Skip to content
Integration · ChatGPT

If your team uses ChatGPT, we set up the CRM connection with you.

Rapitek CRM works with ChatGPT too: it is added on chatgpt.com as a custom connector, you sign in with your CRM account, and it reads and queries your records. We set it up together with you.

Rapitek CRM channels and integrations screen (Turkish interface): WhatsApp Bots, Email Accounts, Meta Pages, Instagram, CTI Adapters, Payment Providers, Claude Connector and İYS Providers cards
Channels and integrations: connection cards

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 both Claude and ChatGPT

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. The connector is built to the open MCP standard and works with ChatGPT too: it is added on chatgpt.com as a custom connector, you sign in with your CRM account, and it reads and queries your records. Your administrator chooses which client families may connect on the Setup › AI Connectors screen; the catalogue includes Claude and ChatGPT.

What to know on the ChatGPT side. In ChatGPT, a custom connector is added only in the web version, on chatgpt.com. Our connector is added as a custom connector, not from the directory. The ChatGPT connection reads and queries your records; creating and updating records works in the Claude connection and in Rapi, the assistant inside the product. Rapi, the assistant inside the product, on the other hand, needs no separate connection; Rapi's usage is priced separately.

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. 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.

A concrete scenario

Thursday 14:25, a rep is preparing for a meeting. Once the connection is in place, this is what changes:

  1. 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. 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. 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. 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. 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. 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 resell ChatGPT usage.

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.

Connection routes

How does it connect with each AI client?

The connector is built to the open MCP standard. It works with Claude and ChatGPT; for ChatGPT, we set up the connection together with you.
ClientConnectionSetup
Claude (claude.ai and iOS)The AI connector works with Claude; you sign in with your own CRM accountWith AI features on in Setup › System Controls, your administrator enables it on the Setup › AI Connectors screen
ChatGPT (chatgpt.com)The connector works with ChatGPT: you sign in with your CRM account, and it reads and queries your recordsAdded on chatgpt.com as a custom connector; we set it up together with you
VS Code/Copilot, Goose and other MCP clientsNot within the connector's scope todayThe connector works with Claude and ChatGPT
The assistant inside the productRapi reads and writes CRM recordsIt works when you use it; an administrator can turn off all AI features in Setup › System Controls
REST APILive; every CRM record can be read and written, the field structure can be read from outside, and several operations can be sent in one requestThis is the surface to build on if you want a custom integration
Where the data goesYou use your own ChatGPT subscriptionThe contract on that side is between you and your provider; we do not resell ChatGPT usage
Summary

The connection at a glance

Read and write
Every CRM record through the open REST API
25 operations
operations that can be sent in a single request
200 records
records per bulk transfer request
Not needed
Separate connection for Rapi, the assistant inside the product
Open MCP
Works with Claude and ChatGPT
Implementation

How is the connection brought live?

  1. 1

    Discovery

    We work out how you use ChatGPT today 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. 2

    Scope and authorization table

    Which objects get read access is written out one by one; if writing is needed, it is defined separately in the Claude connection or the REST API. Which provider the data will go to, and what that means in terms of transfer abroad, sits in the same document.

  3. 3

    Configuration and a limited start

    Access permissions are defined and the connection is opened with a narrow scope. The ChatGPT connection reads and queries records; if you need records written, that is opened in the Claude connection, in Rapi or over the REST API, at your decision.

  4. 4

    Training, auditing and go-live

    The team is shown how to follow the assistant's work through the change history. 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, needs no separate connection; Rapi's usage is priced separately. You connect ChatGPT to the CRM with your own subscription, through the AI connector.
  • The ChatGPT connection is set up as a custom connector. It is added on chatgpt.com (web), and ChatGPT reads and queries your records. Creating and updating records works in the Claude connection and in Rapi.
  • 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 our AI provider in the United States 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 Türkiye 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). When you use Rapi or other AI features, or enable them in an automation, the relevant content is sent to our AI provider in the United States for processing. 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 the Rapi AI usage allowance, on a single page.

Three plans, a scope table and separately priced items, on one page.

