With Intel AI Assistant Builder, Acer needed just three days to create a sales assistant proof of concept.
What sets an AI PC apart from a regular PC?
This new generation of PCs, introduced in December 2023 with the Intel® Core™ Ultra processor family, combines the power of a central processing unit (CPU), graphics processing unit (GPU) and neural processing unit (NPU) to elevate user productivity, creativity, gaming, entertainment, security and more.
Powerful hardware that delivers the performance needed for modern-day artificial intelligence (AI) workloads is only part of what makes a great PC an AI PC. The big opportunity for the PC industry is clear: develop new AI software and new user experiences that take advantage of this modern hardware.
Finding fast, efficient ways to create new AI assistants that help with everyday tasks is the next frontier for making AI PCs deliver the best AI experience.
At CES Las Vegas in January, Intel unveiled Intel® AI Assistant Builder (code-named Project SuperBuilder). It’s a fuss-free solution that enables computer makers and software vendors to create tailored AI assistants for any use case in minutes.
AI Assistant Builder takes the nitty gritty guesswork out of building these models. It breaks down the tasks to just three easy steps: choose a ready-made AI assistant model, download and install it, and then launch the program.
“We’re providing the industry the building blocks to create their own AI-centric content. That enables our customers to reduce their overall development time and speed up the rollout of their own smart solutions,” explained Olena Zhu, senior principal engineer in Intel’s Client Computing Group.
This is how it works:
- The app features a chat window where users can ask questions and upload or delete documents across numerous formats (including PDFs, spreadsheets, presentations and text files).
- Each time the user asks a question, the AI assistant responds based on the query. It learns from the conversation history, related documents and the inherent knowledge of the large language model (LLM).
- It also includes advanced AI safety guardrails that include profanity filters and a secondary safety system that guides the model to respond safely without bias.
- It has ever-growing rich feature sets to allow users to pick and choose different advanced features and custom-build their own AI assistant.
Intel’s key partners are already using AI Assistant Builder to craft customised models for targeted needs:
- Acer built an AI sales assistant proof of concept (POC) integrating its camera vision technology in just three days.
- In South Korea, Intel and Samsung Electronics introduced a generative AI chatbot at Kyobo Bookstore that runs on-device – not the cloud. It’s based on smart LLMs and enables customers to search for books and receive personalized information.
- Asus leveraged Intel’s technology to create a technical-focused Q&A assistant for its NUC customers.
AI Assistant Builder Speeds New Age of AI Helpers
Perfecting AI assistants from scratch is a time-intensive process that takes weeks, if not months, along with a deep knowledge of software programming and AI know-how.
Just months after it was first proposed, AI Assistant Builder was actively being used by original equipment manufacturers of PCs and independent software vendors around the world. And more customers are lining up to partner with Intel as their AI PC platforms mature.
“These AI assistants are powered by large language models (LLMs), retrieval-augmented generation (RAG), and other components optimized for performance and accuracy when run on AI PCs based on Intel CPUs, GPUs and NPUs,” said Zhu.
“Besides vertically optimised LLMs, each vertical or domain has its own set of workflows and feature requirements. At Intel, we also partner with our customers to customize workflows and AI features tailored to each customer.”
