{"article":{"annotation":{"article_id":"agentcore-self-improving-document-processing-idp-2026","available_at":"2026-10-15T20:48:42.871893Z","geography_revision":"ef6ee0010dda5fe7b240fd514749b43e214c57da73222d2e40ec83b276dd0977","id":"17263f0087bd19743775533627a6a5535e0d7724a53e998548fdb538450039e2","input_sha256":"cff0991739eb7835a2694e1f0448f95740b09ea8ed24cedd299a06827160aca4","limitations":["Rule-derived subjects are candidates, not verified editorial labels or calibrated model probabilities.","Coverage is distinct from event location. Unknown country/city/coordinates remain absent; no automatic geocoding.","Article geometries keep their stated precision and methodology; reproducing them is not independent coordinate verification."],"method":"controlled-rules-v1","places":[],"rules_sha256":"fb5ad3c27c91cb840f7a0a05f7f64a5cb26ad0374409ff9457f277c7092e22b4","schema_version":1,"subjects":[{"concept_id":"medtop:13000000","confidence":null,"confidence_method":null,"evidence":[{"field":"category+topics","language":"en","note":"Preserved editorial category/topic; broad candidate only","source_urls":["https://aws.amazon.com/blogs/machine-learning/build-self-improving-document-processing-using-amazon-bedrock-agentcore/"]}],"method":"controlled-rules-v1","rule_id":"technology-broad","status":"candidate"}],"taxonomy_revision":"1f2db31d811fca07e99b16d402c10e2cc2965c9df1c7b41d9be348b40a24e7fb","taxonomy_version":"IPTC Media Topics 2026-Q2"},"api_url":"https://newsverum.com/api/v1/articles/agentcore-self-improving-document-processing-idp-2026?lang=pt","category":"technology","content":{"key_points":[],"paragraphs":["O guia da AWS de 14 de outubro descreve um fluxo com vários agentes para documentos como faturas de fornecedores com layouts variáveis. Um agente analisador extrai texto e identifica o tipo, outro localiza registros semelhantes, e agentes de extração e validação comparam os dados às regras de negócio.","A arquitetura usa Textract, S3 Vectors, Aurora DSQL e componentes AgentCore. Instruções criadas para novos formatos podem ser reutilizadas em documentos semelhantes. A AWS apresenta um guia de implementação, sem divulgar medidas independentes de precisão para cada tipo documental."],"sections":[]},"corrections":[],"country":null,"data":{"blocks":[{"description":{"ar":"نشرت AWS في 14 أكتوبر دليلاً تقنياً لمعالجة الوثائق المتعلمة باستخدام AgentCore.","de":"AWS veröffentlichte am 14. Oktober einen technischen Leitfaden zur lernenden Dokumentverarbeitung mit AgentCore.","en":"AWS published a technical guide to self-improving document processing with AgentCore on October 14.","es":"AWS publicó el 14 de octubre una guía técnica sobre procesamiento documental que aprende con AgentCore.","fr":"AWS a publié le 14 octobre un guide technique sur le traitement documentaire évolutif avec AgentCore.","pt":"A AWS publicou em 14 de outubro um guia técnico sobre processamento de documentos com aprendizagem usando AgentCore.","tr":"AWS, 14 Ekim’de AgentCore ile öğrenen belge işleme sistemi için teknik kılavuz yayımladı."},"id":"ai-event-agentcore","items":[{"date":"2026-10-14","description":{"ar":"نشرت AWS في 14 أكتوبر دليلاً تقنياً لمعالجة الوثائق المتعلمة باستخدام AgentCore.","de":"AWS veröffentlichte am 14. Oktober einen technischen Leitfaden zur lernenden Dokumentverarbeitung mit AgentCore.","en":"AWS published a technical guide to self-improving document processing with AgentCore on October 14.","es":"AWS publicó el 14 de octubre una guía técnica sobre procesamiento documental que aprende con AgentCore.","fr":"AWS a publié le 14 octobre un guide technique sur le traitement documentaire évolutif avec AgentCore.","pt":"A AWS publicou em 14 de outubro um guia técnico sobre processamento de documentos com aprendizagem usando AgentCore.","tr":"AWS, 14 Ekim’de AgentCore ile öğrenen belge işleme sistemi için teknik kılavuz yayımladı."},"label":{"ar":"نشر المقالة التقنية لـ AWS","de":"Veröffentlichung des technischen AWS-Beitrags","en":"AWS technical post published","es":"Publicación del artículo técnico de AWS","fr":"Publication de l’article technique d’AWS","pt":"Publicação do artigo técnico da AWS","tr":"AWS teknik yazısının yayımlanması"},"status":"occurred"}],"methodology":{"ar":"التاريخ هو تاريخ النشر الوارد في المصدر الأولي لـ AWS؛ ولم يُستنتج موعد إطلاق أو تطبيق غير مذكور.","de":"Das Datum entspricht dem Veröffentlichungsdatum der AWS-Primärquelle; ein dort nicht genanntes Start- oder Einführungsdatum wird nicht abgeleitet.","en":"The date is the publication date shown by the AWS primary source; no launch or deployment date beyond the source is inferred.","es":"La fecha corresponde a la publicación indicada por la fuente primaria de AWS; no se infiere una fecha de lanzamiento o despliegue no indicada.","fr":"La date correspond à celle affichée par la source primaire AWS; aucune date de lancement ou de déploiement non indiquée n’est déduite.","pt":"A data é a publicação indicada pela fonte primária da AWS; não se infere uma data de lançamento ou implantação não informada.","tr":"Tarih, AWS birincil kaynağında yayımlanma tarihi olarak verilir; kaynakta belirtilmeyen bir lansman veya uygulama başlangıç tarihi çıkarımı yapılmamıştır."