If your team uses ChatGPT, we set up the CRM connection with you.
Rapitek CRM's AI connector works with Claude. Because it supports the open MCP standard, it is also designed to be added to ChatGPT (Developer Mode) as a custom connector; we set it up in ChatGPT together with you.
The team works in ChatGPT, the record sits in another window
If your team no longer uses ChatGPT as an experiment, the subscription has been bought, the team has settled in, most of the work runs in that window, then the CRM is sitting somewhere else during the same day. The mechanism is this: with no defined link between the two windows, a human does the transfer, and the moment it flows across, the origin of the record is lost. Three outcomes we have seen in our own projects and in our buying conversations:
- Data is moved by copy-paste. The summary is produced in ChatGPT, then pasted into the CRM by hand; where the record came from and who produced it are lost.
- In the procurement meeting someone asks, “Is your CRM AI-powered?” Saying “yes” is easy; once they ask with which model, under what authorization and where the data goes, the answers get blurry.
- IT asks something else: which data goes to which provider, who turned it on, can it be revoked? The answer to that question can be left to the contract stage, that is, to the worst possible moment.
This page answers all three: how ChatGPT connects to the CRM, under what authorization it works, and where the data goes.
The connector works with Claude and is designed to connect to ChatGPT too
Rapitek CRM's AI connector works with Claude. It is in live use on claude.ai and on iOS, and you sign in with your own CRM account. Because the connector is built to the open MCP standard, it is also designed to be added to ChatGPT as a custom connector. Your administrator chooses which client families may connect on the Setup › AI Connectors screen; the catalogue includes Claude, ChatGPT, VS Code/Copilot and Goose.
What to know on the ChatGPT side. In ChatGPT, custom MCP connectors can only be added in the web version with Developer Mode turned on. Our connector is added as a custom connector, not from the directory. OpenAI's own sources describe differently which ChatGPT plans support write tools, so we look at your plan together during setup. Rapi, the assistant inside the product, runs on Anthropic Claude.
Alongside the connector there is an open REST API. If you want to build your own integration, that surface is live today: every record in the CRM, from lead to quote, from invoice to task, can be read and written through the REST API, and you can read the field structure from outside. Access is granted with permissions, without sharing passwords; up to 25 operations can be sent in a single request, and bulk transfers handle up to 200 records per request. A custom integration is built on top of this surface.
Whether you use the connector in ChatGPT or a custom integration over the REST API is something we choose together during discovery, based on your subscription. This surface is usable from outside: ERP integrators can read and write records through this same REST API. We have described the product's own assistant and the AI connector on the Claude integration page, the same framework inside an ERP on the Netsis integration page, and our general approach on the integrations page.
Thursday 14:25, a rep is preparing for a meeting. Once the connection is in place, this is what changes:
-
1
Data is not copied, it is called
Once the connection is in place, the client reads customer, contact and opportunity records from the API. The copy-paste step in between disappears; which record an answer rests on becomes clear.
-
2
Access comes from permissions, not from a shared password
Access is granted with permissions; no user password is shared. You define the scope, and you can take it back the way you granted it, from a single screen.
-
3
Fields are not tracked by hand
The field structure is read from the API. When you add a new field to the CRM, the connection code does not have to chase after it; what it reads changes along with it.
-
4
Write access is a separate and deliberate decision
Reading and writing are not the same thing. Which objects get write access is written out one by one in the scope; we do not grant access that is open to everything by default.
-
5
Changes to existing records leave a trace
Changes made over the API to existing records land in the field-level change history: when which field moved to which value (for protected fields, only a marker). A newly created record's initial values are not recorded there. An assistant coming from outside does not skip the audit trail.
-
6
The relationship with the provider stays in your name
You use your own ChatGPT subscription; the contract on that side is between you and your provider. We do not sell tokens, credits or models in between.
The open surface a custom integration rests on
Every CRM record within reach
From lead to quote, from invoice to task, every record in the CRM can be read and written through the REST API. You can also read the field structure from outside.
Access without sharing passwords
Access is granted with permissions. No integration is built by sharing a user's password; authorization is taken back the way it was granted.
Field structure read automatically
The field structure is read from the API. Custom fields you add without writing code appear there too; the connection stays current.
Several operations in one request
Several operations can be sent in a single request: up to 25 at a time; bulk transfers handle up to 200 records per request.
Change history covers changes made over the API as well
Changes made over the API to existing records land in the field-level change history. A newly created record's initial values are not recorded there; the creator (the user the API client is bound to) and creation time are set by the system and cannot be changed from the user screens, data import or the API. The fields the AI changed on existing records can be seen one by one afterwards.
