Normalized claim
NC programming steps: 177 steps
Traditional CAM-based NC programming involves 177 steps, but TTMC Brain automates all but the first and last stages.
MicrosoftEvidence: Medium50/100
ARUM: LLM-powered AI machining character KAYA using Azure OpenAI, Azure AI Search and Azure Speech
Use case typeFactory automationUpdated 6 days ago
ARUM designed a machining center that leverages LLMs so workers can operate the tool through natural conversations. The solution features AI character KAYA and integrates Microsoft AI services on Azure to support chat, voice communication, summarization, database search, and fallback agent behavior. KAYA enables novice workers to perform high-precision machining and helps automate NC program creation in a manufacturing environment facing skilled labor shortages.
- Organization
- ARUM
- Industry
- Manufacturing
- Location
- Japan
- Published
- July 2026
Reported outcomes
177 steps
NC programming stepsOther quantified impact
2 stepsNC programming steps−50%manufacturing cost per part
Strategic outcomes
Employee experienceEnabled novice workers to perform high-precision machiningOther strategic outcomeSupported multilingual operator interactionSpeed & agilitySimplified machine operation through natural conversation
Why do we believe this?Outcome claims, sources, and evidence checks
Normalized claim
NC programming steps: 2 steps
Traditional CAM-based NC programming involves 177 steps, but TTMC Brain automates all but the first and last stages.
Normalized claim
Manufacturing cost per part: 50% decrease
NC programming accounts for 50% of the production cost per part, so automating this stage could cut production costs in half.
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- ARUM
- Provider
- Microsoft
- Maturity
- Unknown
- Linked source
- Microsoft Customer Stories
No explicit deployment-stage evidence found.
Customer identity supportedSource describes one deploymentMaturity evidence evaluated
Primary read
Use case focus
Showing 3 of 4
- 1Factory automation
- 2Industrial assistant
- 3Voice automation
- Shortage of skilled manufacturing technicians
- Existing machining centers and NC programming required veteran expertise
- Need for a natural-language interface that novices could use reliably
- Developed TTMC Origin with LLM-powered AI character KAYA
- Used Azure Speech for voice communication, Azure OpenAI for summarizing and interpreting conversations, and Azure AI Search for database searches
- Added Foundry Agent Service on Microsoft Foundry as fallback generic AI
- Connected KAYA to TTMC Brain to generate machining programs and control the machining center
- Supported multilingual interaction for manufacturing sites
- 177 NC programming steps reduced to two
- 50% manufacturing cost reduction per part
- Enabled novice workers to perform high-precision machining
- Prototype completed and reservations opened
Architecture
TTMC Origin includes an industrial-PC-based LLM running on the machine, the AI character KAYA for voice/chat interaction, Azure Speech, Azure OpenAI, Azure AI Search, and Foundry Agent Service on Microsoft Foundry as fallback. KAYA feeds conversation context into TTMC Brain, which automatically generates machining programs and controls the machining center.
Sources & evidence1
Evidence: Medium50/100Evidence strength
- Customer explicitly identified
- Primary source available
- Quantified outcome available
- Technical implementation details available
Type: Customer StoryPublished: Jul 22, 2026Publisher: MicrosoftEvidence: PrimaryConfidence: High
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
Browse the catalog
Was this useful?
Community
Comments
No published comments yet.