iTromsø · IBM, VC2
10 minutes per day — time spent reviewing potential stories
Independently reportedMedia & entertainment · Document processing · NLP · In production
Document processing
Maschinenfabrik Reinhausen (MR) · appliedAI
Vendor-reportedManufacturingIn productionEnterpriseLLM
Vendor-reported. The customer is named and the numbers are quoted from the source page, but the account comes from the vendor. No independent confirmation.
Reported by appliedai.de (vendor self-report). Checked against the source page on 2026-09-06. 2 of 5 figures below appear on that page word for word; the rest are marked.
The problem
Low process efficiency and high susceptibility to errors in manually extracting key information from complex specification documents for product configuration and quoting.
What was deployed
- Vendor
- appliedAI
- Technique
- LLM
- Build or buy
- Built in-house or to order
- Deployment
- Custom build
- Data used
- specification documents
- Timeline
- 6 months
What changed
Each row is quoted from the source. Figures we could not find on the page in those words are marked — they are kept, not deleted, so you can judge them.
~3 sQ&A response timefrom 134 s for manual response
“~45x for QA – LLM average Q&A response: ~3 s (vs. 134 s for manual response)”
Not found on the source page in these words
~12 secondsSpecification extraction timefrom ~5 h manually70-pages document
“~1500x for Automated Extraction – Specification extraction (70-pages document): ~12 seconds (vs. ~5 h manually, for basic analysis and detailed analysis)”
Not found on the source page in these words
~13 sProduct matching timefrom estimated 3 h manually70-pages document, 3 products
“~830x for Automated Product Matching – Product matching (70-pages document, 3 products): ~13 s (vs. estimated 3 h manually)”
Not found on the source page in these words
90%Basic analysis extraction results accuracy
“90% for basic analysis extraction results”
Quoted word for word from the source
77%Detailed analysis extraction results accuracy
“77% for detailed analysis extraction results”
Quoted word for word from the source
Sources
- appliedai.de — vendor self-report, 2026-01-13
Similar deployments
Amplitude · Wolfia
4X — throughput of security questionnaires
Vendor-reportedTechnology & software · Document processing · AI agents · Scaled
Adyen · Rossum
70 — automation rate
Vendor-reportedBanking & finance · Document processing · NLP · Scaled · 2023
Skaylink · Moterra
dropped by around 80% — NIS2 preparation time
Vendor-reportedTechnology & software · Document processing · LLM · Scaled
OM Pharma · DrugCard
3 minutes — review time per article
Vendor-reportedPharma & biotech · Document processing · NLP · In production
AMPREP (Amalgamations Repco) · Cimplify.AI
100% — invoice automation
Vendor-reportedManufacturing · Document processing · NLP · In production