LLAMA 3.1 70B
Aitomatic and a leading integrated circuit design company
Specialized Llama-powered Domain-Expert Agent captures and scales expert knowledge to enable more efficient field engineering
At a glance
Industry: Manufacturing
Use case: Equipping field engineers with on-demand expert advice
Goal: Resolve customer queries faster and more effectively
Llama versions: Llama 3.1 70B
Deployment: On-premises
3X
75%
*All results are self-reported and not identifiably repeatable. Generally, expected individual results will differ.
Empowering semiconductor companies with AI
Aitomatic is transforming the semiconductor industry with its Domain-Expert Agents (DXAs). Through its neurosymbolic AI technology, Aitomatic helps semiconductor companies capture and scale their deep domain expertise to enhance and transform operations
THEIR GOAL
Faster and more effective query resolution
A leading producer of integrated circuits (ICs) and software solutions was seeing inefficient response times and inconsistent quality from its customer support. The company wanted Aitomatic to create an AI solution that could capture and scale its veteran experts’ knowledge to help streamline support and improve customer satisfaction.
THEIR SOLUTION
A field-support Domain-Expert Agent powered by Llama
Aitomatic developed a DXA to rapidly gather and synthesize the IC design company’s knowledge, ultimately providing expert guidance and reliable responses to field engineers. The DXA uses Llama 3.1 70B for training and operational problem-solving.
With open-source Llama as the foundation, Aitomatic jumpstarted its efforts and reduced development time and costs. Llama also enabled the company to maintain full ownership and control of its DXA trained with sensitive company information, eliminating dependency on proprietary models.
The IC field engineering Domain-Expert Agent pulls from specialized information to provide expert recommendations
THEIR APPROACH
Capturing and scaling IC design expertise
The DXAs were developed using three key steps: capture, train, and apply. During capture, technical manuals, notes, expert opinions and programs were structured and stored. Next, the DXA was augmented with synthetic knowledge so it could handle a wide range of support situations. The trained DXA was then deployed, pulling from the company’s product specifications and troubleshooting guides as it was used in the field
The DXA lifecycle leverages specific inputs to enhance performance.
THEIR SUCCESS
Expert insights on demand make field engineers faster and better
The Llama-backed DXA has successfully captured decades of specialized knowledge, scaling the expertise across the company. Field engineers can now handle customer inquiries with greater speed and independence, minimizing the need for senior staff involvement
• 3X faster issue resolution
• 75% first-try success rate vs. 15-20% from generic AI tools
• ↓ Significantly reduced dependency on senior experts
Llama stood out because of its great customizability and versatility. The model could be easily fine-tuned for semiconductor terminology and concepts and used as a modular component in agentic problem-solving flows, enabling highly specialized Domain-Expert Agents that could understand and respond to complex IC design queries efficiently.
“Llama stood out because of its great customizability and versatility. The model could be easily fine-tuned for semiconductor terminology and concepts and used as a modular component in agentic problem-solving flows, enabling highly specialized Domain-Expert Agents that could understand and respond to complex IC design queries efficiently.”
Vinh Luong, Aitomatic Head of Open Source
Models used
Create generative AI applications for business with open-source large language models that bring unmatched control, customization and flexibility.
Llama 3.1 70B
Stay up-to-date
Our latest updates delivered to your inbox
Subscribe to our newsletter to keep up with the latest Llama updates, releases and more.
