Enterprise Knowledge Search
While they were still in college, Michael Royzen and Justin Wei saw the potential for using large language models (LLMs) together with high-quality context to build an intelligent search engine for developers.
Reported impact
Phind is continuing to make its models faster and will continue using NVIDIA-powered Amazon EC2 P4d and Amazon EC2 P5 instances to achieve its goal. Using NVIDIA’s new TensorRT library, Phind expects to make its models five times faster than previously. While the company is still determining the best split of LLM training and inference across Amazon EC2 instances, it is very pleased with the overall performance.
While they were still in college, Michael Royzen and Justin Wei saw the potential for using large language models (LLMs) together with high-quality context to build an intelligent search engine for developers. When a developer uses Phind, they can type in a complex coding question to the search bar and receive an answer generated by AI along with links on the side to online sources. Phind can answer coding and development-related questions with much more precision than a generic search engine because it is trained in this context. The company trained its LLMs using NVIDIA A100 Tensor Core GPU-powered Amazon EC2 P4d Instances —which deliver high performance for machine learning training and high performance computing applications in the cloud—and NVIDIA H100 Tensor Core GPU-powered Amazon EC2 P5 Instances , the highest performance GPU-based instances for deep learning and high performance computing applications.
LLMs were becoming more accurate, but many still acted as summarizers.
Phind can answer coding and development-related questions with much more precision than a generic search engine because it is trained in this context.
Software engineering requires a lot of specific knowledge, and traditional search engines often produce responses to technical questions that are too broad or shallow to help developers solve problems quickly.
When a developer uses Phind, they can type in a complex coding question to the search bar and receive an answer generated by AI along with links on the side to online sources.
When the cofounders of Phind were seniors at the University of Texas at Austin, they saw an opportunity to use LLMs as a search engine by feeding them high-quality context.
While they were still in college, Michael Royzen and Justin Wei saw the potential for using large language models (LLMs) together with high-quality context to build an intelligent search engine for developers.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
AWS Sample Feb 14, 2025 MANZ MANZ , an Austrian company that provides information services for legal and tax professionals, sought to revolutionize how its registered users searched its vast repository of legal documents. 30% expected savings Amazon Neptune · Amazon OpenSearch Service AWS Sample Jan 28, 2025 Bynder Bynder initially acquired a company to incorporate visual search capabilities into its software. The fast rate of customer adoption encouraged Bynder to build on its success. One of Bynder’s customers states that the time spent searching for assets for a typical campaign task has… Amazon Bedrock · Amazon Titan Multimodal Embeddings AWS Sample Dec 11, 2024 Goodnotes Founded in 2011, Goodnotes has been a leader in digital note-taking and productivity, now serving over 24 million monthly active users. As a pioneer in digital handwriting, Goodnotes was among the first apps to support… Founded in 2011, Goodnotes has been a leader in digital note-taking and productivity, now serving over 24… Amazon Bedrock · Amazon CloudWatch · Amazon EKS 