Case Studies
April 16, 2024

How Drata Collaborates on AI Workflows with Vellum

Akash Sharma
No items found.

Companies are constantly seeking ways to harness AI’s potential while navigating the challenges of security, privacy, and resource allocation.

Drata, a leading provider of security and compliance solutions, had a wealth of ideas and wanted to identify the right tools to quickly validate and bring them to life. 

That's when they discovered Vellum.

Who is Drata?

Drata is the world's most advanced security and compliance automation platform with the mission to build trust across the cloud.

With Drata, thousands of companies across the globe streamline over 20 compliance frameworks—such as SOC 2, ISO 27001, GDPR, and more—through continuous, automated control monitoring and evidence collection, resulting in a strong security posture, lower costs, and less time spent preparing for annual audits.

What brought them to Vellum?

Drata faced a common dilemma: how could they build AI capabilities that provide value to their customers, without compromising their focus on trust and data security?

Drata needed a resource efficient way to validate AI projects quickly. Traditional tools didn't provide the iterative workflow they were looking for.

Vellum emerged as the clear choice for Drata, offering a unique blend of accessibility, speed, and security.

We sat down with Pratik Bhat, Senior Product Manager at Drata to understand how they used Vellum to test and validate ideas, enabling them to advance existing projects and propel new initiatives forward.

How does Drata use Vellum today?

Vellum provides a powerful and user-friendly platform that allows for both product managers and engineers to collaborate on AI features. 

The platform's accessibility allowed team members to work independently, fostering a culture of innovation and self-reliance. Pratik Bhat, a product manager at Drata, worked alongside Lior Solomon, Drata’s VP of Data, to build prototypes and validate their hypotheses with effective testing. 

Today, Drata’s use of Vellum spans from prompt orchestration to managing complex workflows, enabling them to synthesize vast amounts of information and present actionable insights to their users.

AI Product Research and Discovery at Drata

Drata approaches AI product research and discovery in an iterative, data-driven, and customer-centric manner.

Their process begins with the ideation phase, where Drata collaborates with other product managers to identify viable AI-enabled use cases and deeply understand customer problems.

They then move to validation, creating a proof of concept (POC) using Vellum's Prompt and Workflow products, to test feasibility and collect initial feedback. The process concludes with prioritization and review, assessing the AI solution's effectiveness against defined criteria and gathering insights on the deployed POC from both customers and an internal expert council.

Lior and Pratik have started a blog to document their learnings with building AI-enabled products - check their latest article to learn about their process in detail.

Drata remains committed to ensuring the highest levels of security and privacy, so the next step in their journey is to develop a suitable evaluation approach for their products using Vellum Evals.

What impact has this partnership had on Drata?

Product Teams can Validate LLM Ideas Quickly

Using Vellum, Drata's product team can quickly validate ideas and determine whether they should move forward with them, allowing the team to ensure that resources are allocated to the most promising projects.

"We know the power of AI, but how do we make it secure and ensure that we're not compromising privacy and security while still providing value? Vellum has been a big part of accelerating that experimentation part, allowing us to validate that a feature is high-impact and feasible."

- Pratik Bhat, Senior Product Manager at Drata

Accelerated AI development

From a technical perspective, Vellum has reduced the time required to develop and iterate on AI features. Its intuitive interface and features have saved Drata hours in development time allowing Drata to focus even more on the quality of their AI features.

Informed Decision Making

In Enterprise planning, it's crucial to justify costs and feasibility before investing further. With Vellum, Pratik can quickly assess whether to pursue an idea and confidently advocate the viable options to management because of the Evaluations framework.

Collaborative development

Vellum provided a platform for the Drata team to easily collaborate, quickly build and test ideas. As Drata continues to bring AI into the fold of security and compliance, Vellum remains a partner in their journey and we’re proud to be a part of their story.

Want to Try Out Vellum?

Vellum has enabled more than 100 companies to build complex AI chatbot logic, evaluate their infra and ship production-grade apps. If you’re looking to develop a reliable AI assistant, we’re here to help you.

Request a demo for our app here or reach out to us at if you have any questions.

We’re excited to see what you and your team builds with Vellum next!


Join 10,000+ developers staying up-to-date with the latest AI techniques and methods.
Thanks for joining our newsletter.
Oops! Something went wrong.
Akash Sharma
Linkedin's logo

Co-founder & CEO at

Akash Sharma, CEO and co-founder at Vellum (YC W23) is enabling developers to easily start, develop and evaluate LLM powered apps. By talking to over 1,500 people at varying maturities of using LLMs in production, he has acquired a very unique understanding of the landscape, and is actively distilling his learnings with the broader LLM community. Before starting Vellum, Akash completed his undergrad at the University of California, Berkeley, then spent 5 years at McKinsey's Silicon Valley Office.

About the authors

No items found.

Related posts