logo
episode-header-image
Yesterday
51m 58s

Context Engineering as a Discipline: Bui...

Tobias Macey
About this episode
Summary
In this episode of the Data Engineering Podcast, host Tobias Macey welcomes back Nick Schrock, CTO and founder of Dagster Labs, to discuss Compass - a Slack-native, agentic analytics system designed to keep data teams connected with business stakeholders. Nick shares his journey from initial skepticism to embracing agentic AI as model and application advancements made it practical for governed workflows, and explores how Compass redefines the relationship between data teams and stakeholders by shifting analysts into steward roles, capturing and governing context, and integrating with Slack where collaboration already happens. The conversation covers organizational observability through Compass's conversational system of record, cost control strategies, and the implications of agentic collaboration on Conway's Law, as well as what's next for Compass and Nick's optimistic views on AI-accelerated software engineering.

Announcements
  • Hello and welcome to the Data Engineering Podcast, the show about modern data management
  • Data teams everywhere face the same problem: they're forcing ML models, streaming data, and real-time processing through orchestration tools built for simple ETL. The result? Inflexible infrastructure that can't adapt to different workloads. That's why Cash App and Cisco rely on Prefect. Cash App's fraud detection team got what they needed - flexible compute options, isolated environments for custom packages, and seamless data exchange between workflows. Each model runs on the right infrastructure, whether that's high-memory machines or distributed compute. Orchestration is the foundation that determines whether your data team ships or struggles. ETL, ML model training, AI Engineering, Streaming - Prefect runs it all from ingestion to activation in one platform. Whoop and 1Password also trust Prefect for their data operations. If these industry leaders use Prefect for critical workflows, see what it can do for you at dataengineeringpodcast.com/prefect.
  • Data migrations are brutal. They drag on for months—sometimes years—burning through resources and crushing team morale. Datafold's AI-powered Migration Agent changes all that. Their unique combination of AI code translation and automated data validation has helped companies complete migrations up to 10 times faster than manual approaches. And they're so confident in their solution, they'll actually guarantee your timeline in writing. Ready to turn your year-long migration into weeks? Visit dataengineeringpodcast.com/datafold today for the details. 
  • Your host is Tobias Macey and today I'm interviewing Nick Schrock about building an AI analyst that keeps data teams in the loop
Interview
  • Introduction
  • How did you get involved in the area of data management?
  • Can you describe what Compass is and the story behind it?
  • context repository structure
    • how to keep it relevant/avoid sprawl/duplication
  • providing guardrails
  • how does a tool like Compass help provide feedback/insights back to the data teams?
  • preparing the data warehouse for effective introspection by the AI
  • LLM selection
  • cost management
    • caching/materializing ad-hoc queries
  • Why Slack and enterprise chat are important to b2b software
  • How AI is changing stakeholder relationships
  • How not to overpromise AI capabilities 
  • How does Compass relate to BI?
  • How does Compass relate to Dagster and Data Infrastructure?
  • What are the most interesting, innovative, or unexpected ways that you have seen Compass used?
  • What are the most interesting, unexpected, or challenging lessons that you have learned while working on Compass?
  • When is Compass the wrong choice?
  • What do you have planned for the future of Compass?
Contact Info
Parting Question
  • From your perspective, what is the biggest gap in the tooling or technology for data management today?
Closing Announcements
  • Thank you for listening! Don't forget to check out our other shows. Podcast.__init__ covers the Python language, its community, and the innovative ways it is being used. The AI Engineering Podcast is your guide to the fast-moving world of building AI systems.
  • Visit the site to subscribe to the show, sign up for the mailing list, and read the show notes.
  • If you've learned something or tried out a project from the show then tell us about it! Email hosts@dataengineeringpodcast.com with your story.
Links
The intro and outro music is from The Hug by The Freak Fandango Orchestra / CC BY-SA
Up next
Oct 5
The Data Model That Captures Your Business: Metric Trees Explained
