Frequently asked questions
All questions · 16
Everything about LenSA, the 1C query console: what the purchase includes, how coins work, whether it runs on your configuration, and what happens to your data.
Can't find your question — ask it at the end of this page or write to support@digitalmechanics.ru: we'll look into it and extend this section. If you'd like to share your impressions rather than ask something, there's a review form on the product page.
Buying and installing
Can I see how it works before buying?
There is no trial version yet — we're preparing one, and it will be available right after registration, with no payment required. A button will appear here as soon as that happens.
For now you can get a feel for it from the video demos and screenshots on the product page: they show real scenarios — the assistant building a query against a configuration, refining an existing one, and answering questions about the result.
How do I install and activate the console?
After payment your account will contain the .epf data processor and your API key — a personal
access code to the AI service, much like a long password.
The steps are:
- Download the data processor from your account and open it in 1C via "File → Open" (or add it to additional data processors).
- In the chat header, click the connect button and paste the API key.
- Click "Sign in" — the key is verified on the server, the list of available models and your balance load, and the chat unlocks.
The key is stored in the information base where you entered it, so you won't need to retype it there. In a different base the console will ask for the key again: enter the same one — a single key covers all your workstations and bases.
What exactly am I buying: the data processor or AI access?
Both, and they are separate.
The .epf data processor is the query console itself: the query builder, the editor with
syntax highlighting, parameters, temporary tables, result drill-down, background execution and
export to Excel. It is yours permanently and works without an internet connection and without
coins.
The API key is access to the AI assistant that writes and refines queries. Assistant requests are paid for in coins.
Hence a simple rule: without coins the console remains a full console, just without the AI helper. Starting coins are credited with the purchase — the amount is stated on the product page.
What are coins, and why do models cost differently?
Coins are the single currency for AI assistant requests. Each request spends coins at the rate of the model you selected in the chat.
Orders of magnitude matter more than theory. A typical configuration query on a mid-range model (Claude Sonnet) costs about 800 coins. A large task such as assembling a report on a fast model (Gemini Flash, 7.8M tokens of processed context) costs about 7,000 coins for work that would take hours by hand.
Why there is no flat price per request. Models are billed for the volume of text they read and wrote, and that depends on the task: "add a manufacturer field" and "build a full-year settlements report" differ by orders of magnitude. That's why pricing lists rates rather than a price per item.
Why models cost differently. These are the AI providers' own prices: higher-tier models reason longer and cost more for the same volume. The spread between the entry-level and the top model is several-fold, and it is the main lever on your spending — far bigger than the length of your question.
Practical advice. Start a task on smaller models and move up only when a model can't cope. A common mistake is reaching for the most expensive model right away "to be safe" and overpaying where a smaller one would have done the job. The full model table with rates is in pricing.
Your balance is visible in the chat header and in your account, where packs are also purchased.
How many workstations does the purchase cover?
There is no limit on the number of workstations: install the data processor for everyone who needs it and use a single key.
That said, a personal purchase is preferable. It comes with support and updates, and updates ship constantly — a buyer receives fresh versions, whereas a passed-along copy falls behind over time.
Will it run for me
Which 1C versions and configurations are supported?
Any configuration — standard or custom — on the 1C platform 8.3.16 or newer in managed forms mode, with a file-based or client-server database. The 1C client must run on Windows, 32- or 64-bit; Linux is not supported yet, it is on the roadmap.
Background query execution relies on the Standard Subsystems Library or a configuration extension — the extension installs from the link in the form header.
The full list with versions and addresses is on the technical requirements page.
Will it work in a closed network or behind a proxy?
The console needs outbound HTTPS to a single address — the LenSA API: model requests, key validation, balance and updates all go through it. Proxies are supported: platform settings, your own HTTP proxy, or a direct connection.
If your network is closed, hand your administrator the technical requirements page — it states the exact address and provides a ready-made PowerShell command that verifies access from the user's workstation. One detail that matters for firewall rules: allow the domain name, not a fixed IP — the infrastructure address may change.
