Skip to main content
Integrations allow your Agent to connect directly with third-party applications and services. An Integration can serve as a Source or a Destination:
  • Source: where source documents are retrieved from
  • Destination: where the Agent’s output is sent
See the full list of all supported integrations here and steps on how to integrate with them. Agents can also be connected using our API or Python Client.

​
Configuring Integrations

Integrations can be configured for each Agent either using the “Integrations” tab or by using the Agent overview on the main Agent page. Hovering over the “Input” or “Output” sections of the Agent overview will show an “Add Source” or “Add Destination” button. From here you can select which Integration you wish to configure.

​
How Integrations Work

​
Sources

If a file storage system is used as a Source (e.g. Box, Google Drive, S3), the Agent will periodically poll the Source for new files. When new files are detected, the Agent will create new Runs to process those files. Sources can be configured to read files in two different patterns:
  1. Import Files Separately: Each file in a source location is processed as a separate Run.
  2. Group Files Together: All files in a sub-folder pattern are processed together, where each sub-folder’s content as a single run by the Agent.

​
Destinations

If a file storage system is used as a Destination (e.g. Box, Google Drive, S3), the Agent will write output files to the Destination after each Run is completed. Destinations can be configured to write files in two different patterns:
  1. Write to Directory: Each Run by the Agent produces output files sent to the Destination.
  2. Write to File: Each Run by the Agent produces a row in a single output spreadsheet.
You can export your results to a destination as PDF, Word, Excel, CSV, JSON, or Powerpoints. You can also use templates to customize the format of your output files.

​
Example Workflows

These patterns can be combined. Let’s consider how to model some example workflows:

​
Lease Abstraction

Suppose you have multiple lease documents and amendments for various properties stored in a Box.com folder:
/Leases
/Leases/Property_A/Lease.pdf
/Leases/Property_A/Amendment_1.pdf
/Leases/Property_A/Amendment_2.pdf
/Leases/Property_B/Lease.pdf
/Leases/Property_B/Amendment_1.pdf
and you want to generate an abstract file for each property.In this case, you would set up the Box.com folder as a Source and group files by subfolder (i.e., Property_A, Property_B) so that each property’s documents are processed as a single run. The output can then be sent to another Box.com folder, with one output file per run.

​
Utility Bill Extraction

Suppose you have a folder of utility bills in Google Drive which you want to extract key details into a table, which one row per bill:
/Bills
/Bills/Bill_001.pdf
/Bills/Bill_002.pdf
/Bills/Bill_003.pdf
In this case, you would set up the Google Drive folder as a Source and a single Google Sheet as the Destination. The output of each runs will be synced to a new row in the Google Sheet.

​
FAQ

​
I’ve set up a Source Integration, when will my Agent start processing files?

After an Integration is added to an Agent, it may take up to five minutes before new runs are created.

​
How many Integrations can I add to my Agent?

Multiple Source and Destination Integrations can be added to a single Agent.

​
What happens if I add a new file to a Source?

For Sources where files are imported separately:
  • If a new file is added, Kolena will create a new run for that file
For Sources where files are grouped together:
  • If a new file is added to a sub-folder, Kolena will create a new run if one does not exist or update an existing run if one already exists for that grouping.

​
What happens if I remove a file from a Source?

Kolena will not delete or update existing runs if a file is removed from a Source.

​
What happens if I update a file in a Source?

If you update the content of an existing file, Kolena will not automatically re-process the updated files or refresh existing runs.