customer_support · saas · workflow
Hexagon builds HxGN Alix AI assistant for Enterprise Asset Management using AWS generative AI services
Hexagon's EAM users had to navigate extensive PDF manuals to find information, while base language models lacked product-specific knowledge and frequently produced hallucinations, making them unsuitable without domain grounding.
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 · User submits free-text query
Users submit queries to HxGN Alix in free-text format.
Tools used
Amazon EKSMistral NeMoAmazon Bedrock GuardrailsAmazon Bedrock Knowledge BasesAmazon BedrockNVIDIA L40S GPUs
Outcome
HxGN Alix was successfully launched, optimizing internal workflows and elevating user satisfaction within secure enterprise environments.
What failed first
A proof of concept using an off-the-shelf NeMo model without internal knowledge bases revealed hallucination problems and insufficient product knowledge, making RAG integration necessary for accurate responses.
Results
Time saved1–60 seconds depending on the user's query
Volumereducing hallucinations
Grounding & classification
Source type: technical build writeup
30 fields verified against source quotes, 3 dropped as unverifiable.
conversational aidocument aiknowledge searchragknowledge basepolicy documentfailure mode describednamed customerproduction runtime claimedtools describedvendor confirmedworkflow describedsoftwarecustomer satisfactionemployee productivityerror reductiontechnical build writeupback office opscustomer supportautonomous resolutionrag answering