Subvolts take Notion builds AI agents that code and integrate themselves, shifting work from humans to agent management. Mar 12, 2026
For you
Developers
Learn how Notion is enabling AI agents to build integrations and code, offering new possibilities for developer tools.
Business
Understand how managing AI agent swarms could redefine productivity and team workflows in the near future.
Hype note
3/5Notable

This interview with a co-founder of a major productivity platform provides a firsthand look at advanced agent development.

From Coder to Manager: Navigating the Shift to Agentic Engineering with Notion Co-Founder Simon Last

29 min Interview Hosts: Sarah Guo, Elad Gil
0:0029:02

Audio streams from Conviction. Your place is remembered on this device.

From Subvolts

Summary and analysis by Subvolts editorial, AI-assisted.

Summary

In this No Priors episode, Notion Co-Founder Simon Last discusses the company's evolution toward building AI agents capable of autonomous integration and code generation. Last details the technical challenges of indexing diverse data and the internal shift to using coding agents for Notion's development. He highlights a transition in productivity where humans manage agent swarms instead of performing tasks themselves.

Explained simply

Notion is building smart computer helpers, called agents, that can not only use tools but also write their own code and connect to other software. This means people will soon manage teams of these agents to get work done, rather than doing the work themselves.

Why listen

This episode offers insight into how a major productivity tool is fundamentally rethinking its architecture to support advanced AI agents. Listeners will learn about the technical hurdles in creating agents that can build and code, and how this impacts team dynamics and product development. It's for engineers and product leaders interested in the practical application of agentic AI beyond simple tool use, mirroring current trends in frontier AI labs focusing on agent capabilities.

On the mic
  • HostSarah Guo
  • HostElad Gil
  • GuestSimon LastCo-Founder, Notion
About
Key facts
  • Guest: Simon Last, Co-Founder of Notion
  • Show: No Priors
  • Length: 29 minutes
  • Notion AI Capability: Agents can autonomously build integrations and write code.
  • Productivity Shift: From humans doing work to humans managing agent swarms.
  • Development Practice: Internal shift toward using coding agents to build Notion.
Show notes from Conviction

Notion isn’t designing AI agents that just use tools. Their agents can autonomously build their own integrations, as well as write the code needed to finish a task. Sarah Guo sits down with Notion Co-Founder Simon Last to explore Notion’s rapid evolution from a simple writing assistant to a sophisticated platform for custom AI agents. Simon discusses the technical hurdles of indexing disparate data from sources like Slack and Google Drive, as well as the internal shift toward using coding agents to build Notion itself. Plus, Simon elaborates on what he sees as a fundamental transition in productivity: moving from a tool where humans do the work, to one where humans manage a swarm of agents.

Sign up for new podcasts every week. Email feedback to show@no-priors.com

Follow us on Twitter: @NoPriorsPod | @Saranormous | @EladGil | @simonlast | @NotionHQ

Chapters:

00:00 – Cold Open

00:05 – Simon Last Introduction

00:26 – Genesis of Notion AI

04:10 – Challenge of Semantic Indexing and Retrieval

07:16 – The Six-Month Rewrite Cycle

08:12 – Notion’s Coding Agent Era

09:44 – Impact on Team Dynamics

12:49 – Launching Custom Agents

15:39 – Notion as the ‘Switzerland’ for Models

17:33 – Designing APIs for Agent Customers

20:09 – Simon’s Personal Agentic Workflows

24:48 – Notion: Tool for Work is Now A Tool for Agents

27:28 – How Building Has Changed for Simon

29:00 – Conclusion


Jargon decoded
Agentic Engineering
Simon Last
Building AI systems that can act and make decisions on their own to complete tasks.
Semantic Indexing
Simon Last
Organizing information based on its meaning, not just keywords, to help AI understand and retrieve it better.
Published
Show
No Priors · Conviction
Length
29 min
Products
Notion AI
Summary by
Subvolts, using an AI model (how we work). Spotted a mistake? Tell us.

Questions people ask

What is Notion's approach to AI agents?
Notion is developing AI agents that can autonomously build their own integrations and write code to complete tasks, moving beyond simple tool usage.
How is Notion changing the nature of productivity?
Notion is shifting from being a tool where humans do the work to a platform where humans manage a swarm of AI agents.

Page generated Oct 19, 2026. Summaries are Subvolts' own; the audio, artwork and notes belong to Conviction.