FAQ

Frequently asked questions about the ChatGPT integration

Can we connect ChatGPT to Rapitek CRM?
Yes. Rapitek CRM works with ChatGPT too: it is added on chatgpt.com as a custom connector, you sign in with your CRM account, and it reads and queries your records. We set it up together with you. If you want to build your own integration, a REST API with permission-based access is also live today.
Is Rapitek CRM a “GPT-powered” CRM?
No. Rapi, the assistant inside the product, is not based on ChatGPT. ChatGPT is connected with your own subscription, through the AI connector; we set it up together with you.
Do you provide a ready-made Custom GPT or plugin?
The ChatGPT connection is set up as a custom connector rather than a ready-made Custom GPT or plugin. The connector is built to the open MCP standard and is added in the web version of ChatGPT, on chatgpt.com. We set it up together with you.
Which clients can your AI connector connect to?
The connector works with Claude; it is in live use on claude.ai and on iOS, and you sign in with your own CRM account. It works with ChatGPT too: it is added on chatgpt.com and reads and queries your records. Your administrator chooses which client families may connect on the Setup › AI Connectors screen; we set up the connection together with you.
What does Rapi, the product's own assistant, do?
Rapi does not only read the CRM, it writes records too: it fetches, creates and updates core records such as leads, contacts, companies and opportunities. The number of steps that can be taken in a single request is limited, at most eight, so it is not an agent running on its own in the background. The detail is on the Claude integration page.
Will we be using our own ChatGPT subscription?
Yes. You use your own ChatGPT subscription; we do not resell ChatGPT usage. The practical consequence is this: the contract, the terms of use and the invoice on that side are between you and your provider. We apply the same approach on the WhatsApp and SMS side, which is why we can give a consistent answer.
What does the ChatGPT connection do in the CRM?
It reads and queries your records. Creating and updating records works in the Claude connection and in Rapi, the assistant inside the product; the REST API supports both reading and writing records. In the Claude connection and the REST API, which objects get write access is written out one by one in the scope.
How do we audit the changes the assistant makes?
From the field-level change history. Changes made over the API to existing records land in that trail as well: you can see when which field moved to which value (for protected fields, only a marker). A newly created record's initial values are not recorded in it; 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. An assistant coming from outside does not use a separate route that skips the audit trail.
Does our CRM data go to OpenAI?
It does not go there unless you set up the connection; there is no flow inside the product that goes to OpenAI. Once you set the connection up, the records within the scope you granted your client go to the provider through your own ChatGPT account. Seen from Türkiye this is a transfer abroad and falls under Article 9 of Law No. 6698; we establish its basis together during the contract process.
When do the AI features send my CRM data to an AI provider?
Only when you use an AI feature or your administrator enables it in an automation. The Rapi assistant, business card scanning, meeting analysis, the WhatsApp/Instagram assistant and the AI step in flows send the relevant content to our AI provider in the United States. Audio recordings are transcribed on our own servers; the audio file is 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. The detail is on our security page.
Can our team use ChatGPT from its own window?
Yes. Our connector is added on chatgpt.com as a custom connector; in its own window, ChatGPT reads and queries your CRM records. We set it up together with you.
How long does setup take, is it included in the plan price?
The scope of the connection is determined by how many objects, which permissions and which users are involved, and it is planned together with the CRM rollout. After the discovery call we give you a date, not a range. Project-specific development is scoped separately and priced separately.
Where is our data held?
In the European Union: the database in Helsinki (Finland), the files you upload in Frankfurt, database backups in Falkenstein (Germany). Your CRM data is held in a separate database that belongs to you. When you use Rapi or other AI features, or enable them in an automation, the relevant content is sent to our AI provider in the United States for processing. If you connect your own AI client, that client's provider is added as well.
Can we see it before buying?
Yes. You can try it free for 7 days: fill in the form and we'll open your trial account and send you your login details. If you like, we can also start with a 30-minute intro call. In that call we show the connector, authorization and how the change history records writes, on your own scenario.

Let us spend 30 minutes on which record we open with which permission

Fill in the form and we'll open your 7-day trial account and send you your login details; no credit card required. If you like, in a 30-minute intro call we talk about which AI client you use, set up the connection together and show authorization and how write operations land in the change history, on your own scenario.

Made with RapitekGO

We'd like to use optional measurement cookies; if you decline, the site works the same. Cookie policy