklist on data, access and 152-FZ

Even OpenAI calls the mode where its Codex agent does everything without asking dangerous. An agent with access to your accounts carries more risk than a chatbot. Here is what Russia's 152-FZ requires from a company adopting AI, plus a 20-question vendor checklist on data, access, actions and honesty: the good answer and the red flag based on how real agents are built, and a half-hour hands-on test.

PostSamreshuuuSeptember 14, 2026
Don't pay for people who log in once a month: five free seats in an AI agent for your team
The CRO of Databricks says per-user pricing is a thing of the past: once a company pays for every person, it starts deciding who is allowed in, and usage drops. In a small business this is even sharper: an owner won't buy a seat for the accountant who logs in twice a month. Here is how much an AI agent for a team costs at Samreshuuu: a paid seat for whoever works with it daily, up to five free seats for everyone else, and the rule that turns one into the other.
PostSamreshuuuSeptember 12, 2026
An overnight task: handing an AI employee work that runs while you sleep, and waking up to a result rather than a surprise
The author of Bun leaves an agent overnight with one sentence: "I'm going to sleep, in the morning I want to see result X". We translate the trick into a business owner's language: can an AI run tasks inside your Ozon account and 1C without you, how an overnight task differs from a chat and from an AI agent on a schedule, how to name a result that is checked in a minute, where the report arrives in Telegram and what arrives on the way, where the agent must stop on the irreversible and why everything irreversible goes into drafts. With a ready task text for a MoySklad-to-Ozon stock reconciliation.
PostSamreshuuuSeptember 8, 2026
AI in Excel: three kinds of helpers, and why a wrong number does not come from a formula
How an assistant inside Excel differs from a chat with an uploaded file and from an agent that reads the accounting system and marketplace accounts itself; three causes of a wrong number (ambiguity, staleness, a similar column); a three-sheet file that survives the next export; a scheduled task with blanks instead of zeros; the check before the Monday meeting and three scenarios people start with.
PostСам РешуSeptember 7, 2026
How to connect AI to MoySklad: stock, cost prices, and purchase orders
Samreshuuu connects AI to MoySklad with an employee API token: the agent calculates stock, dead stock, margin and shortages by the rule you described in plain words and carries the job through to a draft purchase order. A walkthrough: four ways to connect AI to MoySklad — a connector wrapper, built-in reports, a custom script and an AI agent — how their outcomes differ, and seven places where a MoySklad integration returns a successful response with a wrong number.
PostSamreshuuuSeptember 4, 2026
An AI agent failed halfway through a task: how to resume without doing it twice
What happens when 1C has created an invoice but its response is lost: how checkpoints, heartbeats, idempotency keys, and an audit log help an agent resume after failure, avoid a duplicate write, and stop when the outcome cannot be proved.
PostSamreshuuuSeptember 3, 2026
Your accounting system sees the debt but can't collect it: where the report ends and the agent begins
Every accounting system has a "who owes us money" report, and almost nobody works from it. Why: the amount is a number, but the reason for non-payment is text, and it lives in the contract, the reconciliation act and the correspondence. Where the report ends, where an AI agent begins, and where it has to stop and ask a human.
PostSamreshuuuSeptember 2, 2026
Automating routine work: handing an agent the job that repeats every week
How to turn repeating work into a scheduled task: choosing between a schedule, a manual run and a skill; the "do it once, then put it on Monday" shortcut; the six lines a task's text is made of, with a before-and-after example; five rules (one account per task, thresholds instead of feelings, a watchdog's right to stay silent); reverse delegation; and why tasks are edited rather than rewritten.
PostSamreshuuuAugust 31, 2026
AI's third era: from chat to a coworker who stays
In the last week of August the industry described one shift three times over: AI is ceasing to be a window you bring questions to and becoming someone who stays between your visits. A walk through the three eras — chat, copilot, coworker — and what persistence is actually made of: memory, harness, access and the autonomy step, not one of which is the model. Plus the background schedule hour by hour, the rule that a number on the screen is always a number off a row, why silence must be distinguishable from death, and Mollick's four reasons to call a human.

How to choose an AI agent for your business without giving it too much: a checklist on data, access and 152-FZ

Don't pay for people who log in once a month: five free seats in an AI agent for your team

An overnight task: handing an AI employee work that runs while you sleep, and waking up to a result rather than a surprise

AI in Excel: three kinds of helpers, and why a wrong number does not come from a formula

How to connect AI to MoySklad: stock, cost prices, and purchase orders

An AI agent failed halfway through a task: how to resume without doing it twice

Your accounting system sees the debt but can't collect it: where the report ends and the agent begins

Automating routine work: handing an agent the job that repeats every week

AI's third era: from chat to a coworker who stays

Archive