it_support · manufacturing · workflow
Linde builds internal employee chatbot with NLP training data from super.AI
Linde's voice-based chatbot could not reliably recognize user intent or named entities in natural language queries, causing employees to receive irrelevant information rather than useful answers from the internal knowledge base.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Linde submits training inputs
Linde provided a list of entities, utterances, and ground truth to initiate the data program.
Tools used
Super.ClassifyNLPNER
Outcome
super.AI produced accurate NLP and NER training data in 6 weeks, generating 88,000+ phrase variations and enabling 6M+ automations; Linde successfully launched the internal chatbot.
What failed first
The existing voice chatbot failed to understand user intent and named entities, rendering it unable to serve relevant information to employees.
Results
Time saved6 weeks
Grounding & classification
Source type: vendor customer story
23 fields verified against source quotes, 3 dropped as unverifiable.
chatbotconversational aidata extractiondocument classificationknowledge searchknowledge basehuman review describednamed customerproduction runtime claimedtools describedworkflow describedmanufacturingaccuracy improvementthroughput increasetime savedvendor customer storyback office opsit supportdocument to recordextract classify route