Document Processing · Enterprise Knowledge Search
Amsterdam City Archives needed to make a massive paper archive usable for the public despite handwritten documents, outdated Dutch, and limited search tools that made discovery difficult.
Reported impact
Amsterdam City Archives turned a hard-to-navigate paper archive into a multilingual conversational knowledge service, improving public access to cultural heritage and establishing a reusable model for archive digitization and discovery.
Amsterdam City Archives, Capgemini, and Microsoft built Chat with History as an agentic AI research assistant over centuries of archival material. The archive first prepared an AI-ready data layer by digitizing documents and applying Transkribus plus handwritten character recognition to transcribe hard-to-read records. Capgemini and Microsoft then used Azure AI Foundry, AI Search, Microsoft Agent Framework, and Speech Services Avatar to create a secure multilingual chatbot that translates old Dutch into modern Dutch, interprets archival material, and answers natural-language questions in the user’s language. Rather than just returning search hits, the system connects and contextualizes source material so users can ask questions such as when a street was built or how children played in the seventeenth century. The result shifts the archive from a passive document repository to an interactive knowledge service that makes cultural heritage searchable and explorable for a global audience.
Archival documents are digitized and transcribed with Transkribus and handwritten character recognition, indexed through AI Search, interpreted in Azure AI Foundry with agentic AI, and then delivered through Chat with History so users can ask natural-language questions and receive contextualized answers.
"By the end of 2025, about two percent of the archive will be digitized."
"Capgemini and Microsoft built on this foundation using technologies such as Microsoft Azure AI Foundry, AI Search, Microsoft Agent Framework, and the Speech Services Avatar."
"The Amsterdam City Archives worked with Capgemini and Microsoft to develop Chat with History, a chatbot that uses agentic AI to open Amsterdam’s history to the public."
"The City Archives invested in creating an AI-ready foundation by structuring data using Transkribus and Handwritten Character Recognition (HCR)."
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
Capgemini Sample Aug 7, 2025 Imperial War Museums Imperial War Museums needed to make more than 20,000 hours of oral history recordings accessible despite challenges such as regional accents, military terminology, multiple languages, and inconsistent audio quality. 20,000+ hours of historic oral history interviews Ask a question · Gemini 2.0 · Google Cloud 
OpenAI Sample Aug 31, 2026 Polimill Polimill needed to reduce administrative burden across fragmented Japanese municipal systems so public employees could find prior decisions, prepare assembly responses, and deliver services without each municipality… 3-5x development speed increase from Codex and OpenAI hands-on support Codex · GPT models · OpenAI API 
NVIDIA Sample Jul 7, 2026 Public Ministry of Rio Grande do Sul (MPRS) MPRS needed to manage rising legal caseloads, archived police inquiries, and public-service requests more efficiently, but the volume of legal documents and the need for compliant, locally controlled analysis made… 497 municipalities Archiving Intelligence Assistant (AIA) · Citizen Access Agent · Justice Intelligence platform 