Never let your data fall asleep
Documents, images, databases, and research material built up inside an organization or a society are organised and structured so they can be searched, analysed, reused, and put to work with AI. Keep it. Order it. Connect it. And go on using it.
What it does, at a glance
- Organising documents
- Scanning and OCR
- Structure and metadata
- Full-text and AI search
- Visualisation and reuse
What it does (in detail)
- Document, version, and revision management
- Scanning, OCR, and OCR correction
- Structuring with XML and TEI
- Metadata design
- Full-text, dictionary, and semantic search
- Azure SQL, CSV, Parquet, and Data Lake
- Microsoft Fabric, semantic models, and Power BI
- Search, summarisation, and classification with LLMs and RAG
- Converting and reusing content, including ebook generation
Archive Map
About this field： Living Archive is not a single service we have just launched. It is a field we keep growing by combining decades of experience — document management, full-text search, content management, ebook generation, classical materials, databases, and data conversion — with newer technology such as OCR, TEI, Data Lake, Microsoft Fabric, Power BI, and AI.
-
Living Classics
Carrying the classics into the future as readable data.
For some fifteen years we have helped build and run the Japanese Literature Web Library. Building on that experience, we aim to preserve classical materials not merely as images or PDFs, but as data that can be searched, cited, researched, and used by AI.
- Japanese Literature Web Library
- Databases of classical texts
- Full-text and dictionary search
- Nihon Shoki and Jingu Tenryaku
- Originals and images, OCR, OCR correction
- XML, TEI, and metadata
- GakuNin RDM and research data publication
-
Homes
Managing documents together with their history of change.
A management system for investment trust agreements that we have built and run for around twenty years. Documents are not simply stored: changes, generation, and history are all managed alongside them.
- Investment trust agreements
- Document database
- Managing the body of each agreement
- Old-and-new comparison tables
- Automatic updates to the text
- Version and revision management
- Search
-
BookFile
Reusing content in another form.
An ebook generation service we have helped develop and operate for many years. Accumulated content is managed and converted into other deliverables, ebooks among them.
- Content management
- Data conversion
- Ebook generation
- Automated processing
- Long-term operation
-
Corporate Archive
Turning the data sleeping inside a company into an asset.
Print, images, production data, PDFs, and documents accumulated over decades are organised into an environment where they can be searched, browsed, and reused — and, in time, connected to AI search, summarisation, classification, and discovery of related material.
- Print, images, and production data
- Organising PDFs, documents, and files
- Search, browsing, and reuse
- AI summarisation and classification
- Discovering related material
-
Data Archive
Turning operational data into an asset you can analyse.
Documents are not the only target. Operational data held in SQL and elsewhere is organised into a data asset that stays usable for the long term, and carried through to visualisation and AI.
- Azure SQL, CSV, and Parquet
- Data Lake and Lakehouse
- Microsoft Fabric and mirroring
- Semantic models and Power BI
- Data analysis with AI
Keep it. Order it. Connect it. And go on using it.
Scattered tools, brought into one flow.
Every Living service sits on the same foundation: LINE, Web, Google Sheets / Excel, freee, AI, Automation. From the first contact with a customer through booking and purchase, customer records, sales, accounting, analysis, and on to the next action — it all becomes one continuous flow.
PDF, 1 A4 page — updated September 2026
Let’s start from “what would this look like for us?” and work it out together.
Start with a conversation