Archive - The Analytics Engineering Roundup

You can't scale vibes (Guy Podjarny)

The co-founder of Tessl on why skills need the same lifecycle as code and why most companies will end up owning their own harness instead of renting…

Aug 27 • Dan Poppy

Roundup: Why your sales team shouldn't query Gong directly

Tristan is joined again by Jason Ganz. This time: Stripe's $7 billion acquisition of OpenRouter, the AI bubble, new benchmarks that say data engineering…

Aug 21 • Dan Poppy

Don't hand a bazooka to an agent making a sandwich (Jeremiah Lowin)

The creator of FastMCP on why a skill file is a polite note, why enterprises pick MCP over CLIs, and why nobody is ready for a context layer yet.

Aug 13 • Dan Poppy

Roundup: a rogue agent, Kimi K3, and data teams in the AI era

We're introducing a new, recurring podcast format. Jason Ganz joins Tristan to take on stories of the day.

Aug 6 • Dan Poppy

July 2026

Data lessons from inside Meta (Shridhar Iyer)

Shridhar Iyer spent 13 years inside Meta's data organization. He joins Tristan on what big tech takes for granted, why you never delete a column at…

Jul 30 • Dan Poppy

The scarce resource is consensus (Ian Macomber)

When building data artifacts is fast and cheap, the scarce resource is company-wide consensus. Ramp's Ian Macomber returns to talk about post-AI data…

Jul 16 • Dan Poppy

The context engineering playbook (Claire Gouze)

nao co-founder and CEO Claire Gouze shares a practical playbook for building a context layer your agents can rely on.

Jul 2 • Dan Poppy

June 2026

DuckDB's agent moment (Jordan Tigani)

The database built for your laptop turns out to be one built for your agents. MotherDuck Founder and CEO Jordan Tigani explains why.

Jun 18 • Dan Poppy

A Catalog Is All You Need

Last year I asked you to give Iceberg a REST. This year, it finally got one.

Jun 14 • Anders Swanson

Hunting for Tokens. Snowflake Summit. Agent Use Cases.

Things are not quieting down for the summer, that's for sure.

Jun 7 • Tristan Handy

May 2026

I built a (very small) long running agent

What do long running agents mean for data teams?

May 31 • Jason Ganz

I built a (very small) agent swarm.

What does the term 'agent swarm' mean? Is it bullshit? Can I build one?

May 26 • Tristan Handy

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts