About this episode
Jul 6
Building the Context Flywheel for AI Data Agents
Summary In this episode Prukalpa Sankar, co-founder of Atlan, talks about what it takes to build a “context flywheel” for AI agents in data-intensive organizations. She explained why model intelligence alone isn’t enough to make AI useful in production, and how real performance d ... Show More
1 h
Jun 18
Holding Kafka Right: Product-Friendly Streaming with TypeStream
Summary In this episode Jevin Maltais talks about the practical realities of building reliable, product-focused streaming systems with Kafka. Jevin shares lessons from roles at Zapier, Humi, and Clio, where real-time synchronization, customer data unification, and document sync a ... Show More
49m 51s
Jun 8
Text to Data Products: Kaarvi’s End-to-End AI for Ingestion, Quality, and Dashboards
Summary In this episode Shravan Gunda, founder and CEO of Kaarvi AI, talks about building an AI-native, agent-driven data platform designed to eliminate the janitorial work that consumes most data teams. He explores Kaarvi’s multi-agent architecture that runs queries across seven ... Show More
52m 52s
Dec 2022
Update Your Model's View Of The World In Real Time With Streaming Machine Learning Using River
Preamble
This is a cross-over episode from our new show The Machine Learning Podcast, the show about going from idea to production with machine learning.
Summary
The majority of machine learning projects that you read about or work on are built around batch processes. The model i ... Show More
1h 16m
May 2024
MLOps + DevOps + Kubernetes with Annie Talvasto
<p>Machine learning models need updating - what's the reliable way to do it? While in Romania, Richard sat down with Annie Talvasto to talk about her work helping to build DevOps practices around machine learning: Building repeatable processes for data ingestions, cleaning, organ ... Show More
33m 17s
Jan 2023
Machine learning at small organizations
Why is ML is so poorly adopted in small organizations (hint: it’s not because they don’t have enough data)? In this episode, Kirsten Lum from Storytellers shares the patterns she has seen in small orgs that lead to a successful ML practice. We discuss how the job of a ML Engineer ... Show More
49m 50s
Feb 2022
AI Today Podcast: Overview of Synthetic Data
Machine learning algorithms need examples of data from which they can learn, especially supervised machine learning algorithms. However, one big challenge for those looking to put machine learning into practice is the lack of a sufficient quantity of good quality data examples fr ... Show More
47m 14s
Dec 2019
Serverless NLP Model Training
<p class="p1"><span class="s1">Alex Reeves joins us to discuss some of the challenges around building a serverless, scalable, generic machine learning pipeline.<span class= "Apple-converted-space"> </span> The is a technical deep dive on architecting solutions and a discussion of ... Show More
29m 2s
Nov 2023
AI in Machine Learning Infrastructure with Emmanuel Turlay, Founder & CEO of Sematic
In this episode, I talk with Emmanuel Turlay, Founder & CEO of Sematic, about the pivotal role of AI in Machine Learning infrastructure. Emmanuel shares his expertise in designing and building platforms for Machine Learning pipelines at scale, discussing key components such as da ... Show More
26m 56s
May 2023
Creating instruction tuned models (Practical AI #223)
At the recent ODSC East conference, Daniel got a chance to sit down with Erin Mikail Staples to discuss the process of gathering human feedback and creating an instruction tuned Large Language Models (LLM). They also chatted about the importance of open data and practical tooling ... Show More
26m 33s
Summary
Building, scaling, and maintaining the operational components of a machine learning workflow are all hard problems. Add the work of creating the model itself, and it’s not surprising that a majority of companies that could greatly benefit from machine learning have yet to either put it into production or see the value. Tristan Zajonc recognized the complexity that acts as a barrier to adoption and created the Continual platform in response. In this episode he shares his perspective on the benefits of declarative machine learning workflows as a means of accelerating adoption in businesses that don’t have the time, money, or ambition to build everything from scratch. He also discusses the technical underpinnings of what he is building and how using the data warehouse as a shared resource drastically shortens the time required to see value. This is a fascinating episode and Tristan’s work at Continual is likely to be the catalyst for a new stage in the machine learning community.
Announcements
- Hello and welcome to the Data Engineering Podcast, the show about modern data management
- When you’re ready to build your next pipeline, or want to test out the projects you hear about on the show, you’ll need somewhere to deploy it, so check out our friends at Linode. With their managed Kubernetes platform it’s now even easier to deploy and scale your workflows, or try out the latest Helm charts from tools like Pulsar and Pachyderm. With simple pricing, fast networking, object storage, and worldwide data centers, you’ve got everything you need to run a bulletproof data platform. Go to dataengineeringpodcast.com/linode today and get a $100 credit to try out a Kubernetes cluster of your own. And don’t forget to thank them for their continued support of this show!
- Schema changes, missing data, and volume anomalies caused by your data sources can happen without any advanced notice if you lack visibility into your data-in-motion. That leaves DataOps reactive to data quality issues and can make your consumers lose confidence in your data. By connecting to your pipeline orchestrator like Apache Airflow and centralizing your end-to-end metadata, Databand.ai lets you identify data quality issues and their root causes from a single dashboard. With Databand.ai, you’ll know whether the data moving from your sources to your warehouse will be available, accurate, and usable when it arrives. Go to dataengineeringpodcast.com/databand to sign up for a free 30-day trial of Databand.ai and take control of your data quality today.
- Atlan is a collaborative workspace for data-driven teams, like Github for engineering or Figma for design teams. By acting as a virtual hub for data assets ranging from tables and dashboards to SQL snippets & code, Atlan enables teams to create a single source of truth for all their data assets, and collaborate across the modern data stack through deep integrations with tools like Snowflake, Slack, Looker and more. Go to dataengineeringpodcast.com/atlan today and sign up for a free trial. If you’re a data engineering podcast listener, you get credits worth $3000 on an annual subscription
- Your host is Tobias Macey and today I’m interviewing Tristan Zajonc about Continual, a platform for automating the creation and application of operational AI on top of your data warehouse
Interview
- Introduction
- How did you get involved in the area of data management?
- Can you describe what Continual is and the story behind it?
- What is your definition for "operational AI" and how does it differ from other applications of ML/AI?
- What are some example use cases for AI in an operational capacity?
- What are the barriers to adoption for organizations that want to take advantage of predictive analytics?
- Who are the target users of Continual?
- Can you describe how the Continual platform is implemented?
- How has the design and infrastructure changed or evolved since you first began working on it?
- What is the workflow for someone building a model and putting it into production?
- Once a model has been deployed, what are the mechanisms that you expose for interacting with it?
- How does this differ from in-database ML capabilities such as what is offered by Vertica and BigQuery?
- How much understanding of ML/AI principles is necessary for someone to create a model with Continual?
- What is your estimation of the impact that Continual can have on the overall productivity of a data team/data scientist?
- What are the most interesting, innovative, or unexpected ways that you have seen Continual used?
- What are the most interesting, unexpected, or challenging lessons that you have learned while working on Continual?
- When is Continual the wrong choice?
- What do you have planned for the future of Continual?
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 show, Podcast.__init__ to learn about the Python language, its community, and the innovative ways it is being used.
- 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.
- To help other people find the show please leave a review on iTunes and tell your friends and co-workers
- Join the community in the new Zulip chat workspace at dataengineeringpodcast.com/chat
Links
The intro and outro music is from The Hug by The Freak Fandango Orchestra / CC BY-SA
Support Data Engineering Podcast
