ceven

Taggun

Extracts structured data from receipt and invoice images in real time and syncs the totals, taxes, and line items directly into your accounting software.

Try Taggun in Ceven

Ask Ceven anything
Standard

Why use Ceven?

  1. AI native Taggun integration

    • Describe the outcome and Ceven picks the right Taggun 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 Taggun data, across all 14 of its actions.

  2. Managed auth

    • Built in OAuth with automatic token refresh and rotation.
    • One place to manage, scope, and revoke Taggun 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 Taggun, when, and on whose behalf.
    • The agent pauses and asks when Taggun is unclear instead of plowing ahead.

  4. Enterprise grade security

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

Supported tools

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

Process receipt via URL
Use this when you have a public image or PDF link and need basic data extraction like total and date.
Process receipt verbose
Use this when you need comprehensive data including line items and merchant details from a public URL.
Validate receipt URL
Confirm a receipt image is valid against specific campaign settings before processing the data.
Export known merchants
Pull the full registry of known merchants for auditing or syncing with an external database.
Generate merchants CSV
Create a CSV file of mock merchants to test bulk import workflows before going live.
Upload receipt image
Send a raw image file to the API for immediate OCR processing and data return.
Get extraction status
Check the progress of an asynchronous OCR job to see if the data is ready for retrieval.
Delete processed receipt
Remove a receipt image from Taggun storage after the data is safely synced to your books.
Search merchant registry
Query for a specific merchant to verify if they are already recognized by the system.
Update merchant details
Correct or add metadata to a known merchant record to improve future matching accuracy.
List recent extractions
Pull a list of the most recent receipts processed to monitor for errors or duplicates.
Verify image quality
Analyze an image to ensure it is legible enough for the OCR engine to process accurately.
URL Validation
Tool to validate a receipt image by url against campaign settings. use after obtaining the receipt url to confirm validity.
URL Verbose
Tool to process a receipt or invoice from a url for detailed data extraction. use when you have a publicly accessible receipt or invoice url and require comprehensive output including line items, merchant details, and confidence metrics. ca

14 actions · scroll to see them all

Frequently asked questions

Taggun uses advanced computer vision to handle noise, blur, and poor lighting. When Ceven sends an image, Taggun attempts to normalize the contrast and rotate the document for better readability. If the image is too degraded, the API returns a specific error code indicating the image is unreadable. You can build a workflow in Ceven that detects this error and automatically sends a message back to the user asking them to retake the photo. This ensures that only high quality data enters your accounting system while reducing the need for manual intervention by the finance team.
Yes, Taggun automatically detects the currency symbol and ISO code from the receipt image. It extracts the numeric value and the currency type separately, allowing Ceven to perform real time currency conversion if the expense is in a different currency than your base book. This is particularly useful for companies with international employees who travel frequently. The agent can pull the exchange rate for the date of the receipt and record the expense in your local currency while keeping the original foreign amount as a reference in the transaction metadata.
Taggun operates on a tier based credit system where each single processing request consumes one credit. Depending on your plan, you may encounter concurrency limits that restrict how many images can be processed at the exact same second. If you trigger a bulk upload of thousands of receipts, Ceven manages the queue by implementing an exponential backoff strategy. This means the agent will pause and retry requests that hit a 429 rate limit error, ensuring that every single receipt is processed without you having to manually restart the workflow or worry about lost data.
Taggun offers both basic and verbose extraction endpoints. The basic endpoint is faster and focuses on the merchant, date, and total amount. For more granular needs, the verbose endpoint performs a deeper analysis to identify individual line items, including the description, quantity, and unit price for each item on the receipt. Ceven uses the verbose endpoint when you need to allocate expenses to specific projects or departments based on what was actually purchased, which is essential for detailed cost center accounting and tax recovery.
Taggun encrypts data in transit using TLS and stores images in secure environments. When Ceven connects to Taggun, it uses secure API keys to authenticate requests. You can further enhance security by setting up a workflow that calls the delete receipt action immediately after the data is extracted and mirrored to your accounting software. This ensures that sensitive financial images do not reside on the OCR servers longer than necessary, helping your company maintain strict data privacy standards and comply with internal security audits.
Taggun supports over 85 languages, making it suitable for global operations. The OCR engine automatically detects the language of the document, so you do not need to specify the language in your Ceven workflow. Whether it is a receipt from Tokyo, Paris, or New York, the agent can extract the core financial data and map it to your standardized chart of accounts. This eliminates the need for separate OCR tools for different regions and centralizes all expense processing into a single automated pipeline.
Yes, you can manage a registry of known merchants within Taggun. By using the update merchant details action in Ceven, you can refine how the AI identifies specific vendors. This is useful for merchants with complex names or those that appear differently across various store locations. Once a merchant is correctly mapped in the registry, Taggun provides higher confidence scores for those matches. This allows your workflow to automatically categorize expenses based on the merchant without needing a human to verify the vendor for every single transaction.
Taggun primarily supports standard image formats like JPG, PNG, and PDF. When using Ceven, you can pass a direct URL to the image or upload the file as a binary stream. The system is optimized for mobile photos, meaning it can handle the perspective distortion common when people take photos of receipts on a table. If a file is uploaded in an unsupported format, the API will return an error, which Ceven can catch to notify the user that the file type is not supported for OCR processing.

Alternatives to Taggun

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

Veryfi logoVeryfiRossum logoRossumExpensify logoExpensify

Try Ceven on your stack

Plug Ceven on top of the tools you already run. Connect Taggun 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