How Tipalti Uses Snowflake Cortex AI to Democratize Data Insights
Tipalti is a global payables automation platform that processes $75 billion in payments annually for hundreds of high-growth companies. The company deployed Snowflake’s Cortex AI to build an internal AI prompt store, allowing sales and marketing teams to query financial data without technical expertise. The result is 5x faster parallel query execution and more than 600 ad-hoc analyses completed since launch.
Impact
5x
Parallel query throughput increase
$75 billion
Annual payments managed on platform
600+
Ad-hoc analyses completed since launch
50+
Users on the AI prompt store
10+
New features deployed since launch
Challenge
Tipalti’s non-technical sales and marketing teams had no direct path to the company’s financial data—generating insights required engineering support or specialized SQL skills, creating bottlenecks and inconsistent information across teams.
Solution
Tipalti built an AI prompt store on Snowflake Cortex AI using AI_COMPLETE, TRY_COMPLETE, and a custom Snowpark parallel execution function, giving business users pre-defined LLM prompts to query data directly from tools like Salesforce without technical assistance.
Tools & Technologies
AWSWhat Leaders Say
“The biggest benefit is that the insights are now always there for our people. If they want to analyze a certain opportunity or group of accounts, they can just log in, make a query, and it’s all there. They don’t have to think about how to build a prompt or manipulate data, they just get answers.”
“We had a clear strategic vision for our data architecture. We wanted maximum scalability with minimum infrastructure overheads, and that’s why we built our data warehouse on Snowflake.”
“Snowflake has enabled us to bring AI capabilities to our data, rather than moving data to the AI. This shift allows our teams to experiment and deploy AI-driven insights faster, while maintaining the vital security and governance of our data platform.”
“It would have been much more complicated to build this without Snowflake. Everything from security and maintenance would have taken a lot more effort. But with Snowflake we don’t have to worry about resources or external infrastructure and LLMs — we don’t need anything.”
Sign up to read complete case studies, access detailed metrics, and unlock all use cases.
Full Story
Tipalti sits at the intersection of finance and scale, automating payables for companies that collectively move $75 billion per year. When your customers depend on you to keep their payments running, data reliability and access speed aren’t operational preferences—they’re existential requirements. The company’s data team understood early that spreading the value of that data across the organization meant more than building dashboards for analysts. It meant giving sales reps and marketers the ability to ask questions themselves.
Before deploying Cortex AI, Tipalti’s non-technical teams faced a familiar barrier: they could see the data existed but couldn’t reach it without writing SQL or waiting for data engineering support. The company’s sales and marketing teams were particularly affected—they needed timely, consistent insights to evaluate opportunities and coordinate campaigns, but the gap between intent and insight created delays and inconsistencies between teams.
Tipalti’s engineering team built what they called an “AI prompt store” on Snowflake’s Cortex AI platform. This library of pre-defined LLM prompts lets non-technical users query data directly from the tools they already use, including Salesforce. Under the hood, the solution uses Cortex AI’s AI_COMPLETE function to execute LLM queries within SQL workflows, the response_format feature to eliminate hallucinations and enforce structured outputs, and TRY_COMPLETE to prevent single failures from collapsing batch processes. A custom Snowpark function enables multiple queries to run in parallel, multiplying throughput fivefold.
Since the system went live, over 50 users have run more than 600 ad-hoc analyses and accessed ten or more new features—all without data team involvement. Teams describe the experience as logging in and simply getting answers. The parallel execution architecture, built entirely within Snowflake without external inference infrastructure, has made the system faster, cheaper, and easier to maintain than equivalent third-party solutions would have been.
Tipalti’s next phase involves evolving the framework into a fully autonomous AI assistant layer using Cortex Semantic Models, RAG via Cortex Search, and improved embedding-based retrieval. For a company whose product promise is to simplify financial operations for businesses of every size, building the same simplicity into its own internal data systems is a logical extension of the mission.