AI & Models · Integration
Azure AI Document Intelligence
Add Azure AI Document Intelligence to your product for your customers, and give your AI agents governed access to it.
Embed an Azure AI Document Intelligence integration so your customers can push documents through their own models and read structured results into your product, with usage attributed per tenant. fastn handles authentication and API upkeep, so document extraction is configuration rather than a service you operate.
In your product
Embedded for your customers. Per-tenant auth, no per-customer code, maintained by fastn.
Let customers submit documents from your product to their own extraction model.
Read extracted fields, tables, and confidence scores into your product.
Route low-confidence results to a human review step in your product.
Trigger your product when an extraction completes or fails.
For your AI agents
Governed, audited access for the agents you build, through the MCP server.
An agent reads extracted fields before deciding what to do with a document.
An agent submits a document for extraction within governed permissions.
An agent reacts to a low-confidence result and routes it for review.
Example prompt
Extract line items from these invoices and flag any field below 80 percent confidence.
Set up Azure AI Document Intelligence in 4 steps
- 01Open the Azure AI Document Intelligence connector from your fastn dashboard.
- 02Have each customer authenticate their Azure resource.
- 03Map the models and output fields your product uses, then enable actions and triggers.
- 04Call them from your product, or expose them to an agent through the MCP server.
Why teams use the Azure AI Document Intelligence integration
What you get by embedding it with fastn instead of building it yourself.
- Ship an Azure AI Document Intelligence integration without building it. Your customers connect their own Azure AI Document Intelligence 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 Azure AI Document Intelligence update is not your on-call problem.
- One integration serves your product and your agents. The same governed Azure AI Document Intelligence 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
ABBYY Vantage
Azure OpenAIOften used alongside
Tools the same teams tend to run next to Azure AI Document Intelligence, across other categories.
Snowflake
Airtable
PostgreSQL
AmplitudeAzure AI Document Intelligence integration FAQ
How do I add an Azure AI Document Intelligence integration to my product?
Enable the Azure AI Document Intelligence connector in your fastn dashboard, then let each customer authenticate their own Azure AI Document Intelligence account. fastn handles the OAuth flow, token storage and refresh per tenant, so there is no Azure AI Document Intelligence client code in your app and no per-customer branch in your codebase. Setup is 4 steps.
Do my customers each connect their own Azure AI Document Intelligence account?
Yes. Every connection is scoped to the individual customer, so each authorises their own Azure AI Document Intelligence 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 Azure AI Document Intelligence integration?
Yes. The same connection is exposed to your agents through the fastn MCP gateway, with permissions scoped per tenant and every call audited. An agent reads extracted fields before deciding what to do with a document.
Who maintains the Azure AI Document Intelligence integration?
fastn does. When Azure AI Document Intelligence 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 Azure AI Document Intelligence API key and quota does each call use?
Each customer authorises their own Azure AI Document Intelligence 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 Azure AI Document Intelligence integration?
A common starting point: submit documents from your product to their own extraction model. 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 Azure AI Document Intelligence integration cost?
It is included. Pricing is based on connected accounts, not on how many connectors you enable, so adding Azure AI Document Intelligence does not change your per-connector cost. You can start free with 3 connected accounts.
Add Azure AI Document Intelligence to your product
Start free with 3 connected accounts. No sales call required, and no per-customer integration code.