},"sourceUrls":["https://aws.amazon.com/blogs/machine-learning/build-self-improving-document-processing-using-amazon-bedrock-agentcore/"],"title":{"ar":"نشر المقالة التقنية لـ AWS","de":"Veröffentlichung des technischen AWS-Beitrags","en":"AWS technical post published","es":"Publicación del artículo técnico de AWS","fr":"Publication de l’article technique d’AWS","pt":"Publicação do artigo técnico da AWS","tr":"AWS teknik yazısının yayımlanması"},"type":"events","updatedAt":"2026-10-15T20:45:40Z"}],"version":1},"data_downloads":[{"formats":{"csv":"https://newsverum.com/api/v1/articles/agentcore-self-improving-document-processing-idp-2026/data/ai-event-agentcore?lang=pt&format=csv","json":"https://newsverum.com/api/v1/articles/agentcore-self-improving-document-processing-idp-2026/data/ai-event-agentcore?lang=pt&format=json"},"id":"ai-event-agentcore"}],"data_types":["events"],"editorial_illustration":{"alt":"Ilustração conceitual de tecnologia, processadores e informações conectadas.","asset_id":"newsverum-v1-technology","avif_variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.avif","width":480},{"height":480,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-720.avif","width":720},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.avif","width":960},{"height":800,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1200.avif","width":1200},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.avif","width":1536}],"credit":"Newsverum","documentary":false,"height":1024,"kind":"symbolic-editorial-illustration","language":"pt","scope":"topic","url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.webp","width":480},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.webp","width":960},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","width":1536}],"width":1536},"event_id":"event-d0c9f222-74cc-5dab-bd82-12acec4742cc","event_period":"2026-10-14","event_period_basis":"source-review","id":"agentcore-self-improving-document-processing-idp-2026","image":null,"importance":0.6,"language":"pt","modified_at":"2026-10-15T20:48:36+00:00","publication_basis":"publication-record","published_at":"2026-10-15T20:48:36+00:00","reading_minutes":1,"region":"world","section_illustration":{"alt":"Ilustração conceitual de tecnologia, processadores e informações conectadas.","asset_id":"newsverum-v1-technology","avif_variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.avif","width":480},{"height":480,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-720.avif","width":720},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.avif","width":960},{"height":800,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1200.avif","width":1200},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.avif","width":1536}],"credit":"Newsverum","documentary":false,"height":1024,"kind":"symbolic-editorial-illustration","language":"pt","scope":"section","url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.webp","width":480},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.webp","width":960},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","width":1536}],"width":1536},"slug":"agentcore-self-improving-document-processing-idp-2026","sources":[{"checkedAt":"2026-10-15","name":"AWS Machine Learning Blog","publishedAt":"2026-10-14","url":"https://aws.amazon.com/blogs/machine-learning/build-self-improving-document-processing-using-amazon-bedrock-agentcore/"}],"summary":"O exemplo classifica documentos, extrai campos e os confere com regras de negócio; também pode reutilizar instruções para novos formatos.","text":"O exemplo classifica documentos, extrai campos e os confere com regras de negócio; também pode reutilizar instruções para novos formatos.\n\nO guia da AWS de 14 de outubro descreve um fluxo com vários agentes para documentos como faturas de fornecedores com layouts variáveis. Um agente analisador extrai texto e identifica o tipo, outro localiza registros semelhantes, e agentes de extração e validação comparam os dados às regras de negócio.\n\nA arquitetura usa Textract, S3 Vectors, Aurora DSQL e componentes AgentCore. Instruções criadas para novos formatos podem ser reutilizadas em documentos semelhantes. A AWS apresenta um guia de implementação, sem divulgar medidas independentes de precisão para cada tipo documental.","title":"AWS apresenta processamento de documentos que aprende com AgentCore","topics":[],"translations":[{"api_url":"https://newsverum.com/api/v1/articles/agentcore-self-improving-document-processing-idp-2026?lang=tr","language":"tr","url":"https://newsverum.com/tr/news/agentcore-self-improving-document-processing-idp-2026"},{"api_url":"https://newsverum.com/api/v1/articles/agentcore-self-improving-document-processing-idp-2026?lang=en","language":"en","url":"https://newsverum.com/en/news/agentcore-self-improving-document-processing-idp-2026"},{"api_url":"https://newsverum.com/api/v1/articles/agentcore-self-improving-document-processing-idp-2026?lang=ar","language":"ar","url":"https://newsverum.com/ar/news/agentcore-self-improving-document-processing-idp-2026"},{"api_url":"https://newsverum.com/api/v1/articles/agentcore-self-improving-document-processing-idp-2026?lang=fr","language":"fr","url":"https://newsverum.com/fr/news/agentcore-self-improving-document-processing-idp-2026"},{"api_url":"https://newsverum.com/api/v1/articles/agentcore-self-improving-document-processing-idp-2026?lang=es","language":"es","url":"https://newsverum.com/es/news/agentcore-self-improving-document-processing-idp-2026"},{"api_url":"https://newsverum.com/api/v1/articles/agentcore-self-improving-document-processing-idp-2026?lang=de","language":"de","url":"https://newsverum.com/de/news/agentcore-self-improving-document-processing-idp-2026"},{"api_url":"https://newsverum.com/api/v1/articles/agentcore-self-improving-document-processing-idp-2026?lang=pt","language":"pt","url":"https://newsverum.com/pt/news/agentcore-self-improving-document-processing-idp-2026"}],"url":"https://newsverum.com/pt/news/agentcore-self-improving-document-processing-idp-2026"},"version":"1"}