Aitomatic and a leading integrated circuit design company

3X

faster issue resolution

75%

first-try success rate vs. 15-20% from generic AI tools

↓

significantly reduced dependency on senior experts

^*All results are self-reported and not identifiably repeatable. Generally, expected individual results will differ.

CASE STUDY

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 version

Llama 3.1 70B

Deployment

On-premises

Download full case study

THEIR STORY

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.

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.

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.Projected results:

3X faster issue resolution
75% first-try success rate vs. 15-20% from generic AI tools

“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

Previous slide

Next slide

Slide 1 of 2

Start building

Download models View documentation

Explore more

ConsumerBusiness

Shopify | Llama case studiesShopify uses Llama to generate product pages, localize content, and automate support, helping developers scale workflows and save time.Read more

ConsumerTech

Scribd, INC | Llama case studiesDelivering faster, cheaper and more accurate results with a Llama-powered AI content discovery assistant.Read more

Tech

Exati | Llama case studiesTransforming support for smart city platform clientsRead more

The IC field engineering Domain-Expert Agent pulls from specialized information to provide expert recommendations.

The DXA lifecycle leverages specific inputs to enhance performance.

Significantly reduced dependency on senior experts