TechnologyBusiness Intelligence

How HP Built a GenAI Data Chatbot in 3 Weeks Using Databricks Mosaic AI to Recover 20-30% of Data Team Time

HP, the global computing and printing company managing data products for 200+ million printers worldwide, deployed Databricks Data Intelligence Platform on AWS to unify customer data ingestion across business units and build an internal GenAI data chatbot. Using Databricks Mosaic AI, DBRX, Unity Catalog, and AI/BI Genie with a RAG architecture, HP built the chatbot in under three weeks — recovering 20-30% of data team time previously spent on manual SQL queries, achieving 20-30% cost savings versus AWS Redshift, and enabling 600+ Databricks users across the organization.

Impact

20-30%

Cost savings vs AWS Redshift

20-30%

Data team time recovered from manual SQL queries

3 weeks

Time to build GenAI data chatbot

600+

Active Databricks users

Challenge

HP's data teams spent significant time on manual SQL queries to answer business questions across complex customer datasets from 200+ million printers worldwide — creating bottlenecks, consuming engineering capacity, and leaving non-technical stakeholders unable to self-serve data insights.

Solution

HP deployed Databricks Data Intelligence Platform on AWS with Unity Catalog, Vector Search, and Mosaic AI, building a GenAI data chatbot using RAG architecture and the DBRX LLM — enabling natural-language data queries for 600+ users and eliminating routine manual SQL work within three weeks of development.

Tools & Technologies

What Leaders Say

This solution has quite a few pieces...The college intern implemented the end-to-end solution in less than three weeks.

William Ma, Data Science Manager, HP
Get the full context.

Sign up to read complete case studies, access detailed metrics, and unlock all use cases.

Full Story

HP manages data ingestion and customer data products at a scale that few organizations match — with more than 200 million printers worldwide generating telemetry and customer signals across multiple business units. Analysts and data teams were spending significant time on manual SQL queries to answer business questions, creating a bottleneck that slowed decision-making and consumed engineering capacity.

HP standardized on Databricks Data Intelligence Platform running on AWS to centralize data operations. The team implemented Unity Catalog for data governance and discoverability, Databricks SQL for analytical queries, and Vector Search for semantic retrieval across internal datasets. The platform gave HP a foundation to run large language models natively within the data environment — without exporting data to external AI services.

The breakthrough moment came when HP's team built an internal GenAI data chatbot using a RAG (Retrieval-Augmented Generation) architecture powered by Databricks Mosaic AI and the DBRX large language model. The chatbot allows analysts and business stakeholders to query HP's internal data in natural language — replacing manual SQL for routine questions and freeing data engineers to focus on higher-value work. As William Ma, HP's Data Science Manager, noted: "This solution has quite a few pieces...The college intern implemented the end-to-end solution in less than three weeks."

The impact was measurable across cost and productivity dimensions. HP achieved 20-30% cost savings versus its previous AWS Redshift environment. The chatbot recovered 20-30% of data team time that had been spent on manual SQL queries. The platform now supports 600+ Databricks users across HP's global business units, with AI/BI Genie enabling self-service analytics beyond the traditional analyst team.

Similar Cases

I
Ibotta
Increased
offer relevance improvement

Ibotta, the US digital rewards platform connecting millions of shoppers with cashback offers from brands across grocery and retail channels, consolidated its rewards infrastructure onto Databricks Data Intelligence Platform. Using Databricks Vector Search for semantic offer matching, AI/BI for self-service analytics, Unity Catalog for governance, and Lakeflow Jobs for pipeline orchestration, Ibotta improved offer relevance, increased shopper engagement, reduced recommendation latency, and streamlined operations by eliminating fragmented tooling across its data and ML teams.

RetailDUDatabricks Unity CatalogDVDatabricks Vector Search
TA
The AA
70%
routine query resolution time reduction

The Automobile Association (The AA), the UK’s leading roadside assistance provider serving 14 million members, integrated Databricks AI/BI Genie via Conversation APIs directly into Microsoft Teams. Non-technical staff can now query operational data in plain English within their existing communication platform, cutting routine query resolution time by up to 70% and freeing data specialists to focus on predictive modeling instead of fielding ad hoc report requests.

Financial ServicesDUDatabricks Unity CatalogDADatabricks AI/BI Genie
F
Furniture.com
95%
shopper engagement with ai review summaries

Furniture.com, the multi-brand furniture aggregator offering single-cart shopping across 70+ retail partners, deployed Databricks Data Intelligence Platform to build AI-powered product experiences at scale. Using Databricks Mosaic AI, Unity Catalog, Delta Lake, and MLflow, a five-person data team deployed 8 production AI models within one year — processing 4.5 million reviews, enriching 265,000+ products, and delivering AI-generated review summaries that engage 95% of shoppers and NLP-powered collections that boost conversion by 26%.

RetailDUDatabricks Unity CatalogDDDatabricks Data Intelligence Platform
E
Experian
35%
customer emails automated

Experian, the multinational data broker holding data on 1.1 billion people across 32 countries, built “Latte” — a GenAI email automation system — on Databricks Mosaic AI by fine-tuning a Llama 8B model. The system now handles 35% of incoming contact center emails autonomously, reduced model fine-tuning time 11x from 86 hours to under 8, and lifted customer NPS by 8%.

Financial ServicesDUDatabricks Unity CatalogDADatabricks Agent Bricks
A
Allspice
20% → 97%
ingredient matching accuracy

Allspice, a food technology startup building a kitchen operating system for consumers and recipe publishers, deployed Pinecone’s vector database to solve the inherent messiness of ingredient data that traditional text search could not handle. The implementation raised ingredient matching accuracy from roughly 20% to 97%, enabling the launch of recipe importing as a core product feature and expanding into a platform-wide semantic layer for search, recommendations, and conversational AI.

TechnologyTtext-embedding-3-largePPinecone
S
Sommo
500–800
additional leads generated monthly

Sommo built an AI-powered SRS generator in Make in a single day, generating 500–800 additional leads per month and achieving a 5x increase in active website users.

TechnologyMMakeOOpenAI
C
Confluent
15,000+
hours saved monthly

Confluent, a data streaming platform company with 2,000+ employees and 4,000+ customers, deployed Glean to solve the knowledge fragmentation that came with rapid growth from 250 to 2,000+ employees across 20+ systems. Glean indexed the company's full tool stack — Slack, Salesforce, Confluence, and more — enabling instant knowledge retrieval across all teams. The result: 15,000+ hours saved monthly, a 13% increase in support team satisfaction, and over 70% employee adoption.

TechnologyGGlean
H
Headstart
90–97%
code written by claude

Headstart, an AI-native software studio, uses Claude 3.5 Sonnet to write 90-97% of client code, compressing enterprise software project timelines from months to weeks and delivering 10-100x development speed.

TechnologyC3Claude 3.5 Sonnet