🤖 AI Summary
Overview
This episode explores how Codex, OpenAI's agent management interface, has evolved from a tool for senior engineers into a transformative daily driver for knowledge work. Dan Shipper and Austin Tedesco discuss the shift in workflows enabled by Codex, its integration with tools like Slack and Notion, and its potential to redefine productivity through automation, agent collaboration, and strategic planning.
Notable Quotes
- If you have a great general-purpose coding agent on your computer, it’s actually really great for any kind of knowledge work.
– Dan Shipper
- When I sign on during the day, Codex is the first thing I open. It’s where I spend 80% of my time because the app itself is just so good.
– Austin Tedesco
- The thing I care about is: Do you stand by it? Have you thought about it? If I talk to you about a particular bullet point, will it be clear you’ve thought it through?
– Dan Shipper
🚀 The Evolution of Codex for Knowledge Work
- Dan Shipper explains how Codex transitioned from a tool for senior engineers to a versatile platform for knowledge work, thanks to improvements in usability, speed, and emotional intelligence.
- Codex now integrates seamlessly with desktop environments, enabling users to delegate tasks like coding, writing, and recruiting.
- The rise of agent management interfaces, such as Codex and Anthropic’s Claude Code, signals a shift toward agent-first workflows as the new operating system
for productivity.
🛠️ Setting Up Codex for Maximum Efficiency
- Austin Tedesco shares how he organized Codex with folders, keys, and custom reviewer agents tailored to his workflow.
- Codex automates tasks across Gmail, Slack, and Notion, suggesting and implementing workflows with minimal manual input.
- Specialized agents, inspired by Claire Vo’s approach, were created to handle distinct tasks like strategic alignment and data accuracy.
📊 Building a Live KPI Tracker in Notion
- Austin describes using Codex to create a dynamic KPI tracker that updates every six hours with metrics from Stripe, social platforms, and internal tools.
- While Codex automates much of the process, Austin emphasizes the importance of manually verifying critical data like MRR to ensure accuracy.
- The tracker serves as a source of truth for both humans and agents, enabling automated actions like generating SEO landing pages when metrics fall short.
🧠 Synthesizing Knowledge into Actionable Plans
- Codex excels at synthesizing meeting transcripts, Slack threads, and templates into actionable documents like go-to-market plans.
- Austin highlights how Codex saved him hours by compiling a comprehensive plan from existing materials, which was 80-90% ready for execution.
- The team normalizes sharing AI-generated documents, with the expectation that users stand behind the content and refine it collaboratively.
🎯 Codex in Recruiting and Beyond
- Dan shares a breakthrough use case: using Codex to identify potential hires by filtering LinkedIn profiles of General Assembly alumni who transitioned into AI roles.
- Codex’s ability to surface highly relevant candidates demonstrates its potential for outbound recruiting and other targeted searches.
- The team envisions a future where agents handle more complex workflows, reducing the need for traditional dashboards and manual onboarding processes.
AI-generated content may not be accurate or complete and should not be relied upon as a sole source of truth.
📋 Episode Description
In January, Dan Shipper wrote that whoever wins vibe coding wins how you work on your computer—and OpenAI had some serious catching up to do.
Three months and the release of GPT-5.5 later, Codex has more than caught up. Austin Tedesco, Every's head of growth, now spends about 80 percent of his working time inside the Codex desktop app, doing everything from drafting go-to-market plans from a stack of meeting transcripts to rebuilding the company's KPI dashboard.
On this episode of AI & I, Dan sat down with Austin to discuss why the agent management interface—a desktop app built on top of a coding agent—is becoming the new operating system for knowledge work, and why Codex has become his daily driver.
If you found this episode interesting, please like, subscribe, comment, and share!
To hear more from Dan Shipper:
Subscribe to Every: every.to/subscribe
Follow him on X: twitter.com/danshipper
Join the membership for Where You Live at joinbilt.com/dan
Timestamps for YouTube:
00:00:00 Introduction
00:00:57 How Codex went from a tool for senior engineers to a daily driver for knowledge work
00:02:42 How Claude Code proved that a great coding agent works for any knowledge work
00:07:24 Austin's switch to Codex
00:13:48 How Austin set up Codex with folders, keys, and reviewer agents
00:18:24 Using Codex to brainstorm automations across Gmail, Slack, and Notion
00:22:42 How Austin manages the human review step when Codex is drafting communications
00:28:54 Using Codex to build specialized agents inspired by product executive Claire Vo
00:31:09 Synthesizing meeting transcripts and Slack threads into a go-to-market plan
00:40:15 Building a live KPI tracker in Notion that agents can read
00:44:54 Using Codex for recruiting
Links to resources mentioned in the episode:
Austin on X: @tedescau
Dan's January essay on OpenAI's catch-up problem: every.to/chain-of-thought/openai-has-some-catching-up-to-do
Every's vibe check on GPT-5.5: every.to/vibe-check/gpt-5-5