ceven

Affinda

Extracts structured data from invoices, receipts, and IDs to trigger downstream business logic and updates your records without manual entry.

Try Affinda in Ceven

Ask Ceven anything
Standard

Why use Ceven?

  1. AI native Affinda integration

    • Describe the outcome and Ceven picks the right Affinda calls, fills the parameters, and checks the result.
    • Structured, agent friendly tool schemas so each call runs reliably instead of by guesswork.
    • Rich coverage for reading, writing, and querying your Affinda data, across all 105 of its actions.

  2. Managed auth

    • Built in OAuth with automatic token refresh and rotation.
    • One place to manage, scope, and revoke Affinda access.
    • Per user and per environment credentials instead of shared keys.

  3. Agent optimized design

    • Actions are tuned from real success and error rates so reliability climbs over time.
    • Full execution logs so you always know what ran in Affinda, when, and on whose behalf.
    • The agent pauses and asks when Affinda is unclear instead of plowing ahead.

  4. Enterprise grade security

    • Fine grained access so you control which agents and people can reach Affinda.
    • Least privilege by default, read scopes first and only the writes a workflow needs.
    • A full audit trail of every Affinda action to support review and sign off.

Supported tools

Every action Ceven's agents can run on Affinda, and when to use it.

Create document
Use this when you have a file or public url and need to extract structured data immediately.
Get document
Pull full metadata and parsing results for a specific document by its id.
Get documents
List documents in your workspace to track processing status or find specific files.
Batch update annotations
Use this to modify parsed values or other fields across many annotations at once.
Create collection
Group documents by a specific extractor within a workspace to keep data organized.
Get collections
Retrieve a list of all collections in your workspace after authentication.
Create workspace
Programmatically create a workspace container within an organization.
Get workspaces
List workspaces filtered by organization or name to find the right environment.
Create RESTHook subscription
Set up a webhook endpoint to receive notifications when document events occur.
Get annotations
Retrieve a list of all annotations for documents after they have been parsed.
Create validation result
Record validation outcomes for a document after the parsing process is complete.
Update document data
Correct or add parsed fields for resume or job description documents.
Create Organization
Tool to create a new organization. use when you have a unique organization name and want to group resources under it.
Create Tag
Tool to create a new tag. use when you need to label documents in a specific workspace.
Delete Collection
Tool to delete a specific collection by its id. use when you need to remove an unused collection. use after verifying the collection id.
Delete Document
Tool to delete a specific document by its id. use when you need to remove a document that is incorrect or no longer needed, after confirming the document id.
Delete Organization
Tool to delete a specific organization by its id. use when you need to remove an organization after confirming its identifier.
Delete Resthook Subscription
Tool to delete a specific resthook subscription by id. use after confirming the subscription identifier when the webhook is no longer needed.
Delete Workspace
Tool to delete a specific workspace by its id. use when you need to remove an unused workspace after confirming the workspace id.
Delete Workspace Membership
Tool to remove a user from a workspace by membership id. use after confirming the workspace membership id to revoke access.
Get Tags
Tool to list all tags. use after confirming authentication to fetch tags across workspaces.
Get All Validation Results
Tool to list validation results for documents. use after processing documents to inspect validation outcomes.
Get Workspace Memberships
Tool to list all workspace memberships for the authenticated user. use when you need to see roles and access across all workspaces.
Get Collection
Tool to retrieve details of a specific collection by its id. use when you need full metadata about a collection after confirming its identifier.
Get Document Type
Tool to retrieve details of a specific document type by its id. use when you need to confirm the configuration or metadata of a document type before processing documents.
Get Document Types
Tool to retrieve a list of all document types. use when you need to display or filter documents by type before processing.
Get Extractors
Tool to retrieve a list of all extractors. use when you need to paginate through available extractors.
Get Organization
Tool to retrieve details of a specific organization by its id. use when you need to fetch an organization's metadata after confirming its identifier.
Get Organizations
Tool to retrieve a list of all organizations. use after authenticating to list all organizations available to the api key.
Get Resthook Subscription
Tool to retrieve details of a specific resthook subscription by its id. use after confirming its creation to verify its settings.

30 actions · scroll to see them all

Frequently asked questions

Ceven uses a polling and webhook strategy to handle the asynchronous nature of AI extraction. When the agent calls the create document action, Affinda begins the parsing process which can take a few seconds depending on file size. The agent can either poll the get document endpoint until the status changes to completed or wait for a RESTHook notification to fire. Once the status is final, Ceven pulls the structured JSON and continues the workflow. This ensures that your workflow does not time out while the machine learning model is reading the document.
Yes, you can use the batch update annotations tool to improve extraction accuracy. When the agent detects a recurring error in how a specific vendor invoice is read, you can instruct it to update the annotations for those documents. By correcting the values through the API, you are providing ground truth data that helps the Affinda engine learn the layout of that specific document type. This creates a feedback loop where the agent identifies the error and you provide the correction to prevent future mistakes.
Ceven can resolve this by using the update document action to reassign the file or by deleting the document and re uploading it to the correct destination. Since the agent has access to get workspaces and get collections, it can verify the destination metadata before the upload happens. If a document is misfiled, you can simply tell the agent to move all files with a certain tag from one workspace to another, and it will execute the sequence of calls needed to clean up the organization.
Ceven is bound by the rate limits and credit quotas of your Affinda subscription tier. A known quirk of the Affinda API is that high volume batch uploads can trigger rate limiting if too many requests hit the create document endpoint in a single second. To manage this, Ceven implements an exponential backoff strategy. If the agent receives a rate limit error, it will pause for a short duration before retrying the request. You should monitor your credits via the get usage by workspace tool to avoid unexpected pauses in your automation.
Ceven acts as a secure bridge between your document source and Affinda. We do not store the actual document files on our own servers permanently. The agent passes the file or the URL directly to Affinda for processing. Once the structured data is extracted and pushed to your downstream system like a database or ERP, the agent can be configured to call the delete document action in Affinda. This ensures that sensitive PII does not linger in the cloud longer than necessary for the extraction process.
This depends on the specific Affinda extractor being used for the workspace. Affinda supports a variety of document types with different levels of OCR capability. If you are using a specialized extractor that supports handwriting, Ceven can pull that data just as it would with digital text. You can verify the capabilities of your current setup by using the get document types tool to see which extractors are active. If the confidence score of the extraction is low, the agent can flag it for human review.
The best way to achieve this is by using the create RESTHook subscription action. The agent can configure Affinda to send a POST request to a Ceven webhook URL every time a document is successfully parsed. This triggers the workflow instantly without the need for scheduled checks. Once the webhook arrives, the agent can immediately pull the document details, perform a validation check, and send a Slack notification or email to the relevant team member with the extracted summary attached.
Yes, Ceven can manage your document organization using the create tag and update document tools. For example, you can build a workflow where the agent reads the extracted vendor name and automatically applies a tag like High Priority or Utility Bill. This allows you to use Affinda as a structured archive where documents are not just parsed but also categorized. You can then use the get tags tool to generate reports on how many documents of a certain category were processed in a given month.

Alternatives to Affinda

Other tools that solve a similar problem. Ceven supports these too, so you can switch or run more than one at once.

Rossum logoRossumABBYY logoABBYYHyperscience logoHyperscience

Try Ceven on your stack

Plug Ceven on top of the tools you already run. Connect Affinda and the rest of your stack, describe the outcome, and its agents handle the work end to end, days of it in minutes.

Get started for free