AI & Models · Integration
Cody
Add Cody to your product for your customers, and give your AI agents governed access to it.
Cody is an AI assistant answering from a knowledge base you upload, with a REST API at getcody.ai/api/v1 authenticated by a bearer token, even though the marketing site sits on meetcody.ai. The object graph runs bots, folders, documents, conversations and messages: a bot is scoped to one or more folders, documents live inside folders, and answers are only grounded in what that bot can see. Documents can be created from raw text, a URL or an uploaded file, and indexing happens after the create call returns, so a document is not answerable the instant it appears in the list. Replies are tied to a conversation id, and dropping it starts a fresh context rather than continuing the thread, which is the common cause of an assistant that seems to forget. A streaming message endpoint returns tokens over SSE for chat-style interfaces. fastn holds each customer's API key, keeps the connection working and controls which bots and folders an agent may touch.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let a customer connect their own Cody workspace so answers come from their knowledge base and their plan.
Push help centre articles or internal docs into a customer's folder whenever the source content changes.
Embed a grounded question box in your product that calls the customer's own bot and keeps conversation history.
Show which documents a bot can see so a customer can audit why an answer was wrong.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
Let an agent ask a named bot a question in an existing conversation and return the grounded answer, with per-tenant auditing of which bot and folders were used.
Have an agent upload a new document and confirm it has finished indexing before relying on it.
Allow an agent to read bots and conversations while blocking deletion of documents or folders.
Example prompt
Ask our support bot what the refund window is and show which document it came from.
Set up Cody in 4 steps
- 01Enable the Cody connector from your fastn dashboard.
- 02Have each customer authorise their own Cody 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 Cody integration
What you get by embedding it with fastn instead of building it yourself.
- Ship a Cody integration without building it. Your customers connect their own Cody 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 Cody update is not your on-call problem.
- One integration serves your product and your agents. The same governed Cody 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
Often used alongside
Tools the same teams tend to run next to Cody, across other categories.
Cody integration FAQ
How do I add a Cody integration to my product?
Enable the Cody connector in your fastn dashboard, then let each customer authenticate their own Cody account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no Cody client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own Cody account?
Yes. Every connection is scoped to the individual customer, so each authorises their own Cody 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 Cody 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 ask a named bot a question in an existing conversation and return the grounded answer, with per-tenant auditing of which bot and folders were used.
Who maintains the Cody integration?
fastn does. When Cody 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 Cody API key and quota does each call use?
Each customer authorises their own Cody 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 Cody integration?
A common starting point: let a customer connect their own Cody workspace so answers come from their knowledge base and their plan. 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 Cody integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding Cody does not change your per-connector cost. You can start free with 3 connected accounts.
Add Cody to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.