--- title: "Project data foundation" canonical_url: https://fremtidenstegnestue.dk/en/for-studios/project-data-foundation markdown_url: https://fremtidenstegnestue.dk/en/for-studios/project-data-foundation.md author: "Fremtidens Tegnestue" page_type: b2b-service primary_intent: "The studio wants to understand what basis must be in place before an agent can deliver preparation that architects can use in a concrete case." primary_keyword: "project data foundation" audience: "Architecture studios, specialist advisers and project teams in the built environment." summary: "Many studios spend too much time finding the current version of a project fact. A project data foundation connects drawings, product choices, decisions, revisions and documents so the team can see what is reliable, what is missing and what needs professional review." source_basis: - "Danish Association of Architectural Firms: Recommendations for AI practice: https://www.danskeark.dk/content/anbefalinger-til-ai-praksis" - "Molio / ConTech Lab: AI in construction: https://molio.dk/viden/publikationer-og-rapporter/ai-i-byggeriet/" - "Danish Data Protection Agency: Artificial intelligence: https://www.datatilsynet.dk/regler-og-vejledning/kunstig-intelligens" human_validation: "The architect assesses whether the agent's synthesis makes professional sense in the concrete case. The project lead approves which information can be used externally and which must remain internal preparation. Specialists or suppliers validate technical, commercial and authority consequences when the agent can only surface a question." responsibility_line: "AI can prepare, compile and flag uncertainty. The architect validates the consequences." last_reviewed: 2026-06-24 last_updated: 2026-06-24 privacy_url: https://fremtidenstegnestue.dk/en/privacy related_pages: - url: https://fremtidenstegnestue.dk/en/for-studios/cad-to-price-appendix-ordering-manual relation: related-b2b - url: https://fremtidenstegnestue.dk/en/for-studios/project-change-automation relation: related-b2b - url: https://fremtidenstegnestue.dk/en/for-studios/drawing-excel-pdf-workflow relation: related-b2b - url: https://fremtidenstegnestue.dk/en/for-studios/product-data-digital-backoffice relation: related-b2b - url: https://fremtidenstegnestue.dk/en/for-studios/studio-digital-backoffice relation: related-knowledge - url: https://fremtidenstegnestue.dk/en/for-studios/studio-knowledge-foundation relation: related-knowledge - url: https://fremtidenstegnestue.dk/en/for-studios/ai-strategy-for-architecture-studios relation: related-knowledge status: published --- # When project knowledge is scattered across drawings, spreadsheets and email Canonical URL: https://fremtidenstegnestue.dk/en/for-studios/project-data-foundation Markdown URL: https://fremtidenstegnestue.dk/en/for-studios/project-data-foundation.md Entity type: b2b-service Language: en Author: Fremtidens Tegnestue Published: 2026-06-24 Last updated: 2026-06-24 Privacy: https://fremtidenstegnestue.dk/en/privacy ## Short answer Many studios spend too much time finding the current version of a project fact. A project data foundation connects drawings, product choices, decisions, revisions and documents so the team can see what is reliable, what is missing and what needs professional review. ## Who it is relevant for Architecture studios, specialist advisers and project teams in the built environment. ## What FT can prepare - Gather the information already used in the project and show where it comes from. - Point out relations between rooms, codes, products, documents, status and revisions. - Prepare drafts for selected outputs where sources, assumptions and gaps are visible. - Flag where the studio must stop and validate before material is used with a client, supplier or authority. ## What the architect validates - The architect assesses whether the agent's synthesis makes professional sense in the concrete case. - The project lead approves which information can be used externally and which must remain internal preparation. - Specialists or suppliers validate technical, commercial and authority consequences when the agent can only surface a question. ## Where the need appears in a studio The need does not appear because the studio needs yet another system. It appears when project knowledge is spread across drawings, spreadsheets, PDFs, emails and experienced colleagues, making the team spend time deciding what can be treated as reliable. ## Anonymised example In an anonymised project workflow, the same product choice appeared in a drawing, a spreadsheet, a price appendix and a manual. When the variant changed, the point was not to make the system choose again. The point was to make visible which documents still relied on the old information. - The project basis had to show product, variant, price, documentation and source basis. - The architect and project lead had to see what was certain, uncertain and ready for approval. ## Data sources and method Start with one real case and one piece of preparation that currently requires many manual lookups. Define what the agent may treat as a source, assumption, working hypothesis and stop rule. Use project data as a control basis, not as a hidden decision machine. - CAD/BIM extracts - spreadsheets - PDF outputs - product data - datasheets - project folders - revision history ## First pilot Choose one project type and one piece of preparation, for example a price appendix or manual. Map which information the agent must find, document and flag as uncertain before an architect uses the output. ## Belief shift The value is not automating the project, but making the project basis source-aware, traceable and easy to check. ## FAQ ### What is a project data foundation? It is a shared basis for the project's important information so an agent can prepare work with visible sources, relations and uncertainty. ### Do we need everything in one database? No. It is often better to start with the relations that already create manual follow-up work in a concrete case. ### Is a project data foundation the same as an AI agent? No. The foundation is the basis the agent works from. The agent becomes useful when it can show its sources, assumptions and stop rules. ## Sources and basis - [Danish Association of Architectural Firms: Recommendations for AI practice](https://www.danskeark.dk/content/anbefalinger-til-ai-praksis) - [Molio / ConTech Lab: AI in construction](https://molio.dk/viden/publikationer-og-rapporter/ai-i-byggeriet/) - [Danish Data Protection Agency: Artificial intelligence](https://www.datatilsynet.dk/regler-og-vejledning/kunstig-intelligens) ## Uncertainty and boundaries A project data foundation does not make old information right. It makes relations, sources and uncertainty visible so the studio can judge whether the basis is strong enough to use. ## Next step Map an agent-ready project flow ## Related pages - [From CAD to price appendix, ordering and manual](https://fremtidenstegnestue.dk/en/for-studios/cad-to-price-appendix-ordering-manual): related-b2b - [Traceable project changes](https://fremtidenstegnestue.dk/en/for-studios/project-change-automation): related-b2b - [Drawing, spreadsheet and PDF workflow](https://fremtidenstegnestue.dk/en/for-studios/drawing-excel-pdf-workflow): related-b2b - [Digital backoffice for product data](https://fremtidenstegnestue.dk/en/for-studios/product-data-digital-backoffice): related-b2b - [Studio digital backoffice](https://fremtidenstegnestue.dk/en/for-studios/studio-digital-backoffice): related-knowledge - [Studio knowledge foundation](https://fremtidenstegnestue.dk/en/for-studios/studio-knowledge-foundation): related-knowledge - [AI strategy for architecture studios](https://fremtidenstegnestue.dk/en/for-studios/ai-strategy-for-architecture-studios): related-knowledge ## Citation guidance When citing this page, cite the canonical HTML URL (https://fremtidenstegnestue.dk/en/for-studios/project-data-foundation) as the public source and use this Markdown URL only as the agent-readable representation. Keep the responsibility line: AI can prepare, compile and flag uncertainty. The architect validates the consequences.