AI & Models · Integration
ChatBotKit
Add ChatBotKit to your product for your customers, and give your AI agents governed access to it.
ChatBotKit is a platform for building conversational agents, and its API at api.chatbotkit.com/v1 is organised around bots, datasets, skillsets, conversations and messages, with collection endpoints named as list actions such as /v1/bot/list rather than plural nouns. Auth accepts either a long-lived secret key or a short-lived JWT, and the JWT path is the one intended for browser-side use so you do not ship a secret to a client. Knowledge and capability are deliberately separate: a dataset holds records and files that give a bot retrieval over custom content, while a skillset defines the abilities it can invoke, and both are linked to a bot rather than embedded in it, so the same dataset can back several bots. Conversations are first-class objects that persist their own message history and can be tagged with contacts, tasks and spaces, which is what you filter on when reporting rather than parsing raw messages. Streaming responses arrive as server-sent events, so a plain JSON client will see an incomplete body. fastn holds each customer's secret, can mint scoped tokens per tenant, and keeps the connection maintained as the API version moves on.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let a customer connect their own ChatBotKit account so your product can provision a bot backed by their own dataset.
Keep a customer's dataset in step with your product's content so retrieval always reflects current documentation.
Attach a skillset so the customer's bot can call actions in your product rather than only answering questions.
Read conversation history back into your app so support staff see what the bot already told a user.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
Let an agent add records to a customer's dataset from an approved source, with the dataset ID and tenant written to a per-tenant audit log.
Have an agent list bots and report which are pointing at a stale dataset.
Let an agent summarise conversations in a given space and flag ones that ended without resolution.
Example prompt
Which of our ChatBotKit bots are still using the old product dataset, and what would repointing them involve?
Set up ChatBotKit in 4 steps
- 01Enable the ChatBotKit connector from your fastn dashboard.
- 02Have each customer authorise their own ChatBotKit 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 ChatBotKit integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a ChatBotKit integration without building it. Your customers connect their own ChatBotKit 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 ChatBotKit update is not your on-call problem.
- One integration serves your product and your agents. The same governed ChatBotKit 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 ChatBotKit, across other categories.
Snowflake
Airtable
PostgreSQL
AmplitudeChatBotKit integration FAQ
How do I add a ChatBotKit integration to my product?
Enable the ChatBotKit connector in your fastn dashboard, then let each customer authenticate their own ChatBotKit account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no ChatBotKit client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own ChatBotKit account?
Yes. Every connection is scoped to the individual customer, so each authorises their own ChatBotKit 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 ChatBotKit integration?
Yes. The same connection is exposed to your agents through the fastn MCP gateway, with permissions scoped per tenant and every call audited. Let an agent add records to a customer's dataset from an approved source, with the dataset ID and tenant written to a per-tenant audit log.
Who maintains the ChatBotKit integration?
fastn does. When ChatBotKit 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 ChatBotKit API key and quota does each call use?
Each customer authorises their own ChatBotKit 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 ChatBotKit integration?
A common starting point: let a customer connect their own ChatBotKit account so your product can provision a bot backed by their own dataset. 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 ChatBotKit integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding ChatBotKit does not change your per-connector cost. You can start free with 3 connected accounts.
Add ChatBotKit to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.