The AI assistant cannot work fully offline: the models live on the providers' side. The console itself works without an internet connection.
1C shows a "Security warning" when opening — is that normal?
Yes, that's the platform's standard "Protection against dangerous actions", not a sign of trouble.
There will be two warnings: when the console opens — the built-in code editor is a full web editor, and 1C asks permission for its service files — and on your first message to the AI chat. Click "Yes": subsequent openings of the same version won't ask again.
If the editor fails to load for some reason, the query can be typed in a plain text field — your work isn't blocked.
How it works and what it costs
How is this different from just asking a neural network directly?
The assistant sees your configuration; a chat does not.
- Exact names instead of guesses. The assistant explores the structure of your specific database — catalogs, documents, registers, their attributes and composition — and looks up concrete types and metadata names in it. An external chat can't see your configuration and invents names: you get a plausible query that doesn't run.
- Validation before delivery. The finished query is checked before it reaches the editor.
- The work is visible and verifiable. The chat shows which objects the assistant inspects, what it changes and what it checks. For complex tasks it first proposes a plan, which you can confirm or adjust before it is applied.
- Diagnostics from actual metrics. For questions like "why is the selection empty" or "why is it slow", the assistant answers while seeing the row count, temporary tables, joins, console output settings and execution time. An external chat has no access to any of this.
Rows from your database are never sent to the neural network — see what is sent to the neural network.
What does the dialogue fill indicator show?
It is a context fill gauge, not a task progress bar. The common misreading: the circle "stopped at 31%" — and the user waits, when there is nothing to wait for.
Context is the entire dialogue history that the model re-reads on every request. The fuller it is, the more each subsequent request costs. That's why history is worth compacting: the assistant retells the gist of the conversation to itself briefly and drops the long transcript.
Compaction works in two modes: automatically as the context fills, and manually — via a button, once the dialogue has accumulated enough. If you've moved to an entirely different task, it's cleaner to start a new dialogue than to compact the old one.
Can I switch models mid-task?
Yes, the model can be changed at any moment from the dropdown in the chat, and the dialogue context carries over — you don't have to restate the task.
One detail about money: switching resets the cache, so the first request to the new model costs more than the ones that follow — reading the entire accumulated history is paid for again. A spike in spending at that moment is normal.
The practical conclusion is the same as for coins: start with a smaller model and switch up when you see the task is beyond it. The reverse order — the most expensive model from the start — is almost always overpaying.
Paid services: generating a data processor or a report
Beyond assistant requests, the console offers services that assemble a finished artifact from your query — an external data processor or an external report. They are billed per delivery rather than by text volume; prices are in pricing.
You are charged only for a successful build: if generation fails, no coins are deducted. Regenerating with the same request within 24 hours is free.
What happens when I run out of coins?
The console stays fully functional: running queries, the query builder, drill-down, background mode and export to Excel don't consume coins. Coins are needed only for the AI assistant and the paid services.
When you need the assistant again, buy a pack in your account. Your key and settings don't change — the balance is simply topped up.
Data, migration and updates
I use a different query console — is migrating easy?
Yes. LenSA saves and loads individual queries in the .q1c format, compatible with other popular
consoles, and stores the whole query list in its own .q1cs format.
The familiar tools are all there — the query builder, parameters, temporary tables, drill-down — plus the AI assistant on top. There's nothing to relearn.
Is my data sent to the neural network?
By default, no. The assistant works with the configuration structure and the query text; result rows are not sent to it — it only sees the fact of execution and the metrics.
Query parameter values are sent only if you enable the corresponding setting yourself — it gives a more precise analysis, but the choice remains yours.
Details of data processing are in the privacy policy.
How does the console update?
The data processor checks for updates on its own and notifies you about a new version. Updating
means replacing a single file: download the fresh .epf from your account and open
it instead of the old one. Settings and saved queries are preserved, and you don't need to
re-enter the key.
What changed in each version is listed in the "What's new" section on the product page.
Didn't find the answer on this page — ask here. We'll look into it and extend this section.