Built with BigQuery and Google AI: How Glean Enhances Enterprise Search Quality and Relevance for Teams
Customer Company Size
Large Corporate
Country
- United States
Product
- Glean
- Google Cloud Dataflow
- Vertex AI
- BigQuery
- Looker Studio
Tech Stack
- Google Cloud
- Kubernetes
- Tensor Processing Units (TPUs)
- Cloud SQL
- Cloud Storage
Implementation Scale
- Enterprise-wide Deployment
Impact Metrics
- Customer Satisfaction
- Digital Expertise
- Productivity Improvements
Technology Category
- Analytics & Modeling - Machine Learning
- Platform as a Service (PaaS) - Data Management Platforms
- Analytics & Modeling - Predictive Analytics
Applicable Industries
- Software
- Professional Service
Applicable Functions
- Business Operation
- Product Research & Development
Use Cases
- Edge Computing & Edge Intelligence
- Remote Collaboration
Services
- Cloud Planning, Design & Implementation Services
- Data Science Services
- System Integration
About The Customer
Glean is a company that specializes in providing enterprise search solutions that enhance productivity and reduce frustration for users by delivering personalized and relevant search results. The company focuses on searching across all workplace applications, websites, and data sources used within an enterprise. Glean's search results respect existing permissions, ensuring users only see what they are authorized to view. The company leverages advanced technology to understand user context, language, behavior, and relationships, providing a highly personalized search experience. Glean is built on Google Cloud, utilizing components such as BigQuery, DataFlow, and Vertex AI to deliver its services. The company is part of Google's Built with BigQuery initiative, which supports tech companies in building applications using data and machine learning products.
The Challenge
Glean faced the challenge of providing a powerful and personalized enterprise search experience across various workplace applications and data sources. The goal was to deliver highly relevant and personalized search results that respect existing permissions and take into account the user's role, projects, collaborators, and company-specific language. This required a robust technology stack capable of processing and analyzing large volumes of data efficiently, while also ensuring high security and scalability. Additionally, Glean needed to measure and optimize user satisfaction with the search results, which involved understanding user actions and identifying when search results were helpful or not.
The Solution
Glean's solution involves leveraging Google Cloud's advanced data processing, analytics, and AI/ML capabilities to build a powerful enterprise search platform. The company uses Google Cloud Dataflow to process and enrich data pipelines, extracting relevant information from various sources and augmenting it with relevance signals before storing it in a search index hosted on Google Kubernetes Engine. Glean also uses Dataflow to generate training data for its models, which are trained on Google Cloud. For analytical workloads, Glean uses BigQuery to store anonymized user actions and compute user satisfaction metrics, which are visualized using Looker Studio. Additionally, Glean uses Vertex AI to train state-of-the-art language models adapted to enterprise-specific language, utilizing TPUs for efficient training and inference. The search is powered by vector search served with encoders and ANN indices trained through Vertex AI. Glean's platform is built on a variety of Google Cloud components, including Cloud GKE, Cloud SQL, Cloud Storage, and more, providing a reliable, secure, scalable, and cost-effective infrastructure.
Operational Impact
Quantitative Benefit
Case Study missing?
Start adding your own!
Register with your work email and create a new case study profile for your business.
Related Case Studies.
Case Study
SET Creative Ditches Google Vault for Datto Backupify
When Kienholz first started at SET, the staff was using Microsoft Outlook for email with no form of data backup. It became apparent that something needed to change as the staff was often burdened with trying to recover emails from departed employees. Kienholz transitioned the team to Google’s Gmail and implemented Google Vault for backup purposes. While SET employees quickly adjusted to Gmail, which many use for personal email, the same could not be said for Google Vault. “Unlike most Google products, Vault was not user friendly at all. It’s very hard to search for items. We never really figured out how to do a restore either,” explained Kienholz. Due to SET’s work with high-profile brands, projects often go through many rounds of revisions right down to the eleventh hour. This means that every bit of information - especially data living in project managers’ emails - is crucial to delivering clients a polished design at deadline.
Case Study
Infosys achieves a 5–7 percent effort reduction across projects
Infosys, a global leader in consulting, technology, and outsourcing solutions, was facing significant challenges in application development and maintenance due to its distributed teams, changing business priorities and the need to stay in alignment with customer needs. The company used a mix of open source, home-grown and third-party applications to support application development projects. However, challenges resulting from distributed teams using manual processes increased as the company grew. It became more and more important for Infosys to execute its projects efficiently, so they could improve quality, reduce defects and minimize delays.
Case Study
Arctic Wolf Envelops Teamworks with 24x7 Cybersecurity Protection and Comprehensive Visibility
Teamworks, a leading athlete engagement platform, faced rising cyberthreats and needed enhanced visibility into its network, servers, and laptops. With software developers connecting from all over the world, the company sought to improve its security posture and position itself for future growth. The company had a secure platform but recognized the need for a more proactive solution to identify gaps within its technology infrastructure. Data exfiltration and malicious access were top concerns, prompting the need for a comprehensive security upgrade.
Case Study
Sawback IT and Datto Save Client From a Costly Mistake
Ballistic Echo, a software development house, faced a critical challenge when human error led to the deletion of thousands of lines of unique code. This incident occurred before the code was pushed to source control, resulting in significant loss of time, revenue, and work. The previous file-level backup solution they used was slow and inefficient, making it nearly impossible to manually recreate the lost work. The need for a more reliable and efficient business continuity solution became evident to avoid such disasters in the future.
Case Study
Opal Helps Customers Shine Thanks to Datto
SP Flooring & Design Center faced a ransomware attack that encrypted and locked their files. The attack was initiated through a compromised service account set up by an outside vendor. The ransomware infection was isolated quickly, but there was a concern about the extent of the data at risk. The company had backups in place but was unsure of how much information was compromised. The situation required immediate action to prevent further damage and restore the affected data.
Case Study
Zapier Aggregates Multiple Analytics in a Single Dashboard with the New Relic Platform
Zapier, a company that enables non-technical users to push data between hundreds of web applications, was facing a challenge in automating and provisioning servers for optimal performance. The company's environment consisted of 50 Linux servers on the Amazon Elastic Compute Cloud (EC2), a Django application split across several servers, and a backend consisting of a dynamic number of celery task workers fed by messages published to a RabbitMQ cluster. They also maintained a number of internal web services on nginx in front of Gunicorn and Node.js processes. Redis handled simple key and value stores, with logging handled by Graylog2 and ElasticSearch. However, they realized that no level of automation would be sufficient without an effective monitoring solution in place. They needed a tool that could provide immediate alerts when something was breaking and could be easily implemented into their environment.
