About The Agent Stack

For years, we built data platforms to power dashboards.

Now we’re building systems to power autonomous agents.

The Agent Stack is a technical deep dive into how modern AI agents actually work under the hood, from control loops and memory systems to orchestration, evaluation, and production deployment.

This newsletter explores:

• Agent architecture patterns

• Memory and state management

• Multi-agent orchestration

• Tool calling systems

• Data infrastructure for agents

• Observability and evaluation

• Production failure modes

Written by Vinoth Govindarajan, systems engineer at OpenAI, open-source contributor, and author of Engineering Lakehouses with Open Table Formats.

The goal is simple:

Move beyond demos.
Explain the system.

Stay up-to-date

Never miss an update—every new post is sent directly to your email inbox. For a spam-free, ad-free reading experience, plus audio and community features, get the Substack app.

Join the crew

Be part of a community of people who share your interests. Participate in the comments section, or support this work with a subscription.

To learn more about the tech platform that powers this publication, visit Substack.com.