Search & retrieval

German Federal Ministry of Research, Technology, and Space (BMFTR) · deepset

Vendor-reportedPublic sectorGermanyIn productionPublic sectorNLP

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 deepset.ai (vendor self-report). Checked against the source page on 2026-09-06. 3 of 3 figures below appear on that page word for word.

The problem

Staff struggled to navigate a 200-page manual, causing delays and potential inconsistencies, and finding information was time-consuming and difficult.

What was deployed

Vendor
deepset
Products
Haystack Enterprise Platform, Haystack framework
Technique
NLP
Build or buy
Bought and customised
Deployment
Custom build
Data used
200-page Project Funding Manual
Scale
1000 queries conducted weekly
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.

1000queries handledweekly

1000 queries per week

Quoted word for word from the source

< 3response time

< 3 seconds response time per question

Quoted word for word from the source

100%compliance with C5 cloud security criteria

100% compliance with C5 cloud security criteria

Quoted word for word from the source

issue resolution time

Reduction in issue resolution time

Quoted word for word from the source

transparency

Enhanced transparency through verifiable source citations and references

Quoted word for word from the source

Thanks to the collaboration with deepset, we were able to develop a finished product in just six months that meets our agency's stringent requirements for information security and accuracy. We have learned a lot about developing products with artificial intelligence and have positioned ourselves for the future.
Josefine Theden-Schow, Project Manager, BMFTR

Sources

Similar deployments

Walmart · Microsoft

22% — global ecommerce growth

Independently reportedRetail & e-commerce · Search & retrieval · LLM · In production · 2024

Osprey · NOVOS

72.6% — share of AI answers

Vendor-reportedRetail & e-commerce · Search & retrieval · LLM · In production

Safe · Victoria Olsina

40.88% — Enterprise keyword visibility

Vendor-reportedOther · Search & retrieval · LLM · In production

SoWork · iGrow

100% — AI Visibility Score

Vendor-reportedTechnology & software · Search & retrieval · NLP · In production · 2026

WS Audiology · QueryNow

85% increase — daily active users

Vendor-reportedHealthcare · Search & retrieval · NLP · In production