canonical: https://jentic.com/apis/taggun.io/taggun # TAGGUN Receipt OCR Scanning API Expects only running software, real reactions, and beautifully crafted APIs to serve your every desire to transcribe a piece of paper to digital form. The API exposes 25 endpoints. ## For AI agents Programmatically add manually verified receipt data to a given receipt for feedback and training , export a list of merchant names and addresses to normalise and match in csv form. Covers 25 operations. ## Scope Does not handle payments, communications, or crm - use for ai and machine learning only. ## Capabilities - Add manually verified receipt data to a given receipt for feedback and training - Export a list of merchant names and addresses to normalise and match in CSV form - Import a list of merchant names and addresses to normalise and match in CSV to T - Query and filter TAGGUN Receipt OCR Scanning API records by parameters - Monitor TAGGUN Receipt OCR Scanning API operational status and events ## Use cases ### AI and Machine Learning Operations Use the TAGGUN Receipt OCR Scanning API to perform ai ml operations programmatically. The API provides 25 endpoints covering core functionality including add manually verified receipt data to a given receipt for feedback and training , export a list of merchant names and addresses to normalise and match in csv form, import a list of merchant names and addresses to normalise and match in csv to t. Example prompt: Call POST `/api/account/v1/feedback` to add manually verified receipt data to a given receipt for feedback and training ### Automated Account Management Automate account operations by combining multiple TAGGUN Receipt OCR Scanning API endpoints. Agents can export a list of merchant names and addresses to normalise and match in csv form and then import a list of merchant names and addresses to normalise and match in csv to t in a single workflow. Example prompt: Call GET `/api/account/v1/known-merchants/export` to export a list of merchant names and addresses to normalise and match in csv form, then verify the result ### AI Agent Integration via Jentic AI agents discover and call TAGGUN Receipt OCR Scanning API endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle none tokens manually. Example prompt: Search Jentic for 'add manually verified receipt data to a given receipt for feedback and training ', load the operation schema, and execute with Jentic-managed credentials ## Key endpoints | Method | Path | Description | | --- | --- | --- | | POST | `/api/account/v1/feedback` | Add manually verified receipt data to a given receipt for feedback and training | | GET | `/api/account/v1/known-merchants/export` | Export a list of merchant names and addresses to normalise and match in CSV form | | POST | `/api/account/v1/known-merchants/import` | Import a list of merchant names and addresses to normalise and match in CSV to T | | GET | `/api/account/v1/known-product-codes/export` | Export a list of product codes to normalise and match in CSV format | | POST | `/api/account/v1/known-product-codes/import` | Import a list of product codes to normalise in and match in CSV to TSV format. | | POST | `/api/account/v1/merchantname/add` | Add a keyword to your account's model to predict merchant name. Changes in your | | GET | `/api/account/v1/product-categories/export` | Export a list of product categories and descriptions to match in CSV format | | POST | `/api/account/v1/product-categories/import` | Import a list of product categories and descriptions to match in CSV to TSV form | ## Key resources - **Account** — Operations for account - **Receipt** — Operations for receipt - **Validation** — Operations for validation ## AI readiness This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use. - **Score:** 67 / 100 - **Maturity:** AI-Aware - **Dimensions:** - Foundational Compliance: 93 / 100 - Developer Experience & Jentic Compatibility: 72 / 100 - AI-Readiness & Agent Experience: 44 / 100 - Agent Usability: 94 / 100 - Security: 100 / 100 - AI Discoverability: 52 / 100 - **View full report:** https://jentic.com/apis/taggun.io/taggun/scorecard - **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/ - **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview ### Score it yourself Every API in the directory is allowlisted, so you can re-score it with no key required. - **Score your own API:** https://jentic.com/scorecard.md - **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md ```sh npx @jentic/api-scorecard-cli score ``` ## Why Jentic - **Setup:** Wiring the TAGGUN Receipt OCR Scanning API by hand means posting receipt and training payloads to its account endpoints and handling the import and export routes yourself. Through Jentic you install once, import the TAGGUN Receipt OCR Scanning API from the API Directory, and your agent calls it. - **Permission scoping:** TAGGUN's account operations carry their data in the request body, so limit the agent to the operations it needs, such as submitting feedback or exporting known merchants, rather than to any one resource. Every operation the agent can run is one you chose to allow, so imports that overwrite training data are excluded unless you add them. - **Credential handling:** Any TAGGUN credential is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context. - **Discovery method:** Agents search Jentic by intent such as 'add verified receipt data for training' or 'export known merchants', and Jentic returns the matching TAGGUN operation with its input schema so the agent calls the right endpoint without browsing the reference docs. ## Related APIs - **Openai** — Alternative ai ml API - **Anthropic** — Alternative ai ml API - **Cohere** — Complementary ai ml API - **Huggingface** — Complementary ai ml API ## FAQ ### What authentication does the TAGGUN Receipt OCR Scanning API use? The TAGGUN Receipt OCR Scanning API uses no authentication. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context. ### Can I add manually verified receipt data to a given receipt for feedback and training with the TAGGUN Receipt OCR Scanning API? Yes. Use the POST `/api/account/v1/feedback` endpoint. The API returns structured JSON responses that agents can parse and act on directly. ### What are the rate limits for the TAGGUN Receipt OCR Scanning API? Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer. ### How do I add manually verified receipt data to a given receipt for feedback and training through Jentic? Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'add manually verified receipt data to a given receipt for feedback and training '. Jentic returns the matching TAGGUN Receipt OCR Scanning API operation with its input schema. Load the schema and execute the call - credentials are injected automatically. ### How many endpoints does the TAGGUN Receipt OCR Scanning API have? The TAGGUN Receipt OCR Scanning API exposes 25 endpoints covering account, receipt, validation operations. ### Can I limit what my agent is allowed to do with the TAGGUN Receipt OCR Scanning API? Yes. Because you run Jentic One yourself, your own rules decide which TAGGUN operations the agent may call and which credentials it may use. You can allow only the operations you need, such as POST `/api/account/v1/feedback` to submit verified receipt data or GET `/api/account/v1/known-merchants/export` to export merchant lists, while withholding others. Destructive operations like the import routes that overwrite training data stay excluded until you explicitly grant them.