A separate database per customer
Your CRM data is held in a separate database that belongs to you; access arriving over the API also stays inside that boundary.
How does it connect with each AI client?
| Client | Connection | Setup |
|---|---|---|
| Claude (claude.ai and iOS) | The AI connector works with Claude; you sign in with your own CRM account | Your administrator enables it on the Setup › AI Connectors screen |
| ChatGPT | Designed to be added as a custom connector; in ChatGPT, custom MCP is only available in the web version and in Developer Mode | We look at which plans support write tools together during setup, based on your plan |
| VS Code/Copilot, Goose and other MCP clients | Designed to connect through the open MCP standard | We set it up together with you |
| The assistant inside the product | Rapi runs on Anthropic Claude; it reads and writes CRM records | It works when you use it; an administrator can turn off all AI features in Setup › System Controls |
| REST API | Live; every CRM record can be read and written, the field structure can be read from outside, and several operations can be sent in one request | This is the surface to build on if you want a custom integration |
| Where the data goes | You use your own ChatGPT subscription | The contract on that side is between you and your provider; we do not sell tokens or credits in between |
The connection at a glance
How is the connection brought live?
-
1
Discovery
We work out how you use ChatGPT today, which subscription type you are on, and which records you want to look at in the CRM. We recommend that your counterpart on the IT and compliance side is in this call.
-
2
Scope and authorization table
Which object gets read access and which gets write access is written out one by one. Which provider the data will go to, and what that means in terms of transfer abroad, sits in the same document.
-
3
Configuration and a limited start
Access permissions are defined and the connection is opened with a narrow scope. We recommend limiting the initial scope to reading only; write access is widened after the team's flow has been seen, and at your decision.
-
4
Training, auditing and go-live
The team is shown how to follow the assistant's work through the change history. We do not commit to a timeline before discovery; after the discovery call we give you a date, not a range.
Scope and setup terms
What the connection covers, item by item:
- Rapi, the assistant inside the product, runs on Anthropic Claude. You connect ChatGPT to the CRM with your own subscription, through the AI connector.
- The ChatGPT connection is set up as a custom connector. In ChatGPT, custom MCP connectors are available in the web version and in Developer Mode; we look together during setup at how write tools work on your plan.
- Rapi works on request, step by step. The product's own assistant takes at most eight steps in a single request; it does not run on its own in the background.
- Stock sync, a self-running order → invoice → collection chain and production/MRP automation are outside the scope. Connecting an assistant does not change that. The reasons, and what can be done instead, are in one place: scope and setup terms.
AI and consent: the product's own AI features (the Rapi assistant, business card scanning, meeting analysis, the WhatsApp/Instagram assistant and the AI step in flows) send the relevant content to Anthropic (Claude) only when you use them or enable them in an automation. Audio recordings are transcribed on our own servers and are not sent to the AI provider. With a single switch under Setup › System Controls you can turn off all AI features, and you can turn off meeting analysis separately. When you connect your own ChatGPT client, that decision is yours, and we define its scope in writing at setup: which object, which permission, which user. Seen from Turkey this is a transfer abroad and falls under Article 9 of Law No. 6698; we establish its basis together during the contract process. Our sub-processor list is on our security page.
Data location: your data is held in the European Union: the database in Helsinki (Finland), files in Frankfurt, backups in Falkenstein (Germany). We have no component in Turkey and we have no region-selection feature. The detail is on the security page and in the KVKK privacy notice.
Certification: we do not hold an ISO 27001 or SOC 2 certificate, and we will not claim one until we do. We fill in your enterprise security assessment forms and describe the architecture in writing.
Plan prices are published; scope comes out of discovery
The scope of a ChatGPT connection, and any fee for it, comes out of the discovery call. We publish plan prices, and separately priced items such as Rapi AI credits, on a single page.
Three plans, a scope table and separately priced items, on one page.
Frequently asked questions about the ChatGPT integration
Can we connect ChatGPT to Rapitek CRM?
Is Rapitek CRM a “GPT-powered” CRM?
Do you provide a ready-made Custom GPT or plugin?
Which clients can your AI connector connect to?
Which model does the product's own assistant run on?
Will we be using our own ChatGPT subscription?
If the connection is set up, can ChatGPT write records to the CRM?
How do we audit the changes the assistant makes?
Does our CRM data go to OpenAI?
When do the AI features send my CRM data to an AI provider?
Why does the product's assistant run on Claude?
How long does setup take, is it included in the plan price?
Where is our data held?
Can we see it before buying?
Let us spend 30 minutes on which record we open with which permission
In the intro call, let us talk about which AI client you use and set up the connection together; and let us show authorization and how write operations land in the change history, on your own scenario. Then we open your 7-day trial account; no credit card required.
