{"slug": "building-a-technical-literature-dashboard-with-power-automate-power-apps-ldx-hub", "title": "Building a Technical Literature Dashboard with Power Automate Power Apps LDX hub StructFlow", "summary": "Creation of TechLit Viewer, a technical literature management system built using a no-code/low-code stack that combines LDX hub StructFlow for AI-powered data extraction from PDFs, patents, and reports with Microsoft 365 tools like SharePoint, Power Automate, and Power Apps. The system automatically extracts eight structured fields from documents, stores them in SharePoint lists, and displays the data through both a Power Apps interface and a standalone HTML dashboard featuring interactive charts. In testing across 18 documents, the system achieved 83% extraction accuracy, with the remaining inconsistencies attributed to mixed-language issues in the field for major technology domain.", "body_md": "Verification Case Report #006 — 2026.05.18 | Time spent: ~3 days\nWe built TechLit Viewer — an end-to-end technical literature management system that uses LDX hub StructFlow to extract structured data from documents, Power Automate to keep everything updated, and both Power Apps and a standalone HTML dashboard for visualization.\nMany customers express a need to continuously collect and evaluate technical literature across diverse fields. The old approach — storing PDFs and patent documents in folders — made it nearly impossible to answer questions like \"which technologies are at which maturity level?\" or \"which documents are most relevant to our business?\"\nWe set out to verify whether a practical technical literature management system could be built within a no-code/low-code stack by combining LDX hub StructFlow for AI extraction with Microsoft 365 tools for storage, automation, and display.\nWhat we're testing: Can StructFlow turn unstructured technical documents (PDFs, patents, reports) into structured data that integrates cleanly with SharePoint, Power Automate, and Power Apps?\n// TechLit Viewer — System Overview\n[1] INPUT Source files (PDF / patents / reports)\n└─ Stored in SharePoint document library. 18 documents total.\n[2] AI EXTRACTION LDX hub StructFlow\n└─ Auto-extracts 8 fields:\nTitle / DocType / Authors / Year / FieldMajor /\nTRL / RelevanceScore / Summary\n[3] DATA LAYER SharePoint Lists (TechLit_Master / TechLit_Metrics)\n└─ Power Automate writes; Power Apps + HTML dashboard reads.\n[4] AUTOMATION Power Automate (2 flows)\n└─ ① Auto-extract on item update (TechLit_Pipeline_UPDATE)\n② Manual bulk processing (TechLit_BulkUpdate)\n[5] DISPLAY Power Apps (TechLit_Viewer) + HTML dashboard\n└─ 4-screen Power Apps + standalone HTML dashboard\nFires automatically when a SharePoint list item is updated. Detects new document registrations or changes to existing records, sends the file to StructFlow, and immediately writes the extracted results back. Day-to-day document additions are fully automated via this flow.\nA manual-trigger flow for bulk processing all 18 documents. Used after schema changes, prompt revisions, or for initial data loading. Iterates through all items with a foreach loop, waits for StructFlow polling to complete, and writes results back to the list.\nKey design insight: The update trigger excels at immediacy but isn't suited for full reprocessing. The manual trigger handles bulk operations well but requires operator action. Using both flows together covers both daily operations and administrative tasks.\nSchema design started from the question: \"what do we want to decide?\" — not \"what can we extract?\"\nAbout TRL (Technology Readiness Level): Originally developed by NASA and adopted by EU Horizon programs. Levels 1–3 = basic research, 4–6 = demonstration, 7–9 = operational/production. Quantifying maturity makes it easy to distinguish research-stage from production-ready technologies at a glance.\nAlongside Power Apps, we built a standalone HTML dashboard (techlit_dashboard.html\n) that runs entirely in the browser — no Power Apps dependency. This makes it easy to share with executives or external stakeholders.\n// StructFlow extraction results stored directly as a data array\nconst data = [\n{\nid: 17,\ntitle: 'Immobilized Photocatalyst Paper',\ndocType: 'patent',\nauthors: '[Author name masked]',\nyear: 2002,\nfieldMajor: 'Chemistry',\ntrl: 4,\nrelevance: 'high',\nurl: '' // SourceFileUrl — will become a live link once populated\n},\n// ... 18 documents total\n];\nThe dashboard includes 4 charts (technology domain distribution, TRL distribution, year-over-year trend, document type breakdown) plus a searchable full-document table. Passing StructFlow's structured data to Chart.js generates all analysis charts automatically.\n15 of 18 documents (83%) had all fields extracted correctly. The remaining 3 showed mixed-language inconsistencies in FieldMajor\n(English vs. Japanese) — no impact on usability, but a clear prompt improvement opportunity.\nAverage processing time per document: ~67 seconds (including StructFlow polling). Full run of all 18 documents: ~20 minutes. Both scheduled and trigger-based execution confirmed stable.\nEnvironmental Science was the largest category (6 documents), followed by Materials Science (4). TRL distribution: basic research (1–3) was highest at 8 documents; operational stage (7–9) had 3. For the first time, we had a quantitative picture of the entire portfolio.\n15 of 18 documents scored RelevanceScore = High\n. By embedding our business context (translation & localization) into the StructFlow system prompt, we achieved automatic screening aligned with our actual evaluation criteria.\nBiggest insight: from \"searching\" to \"discovering\"\nTechnical documents that could previously only be searched by filename can now be filtered across TRL, technology domain, and relevance simultaneously. Being able to instantly narrow down to \"TRL ≥ 4 AND Materials Science AND High relevance\" fundamentally changes the speed of technology strategy decisions.\nColumn types (hyperlink vs. single line of text) can't be changed after the fact. Confirm the format Power Automate will write, then finalize column design before building.\nDon't start from \"what can we extract?\" — start from \"what do we need to decide?\" Including evaluation-axis fields like TRL\nand RelevanceScore\nfrom the beginning dramatically increases dashboard value.\nPower Apps suits day-to-day search and update operations; the HTML dashboard suits sharing and presentations. Using two UIs on the same data source expands both the audience and the use cases.\nMixed English/Japanese values like \"Materials Science\" and \"材料科学\" split aggregations. Adding an explicit instruction to the StructFlow system prompt (\"always output technology domains in English\") prevents this drift.\nKawamura International is a translation and localization company documenting its AI process experiments in public. StructFlow, RefineLoop, RenderOCR — and whatever comes next.", "url": "https://wpnews.pro/news/building-a-technical-literature-dashboard-with-power-automate-power-apps-ldx-hub", "canonical_source": "https://dev.to/kozo-ki/building-a-technical-literature-dashboard-with-power-automate-power-apps-ldx-hub-structflow-3aa4", "published_at": "2026-05-18 23:51:51+00:00", "updated_at": "2026-05-19 00:03:32.051865+00:00", "lang": "en", "topics": ["enterprise-software", "data", "developer-tools", "research"], "entities": ["LDX hub StructFlow", "Power Automate", "Power Apps", "SharePoint", "Microsoft 365", "TechLit Viewer"], "alternates": {"html": "https://wpnews.pro/news/building-a-technical-literature-dashboard-with-power-automate-power-apps-ldx-hub", "markdown": "https://wpnews.pro/news/building-a-technical-literature-dashboard-with-power-automate-power-apps-ldx-hub.md", "text": "https://wpnews.pro/news/building-a-technical-literature-dashboard-with-power-automate-power-apps-ldx-hub.txt", "jsonld": "https://wpnews.pro/news/building-a-technical-literature-dashboard-with-power-automate-power-apps-ldx-hub.jsonld"}}