AI-powered automatic TARIC and INTRASTAT code classification for products
auto_awesome What this module does
AI-generated from the code · Odoo 18.0This module lets you assign customs TARIC/HS codes to products using AI suggestions from Claude, verify them, and keep a full history of every classification change.
The module adds a Classification section on the product form where you can store a TARIC code, see the AI confidence as a progress bar, and check whether the code has been verified. From there you can press "Classify with AI" to get suggested codes, "Verify Code Online" to mark the current code as verified, and "View History" to see every past classification with its method, confidence and user.
A new TARIC Codes menu under Accounting configuration lets you manage the code list itself: code, description, duty rate, validity dates, AI confidence and verification status. Codes must be unique and contain only 6, 8 or 10 digits. A button on each code shows all products using it, and a "Verify Online" button records who verified it and when.
A batch wizard (also available from the product list) can classify many products at once, optionally only unclassified ones or those in a chosen category, showing progress and a result list. If enabled, suggestions above 90% confidence are applied automatically.
In Settings you can enter an Anthropic API key, turn auto-classification on, set a minimum confidence threshold, and choose whether to auto-apply high-confidence suggestions. Every time a product's TARIC code changes, the HS code is updated and a history entry is created.
Depends on
Menus it adds
Models and fields (8)
- taric.code · new modelcode (HS/TARIC Code), active, valid_to, verified, duty_rate (Duty Rate %), valid_from, description, product_ids (Products), verified_date (Verification Date), verified_by_id (Verified By), confidence_score (AI Confidence), classification_history_ids (History)
- product.template · extends an existing modeltaric_code_id (TARIC Code (template)), classification_method, classification_verified (Classification Verified), classification_history_ids (Classification History), ai_classification_confidence (AI Confidence)
- res.config.settings · extends an existing modelanthropic_api_key (Anthropic API Key), auto_classify_enabled (Enable Auto-Classification), min_confidence_threshold (Minimum Confidence Threshold %), auto_apply_high_confidence (Auto-apply High Confidence)
- batch.classify.result · new modelstatus, message, wizard_id, confidence (Confidence %), product_id (Product), taric_code (Suggested Code)
- batch.classify.wizard · new modelstatus, progress (Progress %), result_ids (Results), category_id (Category Filter), product_ids (Products), filter_unclassified (Only Unclassified), auto_apply_high_confidence (Auto-apply High Confidence)
- taric.classify.wizard · new modelnotes (Classification Notes), product_id (Product), custom_code (Custom TARIC Code), suggestion_ids (AI Suggestions), selected_suggestion_id (Selected Code)
- taric.classify.suggestion · new modelcode, sequence, reasoning (AI Reasoning), wizard_id, confidence (Confidence %), description_bg (Описание (BG)), description_en (Description (EN)), supplementary_unit (Unit)
- taric.classification.history · new modeluser_id, ai_model (AI Model), reasoning, product_id, create_date (Date), taric_code_id, confidence_score (Confidence %), classification_method
Text generated by AI (DeepSeek) from reading the Odoo 18.0 code on GitHub; it may contain mistakes, so check the code before deciding. View the code on GitHub
Availability by version
Reviewed: 2026-11-03Confirmation status: 1 confirmed, 8 with no information of 9 versions.
Sources · Odoo 18.0
Confirmed on 2026-11-03 in branch 18.0 of OCA/l10n-bulgaria.
terminal Installation and usage
No verified informationInstallation instructions, the distribution package, dependencies and configuration steps are not shown because they have not yet been verified in the module documentation for any version.
Data imported from GitHub: this sheet reflects the latest catalog review, not a live lookup. Always check the module documentation and staging before installing in production.