AI & Models · Integration
AgentX
Add AgentX to your product for your customers, and give your AI agents governed access to it.
The AgentX access API sits under https://api.agentx.so/api/v1/access and is conversation shaped: you list agents, create a conversation against one with POST /agents/{id}/conversations/new, then post to /conversations/{id}/message. Streaming is a different path rather than a flag, so /conversations/{id}/messagesse and /jsonmessagesse are the server sent event variants and you pick the endpoint up front. DELETE on a conversation resets its context rather than being a routine cleanup call, and PUT /conversations/{id}/update-context lets you inject context by hand, which is what most people reach for instead of resetting. Observability is two hops: /messages/{id}/trace gives you a trace id and /traces/{id} returns the actual trace. There are also voice endpoints for speech recognition and text to speech, including a streaming synthesis variant. fastn holds each customer's AgentX key and keeps the per tenant connection working as keys are rotated.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let a customer connect their own AgentX workspace so their agents answer inside your product on their own key
Embed a customer's existing agent in your support surface and keep one conversation per end user
Feed account context into a conversation with the update context call so answers reflect the current record
Store the trace for each answer alongside the message so a customer can see how a reply was produced
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
Let an agent list the AgentX agents a tenant has access to and route a question to the right one
Have an agent send a message into an existing conversation and return the streamed reply
Audit per tenant which conversations were created and which traces were fetched, so agent usage is attributable
Example prompt
Ask our onboarding agent what this customer still needs to finish setup.
Set up AgentX in 4 steps
- 01Enable the AgentX connector from your fastn dashboard.
- 02Have each customer authorise their own AgentX 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 AgentX integration
What you get by embedding it with fastn instead of building it yourself.
- Ship an AgentX integration without building it. Your customers connect their own AgentX 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 an AgentX update is not your on-call problem.
- One integration serves your product and your agents. The same governed AgentX 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 AgentX, across other categories.
Snowflake
Airtable
PostgreSQL
AmplitudeAgentX integration FAQ
How do I add an AgentX integration to my product?
Enable the AgentX connector in your fastn dashboard, then let each customer authenticate their own AgentX account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no AgentX client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own AgentX account?
Yes. Every connection is scoped to the individual customer, so each authorises their own AgentX 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 AgentX 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 list the AgentX agents a tenant has access to and route a question to the right one
Who maintains the AgentX integration?
fastn does. When AgentX 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 AgentX API key and quota does each call use?
Each customer authorises their own AgentX 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 AgentX integration?
A common starting point: let a customer connect their own AgentX workspace so their agents answer inside your product on their own key. 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 AgentX integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding AgentX does not change your per-connector cost. You can start free with 3 connected accounts.
Add AgentX to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.