SummaryIn this episode of the Data Engineering Podcast Vijay Subramanian, founder and CEO of Trace, talks about metric trees - a new approach to data modeling that directly captures a company's business model. Vijay shares insights from his decade-long experience building data pr ... Show More
1h 1m
Sep 28
From GPUs-as-a-Service to Workloads-as-a-Service: Flex AI’s Path to High-Utilization AI Infra
SummaryIn this crossover episode of the AI Engineering Podcast, host Tobias Macey interviews Brijesh Tripathi, CEO of Flex AI, about revolutionizing AI engineering by removing DevOps burdens through "workload as a service". Brijesh shares his expertise from leading AI/HPC archite ... Show More
56m 31s
Sep 18
From RAG to Relational: How Agentic Patterns Are Reshaping Data Architecture
SummaryIn this episode of the AI Engineering Podcast Mark Brooker, VP and Distinguished Engineer at AWS, talks about how agentic workflows are transforming database usage and infrastructure design. He discusses the evolving role of data in AI systems, from traditional models to m ... Show More
52m 58s
Recommended Episodes
Nov 2024
#262 Self-Service Business Intelligence with Sameer Al-Sakran, CEO at Metabase
We’re improving DataFramed, and we need your help! We want to hear what you have to say about the show, and how we can make it more enjoyable for you—find out more here.We’re often caught chasing the dream of “self-serve” data—a place where data empowers stakeholders to answer th ... Show More
51m 33s
Mar 2025
#295 How To Get Hired As A Data Or AI Engineer with Deepak Goyal, CEO & Founder at Azurelib Academy
The role of data and AI engineers is more critical than ever. With organizations collecting massive amounts of data, the challenge lies in building efficient data infrastructures that can support AI systems and deliver actionable insights. But what does it take to become a succes ... Show More
52m 27s
Apr 2025
Specialized AI brains for physical industry
Everyone wants a piece of general purpose models. Instacart has deployed ChatGPT for recipes and meal planning. The Mayo Clinic is using it to summarize patient records. Schneider Electric is using an OpenAI LLM to generate sustainability reports. With such powerful models, what’ ... Show More
39m 2s
Jul 2022
IoT, IIoT and Managing Edge Data
Brian Gilmore (@BrianMGilmore, Director IoT/Emerging Technology @InfluxDB) talks about Edge and Industrial Edge Computing, as well as application and data challenges at the edge.SHOW: 634CLOUD NEWS OF THE WEEK - http://bit.ly/cloudcast-cnotwCHECK OUT OUR NEW PODCAST - "CLOUDCAST ... Show More
35m 37s
Nov 2024
Model Plateaus and Enterprise AI Adoption with Cohere's Aidan Gomez
In this episode of No Priors, Sarah is joined by Aidan Gomez, cofounder and CEO of Cohere. Aidan reflects on his journey to co-authoring the groundbreaking 2017 paper, “Attention is All You Need,” during his internship, and shares his motivations for building Cohere, which delive ... Show More
44m 15s
Jan 2025
3164: Breaking Data Silos: How Hammerspace is Powering AI Storage and Hybrid Cloud
As part of the IT Press Tour in Silicon Valley, I had the opportunity to sit down with David Flynn, CEO of Hammerspace, to explore how the company is redefining the future of enterprise data storage. At a time when AI-driven workloads and hybrid cloud computing are pushing storag ... Show More
24m 26s
Sep 15
#321 Developing Financial AI Products at Experian with Vijay Mehta, EVP of Global Solutions & Analytics at Experian
Financial institutions are racing to harness the power of AI, but the path to implementation is filled with challenges. From feature engineering to model deployment, the technical complexities of AI adoption in finance require careful navigation of both technological and regulato ... Show More
49m 28s
Feb 2025
How Can GenAI Make Analytics More Accessible to Product Teams? (with Mario Ciabarra)
Whether you prefer the term data-driven, or data-informed, or data-dazzled, it doesn't matter—today's tech cannot survive without high quality data sets AND the tools to use them effectively. But we also can't afford to think about data as the responsibility of jus ... Show More
27m 46s
Apr 2025
Andriy Burkov - The TRUTH About Large Language Models and Agentic AI (with Andriy Burkov, Author "The Hundred-Page Language Models Book")
Andriy Burkov is a renowned machine learning expert and leader. He's also the author of (so far) three books on machine learning, including the recently-released "The Hundred-Page Language Models Book", which takes curious people from the very basics of language models all the wa ... Show More
1h 24m
Mar 2025
189. Numbers Need Narrative: Use Data to Influence and Inspire
Why numbers are only as compelling as the narratives we attach to them. Facts and figures can be your friend, but before you load your presentation full of data, Miro Kazakoff has a word of caution: “Data’s objective, but people are not.”You might think that your data speaks for ... Show More
21m 9s