AI & Models · Integration
DocsBot AI
Add DocsBot AI to your product for your customers, and give your AI agents governed access to it.
DocsBot AI addresses everything through api.docsbot.ai paths shaped as /teams/{teamId}/bots/{botId}, so both identifiers have to be carried on every call and a wrong id returns a validation error rather than an empty result. A bot answers only from the sources indexed into it, and adding a source starts an asynchronous crawl or ingest whose completion has to be observed before answers reflect the new content. Chat can be called as a plain request or over a streaming connection, and conversation continuity depends on passing the same conversation identifier back rather than on any server-side session tied to the key. Responses carry the source references used to produce the answer, which is what makes the output auditable rather than an opaque completion. fastn holds each customer's key with their team and bot scoping and keeps the integration current.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let a customer connect their own DocsBot AI team and choose which bot your product may query
Embed answers from a customer's own documentation bot inside your product's help experience
Push a customer's updated help articles into a bot as a source and wait for indexing to finish
Show the cited source documents alongside every answer so users can check where it came from
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
Let an agent query a specific bot and return the answer together with the source references it cited
Have an agent add or refresh a source on a bot and confirm indexing completed before answers are trusted
Audit, per tenant, every bot an agent queried, with the team and bot ids and the conversation identifier used
Example prompt
What did our DocsBot AI support bot answer about refund timelines, and which documents did it cite?
Set up DocsBot AI in 4 steps
- 01Enable the DocsBot AI connector from your fastn dashboard.
- 02Have each customer authorise their own DocsBot 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 DocsBot AI integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a DocsBot AI integration without building it. Your customers connect their own DocsBot 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 DocsBot AI update is not your on-call problem.
- One integration serves your product and your agents. The same governed DocsBot 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 DocsBot AI, across other categories.
Snowflake
Airtable
PostgreSQL
AmplitudeDocsBot AI integration FAQ
How do I add a DocsBot AI integration to my product?
Enable the DocsBot AI connector in your fastn dashboard, then let each customer authenticate their own DocsBot AI account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no DocsBot 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 DocsBot AI account?
Yes. Every connection is scoped to the individual customer, so each authorises their own DocsBot 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 DocsBot 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. Let an agent query a specific bot and return the answer together with the source references it cited
Who maintains the DocsBot AI integration?
fastn does. When DocsBot 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 DocsBot AI API key and quota does each call use?
Each customer authorises their own DocsBot 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 DocsBot AI integration?
A common starting point: let a customer connect their own DocsBot AI team and choose which bot your product may query. 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 DocsBot AI integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding DocsBot AI does not change your per-connector cost. You can start free with 3 connected accounts.
Add DocsBot AI to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.