AI & Models · Integration
CustomGPT.ai
Add CustomGPT.ai to your product for your customers, and give your AI agents governed access to it.
CustomGPT.ai calls each agent a project, and the API lives on app.customgpt.ai under /api/v1/projects rather than on an api. subdomain, which catches out anyone guessing the hostname. Content is added as pages, either by crawling a sitemap or by uploading files, and indexing is asynchronous, so a project reports queued pages well before answers reflect them. Conversations are two-step: create a conversation to obtain a session id, then post messages against that session, with streaming chosen per message rather than per project. Answers return citation ids that must be resolved through a separate citations endpoint to recover the source URL or file name, so citations are never inline. Removing a page does not immediately change answers until reindexing finishes, which makes content takedowns feel slower than expected. fastn holds each customer's API key, keeps project scoping correct and maintains the connector.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let a customer connect their own CustomGPT.ai project so answers are grounded in their content, not yours.
Upload or crawl new source pages when a customer's knowledge base changes, and surface indexing progress.
Embed a conversation session inside your product and keep message history against your own records.
Resolve citation ids to source links so every answer shown carries a checkable reference.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
Ask an agent which sources were cited in the last answer about a topic, with each call audited per tenant.
Have an agent report how many pages are still queued for indexing in a project.
Let an agent post a question to a customer's project and return the answer with its resolved citations.
Example prompt
Which sources did the agent cite in its last answer about refunds?
Set up CustomGPT.ai in 4 steps
- 01Enable the CustomGPT.ai connector from your fastn dashboard.
- 02Have each customer authorise their own CustomGPT.ai account, so calls run under their credentials rather than a shared key.
- 03Decide which models, requests and outputs your product needs, map those fields, then enable the actions and triggers you want.
- 04Call it from your product and expose it to your agents through the same governed connection.
Why teams use the CustomGPT.ai integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a CustomGPT.ai integration without building it. Your customers connect their own CustomGPT.ai account inside your product and work their models, requests and outputs there, with no per-customer code on your side.
- Handle the part that actually costs time: per-customer keys, quotas and cost attribution matter more than schema here, because every call is billed. fastn owns the auth, token refresh, rate limits, pagination and breaking-change fixes, so a CustomGPT.ai update is not your on-call problem.
- One integration serves your product and your agents. The same governed CustomGPT.ai connection powers in-product features and gives AI agents scoped, audited access, so you give your product and your agents a model call each customer pays for themselves without wiring it twice.
Used by these teams
Compare with
Anthropic Claude
OpenAI
Azure OpenAIOften used alongside
Tools the same teams tend to run next to CustomGPT.ai, across other categories.
Snowflake
Airtable
PostgreSQL
AmplitudeCustomGPT.ai integration FAQ
How do I add a CustomGPT.ai integration to my product?
Enable the CustomGPT.ai connector in your fastn dashboard, then let each customer authenticate their own CustomGPT.ai account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no CustomGPT.ai client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own CustomGPT.ai account?
Yes. Every connection is scoped to the individual customer, so each authorises their own CustomGPT.ai account and only ever sees their own models, requests and outputs. That per-tenant isolation is the point of an embedded integration: you support the long tail of customer setups without maintaining an integration per customer.
Can AI agents use this CustomGPT.ai integration?
Yes. The same connection is exposed to your agents through the fastn MCP gateway, with permissions scoped per tenant and every call audited. Ask an agent which sources were cited in the last answer about a topic, with each call audited per tenant.
Who maintains the CustomGPT.ai integration?
fastn does. When CustomGPT.ai changes an endpoint, deprecates a field or alters its auth, the fix lands in the connector rather than in your backlog, and your customers' connections keep working.
Whose CustomGPT.ai API key and quota does each call use?
Each customer authorises their own CustomGPT.ai account, so usage, rate limits and cost land on the customer that caused them. You are not metering a shared key and re-billing it, and one heavy customer cannot exhaust another's quota.
Are inputs and outputs auditable?
Yes. Every call is logged per tenant with the call, the input and the result, so an output can be traced back to what produced it. That matters more here than in most integrations, because a generated answer or an extracted field cannot be reconstructed from the request alone.
What can I build with the CustomGPT.ai integration?
A common starting point: let a customer connect their own CustomGPT.ai project so answers are grounded in their content, not yours. Teams also use it for the other use cases listed above, and expose it to agents for governed reads and writes.
How much does the CustomGPT.ai integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding CustomGPT.ai does not change your per-connector cost. You can start free with 3 connected accounts.
Add CustomGPT.ai to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.