Skip to main content
NVIDIA AI Podcast

Amperity Reimagines Data and Developer Workflows with AI - Ep. 271

36 min episode · 2 min read
·
Derek Slager

Episode

36 min

Read time

2 min

Topics

Productivity, Remote Work, Investing

AI-Generated Summary

Key Takeaways

  • Agentic AI Definition: Define agentic systems as programs where the LLM controls flow through retries, tool calls, or agent interactions—this shifts evaluation metrics, monitoring approaches, and system capabilities compared to traditional programs with simple LLM calls.
  • Vibe Coding Workflow: Launch 10 parallel LLM processes simultaneously, continue other work, then review results—discard 3-4 failures, refine 3-4 partial solutions, accept 2-3 complete outputs. This asynchronous approach multiplies engineering capacity beyond sequential coding methods.
  • Non-Technical Data Access: Text-to-SQL interfaces for non-programmers drove sustained adoption increases in cohort analysis, with users moving from occasional to frequent data introspection once SQL barriers were removed, enabling data-informed decisions across broader organizational roles.
  • Business Context Integration: Bootstrap LLMs with company-specific terminology and domain knowledge immediately—a car dealer's "taco" means Toyota Tacoma while a restaurant's means food item. Context-aware systems dramatically improve efficacy and user empowerment in customer data applications.

What It Covers

Derek Slager, CTO of Amperity, explains how his company uses AI agents to unify customer data across enterprises, discusses vibe coding workflows that transform developer productivity, and shares practical implementation strategies for agentic systems.

Key Questions Answered

  • Agentic AI Definition: Define agentic systems as programs where the LLM controls flow through retries, tool calls, or agent interactions—this shifts evaluation metrics, monitoring approaches, and system capabilities compared to traditional programs with simple LLM calls.
  • Vibe Coding Workflow: Launch 10 parallel LLM processes simultaneously, continue other work, then review results—discard 3-4 failures, refine 3-4 partial solutions, accept 2-3 complete outputs. This asynchronous approach multiplies engineering capacity beyond sequential coding methods.
  • Non-Technical Data Access: Text-to-SQL interfaces for non-programmers drove sustained adoption increases in cohort analysis, with users moving from occasional to frequent data introspection once SQL barriers were removed, enabling data-informed decisions across broader organizational roles.
  • Business Context Integration: Bootstrap LLMs with company-specific terminology and domain knowledge immediately—a car dealer's "taco" means Toyota Tacoma while a restaurant's means food item. Context-aware systems dramatically improve efficacy and user empowerment in customer data applications.

Notable Moment

Slager expected skepticism around AI-generated data analysis but discovered users trusted and adopted conversational interfaces more than anticipated, with people who previously relied on SQL experts now independently exploring data and maintaining high engagement levels over time.

Know someone who'd find this useful?

Episode Transcript

Hello, and welcome to the NVIDIA AI podcast. I'm your host, Noah Kravitz. From Magenta AI to VibeCoding, our guest has been at the forefront of showing how AI powered systems can empower engineers while delivering measurable business value. Derek Slager is cofounder and chief technology officer of Amperity, a company that's redefining how enterprises use data to better understand and serve their customers. Derek's here to talk about his journey founding Amperity, the tools his team is building, like Chuck Data, an AI agent for data engineers, and his perspective on how AI is reshaping not just the enterprise landscape, but the developer experience itself. So let's get to it. Welcome, Derek, and thanks so much for joining the NVIDIA AI podcast. Thanks, Noah. Great to be here. Great to have you. So let's start at the beginning. Tell us a little bit about Amperity. Yeah. So Amperity is an AI powered customer data cloud, and we help brands unify, understand, and activate customer data at scale, which is a lot of things. And, you know, we're really particularly focused on data quality. Right? Because we're big believers that, better data equals better results. Right? Right. You're funneling that through agentic use cases or otherwise. And so, we have a lot of, great capabilities to to help people all over a consumer business take advantage of that data, but it's all about getting the data right. So what inspired you to cofound the company, and how does your background, your own journey as an engineer kind of shape the direction of Imperity? Yeah. For sure. So, we started in 2016. Right? Like, which which, you know, I sometimes refer to as, like, the false start AI era. Right. Sure. You know, there was a lot of, you know, a lot of excitement about kind of, you know, deep neural networks and and and a lot of other kind of innovation happening in the AI space. But, certainly, it was, you know, nothing in comparison to the current AI wave. But but nonetheless, right, like, that was kind of you know, it was on a lot of people's minds. And and, you know, what we observed in kinda researching, Amperity was almost every consumer brand had a project to unify all their customer data. Mhmm. And yet we couldn't find a single one, and we tried pretty hard. We couldn't find a single one that said, yeah. Yeah. We solved it. Right? Despite all that effort. And and we just found that ridiculous. And so, you know, what inspired us to start Amparity was really the opportunity to help all these people who were trying and failing to solve a problem that was really important to their business, actually succeed in doing that. And and, of course, like, the the the key point there was, you know, all these people were smart. They were trying really hard to solve it. Right? So so clearly, the existing tools were insufficient. Because …

Get the full transcript (7,381 words) + summary by email — free

One-time email with the complete transcript and AI summary of this episode. No account needed.

One email, no spam. We’ll also show you what SignalCast does.

Browse all NVIDIA AI Podcast transcripts →

You just read a 3-minute summary of a 33-minute episode.

Get NVIDIA AI Podcast summarized like this every Monday — plus up to 2 more podcasts, free.

Pick Your Podcasts — Free

Keep Reading

More from NVIDIA AI Podcast

We summarize every new episode. Want them in your inbox?

Similar Episodes

Related episodes from other podcasts

Explore Related Topics

This podcast is featured in Best AI Podcasts (2026) — ranked and reviewed with AI summaries.

Read this week's Investing & Markets Podcast Insights — cross-podcast analysis updated weekly.

You're clearly into NVIDIA AI Podcast.

Every Monday, we deliver AI summaries of the latest episodes from NVIDIA AI Podcast and 192+ other podcasts. Free for one show.

Start My Monday Digest

No credit card · Unsubscribe anytime