TerminalNUOVO
Every CRM promises customization and delivers a list of checkboxes. The SellioCRM Terminal delivers something else: a conversation with an agent that has hands. You describe what you need and it builds it right there, in your company: it creates objects and fields, writes automations and reports, and can publish your own code running on top of the system. It is the difference between requesting a feature and having the feature. And none of it leaks outside your company: the code runs on an isolated machine, with no database credentials, that reaches the CRM only through the API with your own access. It ships off; an administrator turns it on when you want.
- A conversation with an agent that really creates objects, fields, automations and reports
- Your own code running on top of the system, on defined hooks
- Its own window: close it, it keeps working, reopen where you left off
- Administrators only, and only after it is turned on
Customer code NEVER runs in our process: an isolated machine, no database credentials, reach limited to your own CRM
An extension that keeps failing turns itself off and tells you why, so your CRM never gets slow because of code inside it
A button that turns every extension off at once, outside the terminal, because you need it exactly when the terminal is not answering
What the agent thinks is measured on your account and respects your spend limit, like every other AI feature
Ask in plain words, get it built
You write what you want in your own language and the agent carries it out inside your company. It is not an assistant that suggests where to click: it is an agent that creates the field, writes the automation, builds the report and shows you what it did.
Your code, on top of ours
When customization goes past what a screen can configure, you publish your own code bound to a hook: before a record is saved, after it is saved, when a deal is won, on a schedule, or on its own endpoint. Only the before-save hook may refuse a write, and whatever it returns goes through the same validation as any other input.
Isolation that is architecture, not a promise
Your code runs on a separate machine that holds no database credentials and whose network is a closed list. It reaches the CRM only through the API, with your own company access, so it sees exactly what your company sees. And if the company is ever deleted, everything the terminal created goes with it.
It works while you work
The terminal opens in its own window and the session lives on the server. Close the window, keep using the CRM, come back later and find the conversation where it was, with the full history of what was done.
Who can use it?
Only administrators of the company, and only after the terminal has been turned on for it. Otherwise the item does not even appear.
Can the agent see another company’s data?
No, and that does not rely on a check: it runs on a machine with no database credentials and talks to the CRM through the API with your company access. Its reach is your company’s reach.
Can I use my own AI key?
No. The AI is always ours, and that is by construction: the machine the agent runs on never receives a key. In exchange, everything is measured on your account and respects your spend limit.
What if the code I publish breaks?
An extension that keeps failing turns itself off and shows the error. No extension failure brings down CRM operations, and there is a button that turns them all off at once.
What if what I need requires a change in SellioCRM?
The agent does not pretend to solve it: it opens a request that reaches our team, and you follow the status like any other request.
Automazione avanzata
Un builder di automazione visivo che fa per te il lavoro ripetitivo, senza scrivere una singola riga di codice.
API pubblica e sviluppatori
Un'API REST v1 aperta, un server MCP nativo e un portale per sviluppatori con OpenAPI e Postman.
Automazioni e regole
Trigger, azioni pianificate, regole tra oggetti e validazioni.