Advertise on podcast: The Analytics Engineering Podcast

Can an AI agent do the work of a junior data analyst? Shreya Shankar, an incoming database professor at Carnegie Mellon University built a benchmark to find out. Her benchmark uses messy conditions: multiple databases, tribal knowledge, and unstructured text. In her tests, the best agents solved about 61% of queries on the first try. Tristan and Shreya get into why agents tend to pull everything into pandas instead of pushing computation down to the source, and why a good semantic layer makes such a big difference. They also cover why plugging agents into raw data goes badly while gold-layer tables with a semantic layer work much better. And they ask whether agents need their own version of the visual shortcuts humans use to spot what's interesting in data. They also cover evals. Shreya explains "criteria drift," the finding from her paper Who Validates the Validators? that people don't know what they want from an LLM judge until they see the outputs. She also explains why she wrote In Defense of AI Evals, and what practitioners can do today when exploratory data analysis doesn't map cleanly onto agent outputs. Finally, she previews her research at CMU on making AI SQL cheaper, including a custom inference engine for AI-powered queries. The Analytics Engineering Podcast is sponsored by Fivetran + dbt Labs.

AI agents are good at getting meaning from data, and the data stack companies have spent ten years building is the ideal source for it. Fivetran + dbt Labs CEO George Fraser, Tristan Handy, and Andreessen Horowitz general partner Martin Casado discuss why an open, composable data stack wins in a moment of fast change. The Analytics Engineering Podcast is sponsored by dbt Labs. Reach us at [email protected] with comments and guest suggestions.

Personal AI agents hit a tipping point, AI became a top voter issue, and OpenAI shelved GPT-6.1 Astra. Tristan Handy and Jason Ganz break down stories from the past few weeks and what they mean for data teams. In this episode: Personal agents: Instinct, Meta's Muse, Grokbot, and OpenAI's Dot, and why filtering information overload is the real prize. AI policy: 8% of voters now name AI their top issue, and senators ask whether recursive self-improvement should be illegal. GPT-6.1 Astra: why OpenAI canceled the release, including unsanctioned supply chain attacks in 29.2% of simulated runs. Jev: TypeSafe's decision model and how data teams can use it. Full show notes and links: https://roundup.getdbt.com Reach us at [email protected] with comments and guests suggestions This episode is sponsored by dbt Labs. Discover why more than 80,000 data teams use dbt to accelerate their data development.

Emilie Schario is co-founder and head of product and engineering at Kilo Code, the open-source, model-agnostic coding agent platform Anaconda acquired in July 2026. She joins Tristan Handy to talk why nobody on her 20-person engineering team is really an individual contributor anymore, and why she thinks data people are better prepared than software engineers for a world where everyone manages a portfolio of agents. The Analytics Engineering Podcast is sponsored by dbt Labs. Reach us at [email protected] with comments and guest suggestions.

Four stories: The political fight over data centers, claims about a physical AI model, Ian Macomber on the shape of the post-AI data stack, and an update on the Hugging Face story and what it means for how data teams think about evals. The Analytics Engineering Podcast is sponsored by dbt Labs. Reach us at [email protected] with comments and guest suggestions.

Guy Podjarny has built developer tools three times over: Blaze (acquired by Akamai), Snyk, and now Tessl. He joins Tristan Handy to argue that skills need the same lifecycle as code or teams end up scaling nothing but vibes, and to make the case that most companies will end up owning their own harness rather than renting one from a frontier lab. The Analytics Engineering Podcast is sponsored by dbt Labs. Reach us at [email protected] with comments and guest suggestions.

Tristan Handy and Jason Ganz are back for Roundup. This time: Stripe's $7 billion acquisition of OpenRouter, two new benchmarks showing data engineering agents are reliably good now, Exponential View's latest "are we in a bubble" gauges (verdict: no, not yet), and why your sales team shouldn't query Gong directly. The Analytics Engineering Podcast is sponsored by dbt Labs. Reach us at [email protected] with comments and guest suggestions.

Jeremiah Lowin built FastMCP as a side project days after Anthropic announced the Model Context Protocol. It's now downloaded millions of times a day. He joins Tristan Handy on why a skill file is a polite note rather than a workflow engine, why enterprises are choosing MCP over CLIs, and why the buyers he meets aren't ready to talk about the context layer at all—they want the security plumbing first.

Something new. Tristan Handy is joined by Jason Ganz for the first Roundup, a recurring conversation about the stories moving the ecosystem right now. This time: the OpenAI model that escaped its sandbox and hacked Hugging Face, Moonshot's Kimi K3 and what a restrictive license on open weights really means, and Katie Bauer's read on what changes for data teams as agents arrive. The Analytics Engineering Podcast is sponsored by dbt Labs. Reach us at [email protected] with comments and guest suggestions.

Shridhar Iyer spent more than 13 years inside Meta's data organization, most recently leading AI and the data stack. He joins Tristan Handy to talk about how deleting a single column can save millions at Meta scale, the abstraction stack that quietly powers the company, and the two steps every company needs to become AI-native. Plus a detour through the hard problem of consciousness. For full show notes and to read the podcast's companion newsletter, head to https://roundup.getdbt.com. The Analytics Engineering Podcast is sponsored by dbt Labs.

The last time Ramp's Ian Macomber joined the show, the episode was titled, "Ramp's $8 billion data strategy." Ramp is now valued at $44 billion, and the data team's job has completely changed. Ian Macomber returns to talk with Tristan Handy about self-serve analytics at 50x scale, routing agents through the data lake, and why consensus is the scarce resource in a post-AI world. For full show notes and to read the podcast's companion newsletter, head to https://roundup.getdbt.com. The Analytics Engineering Podcast is sponsored by dbt Labs.

nao co-founder and CEO Claire Gouze shares a practical playbook for building a context layer your agents can actually rely on. For full show notes and to read the podcast's companion newsletter, head to https://roundup.getdbt.com. The Analytics Engineering Podcast is sponsored by dbt Labs.

Jordan Tigani helped build BigQuery, then left to bet that most data isn't big. Three years on, agents are proving him right. The MotherDuck CEO joins Tristan Handy on why local-first databases fit the agent era, and what an "agent swarm for data management" looks like. For full show notes and to read the podcast's companion newsletter, head to https://roundup.getdbt.com. The Analytics Engineering Podcast is sponsored by dbt Labs.

Tristan sits down with Anders Swanson, a developer experience advocate at dbt Labs, to talk about the state of the Apache Iceberg ecosystem. They unpack the "open standards" shift, define the core building blocks (query engines, object stores, catalogs), and dig into why external catalogs have become a fourth namespace tier across platforms. Anders outlines a pragmatic, phased adoption model for Iceberg integrations, explains why metadata performance and resiliency are hard requirements, and clarifies why vended credentials exist and what they solve. For full show notes and to read 6+ years of back issues of the podcast's companion newsletter, head to https://roundup.getdbt.com. The Analytics Engineering Podcast is sponsored by dbt Labs.

Tristan talks with Russell Spitzer, a PMC member of Apache Iceberg and principal engineer at Snowflake, about the evolution of open table formats and the catalog layer. They dig into identity and access at the catalog layer and why consensus‑driven standards make interoperability possible. For full show notes and to read 6+ years of back issues of the podcast's companion newsletter, head to https://roundup.getdbt.com. The Analytics Engineering Podcast is sponsored by dbt Labs.