Inside OpenAI’s Agentic Browser, Atlas (56 min)
- Release date: 2026-02-11
- Listen on Spotify: Open episode
- Episode description:
The AI labs fighting for attention during the Super Bowl call to mind another iconic Super Bowl moment: Apple’s 1984 ad for the Macintosh, which promised that the personal computer would be a source of unbound wonder, freedom, and delight.They were right, but over time, the personal computer has also become cluttered with errands.These “computer errands”—downloading a W-2 when tax season rolls around, hunting for the right coupon code before checkout, or navigating the unholy labyrinth of the Amazon Web Services dashboard just to change one permission setting—have taken over our digital lives. Atlas, OpenAI’s agentic browser, sprang from the idea that AI should handle this tedium for you.In this week’s episode of AI & I, Dan Shipper sat down with two members of the Atlas team, Ben Goodger and Darin Fisher. Goodger is Atlas’s head of engineering, and Fisher is a member of the technical staff. Both are legends of the browser world. They’ve spent decades building the modern web, working together on Netscape, Firefox, and Chrome before arriving at Atlas. From that vantage point, they told Dan how they think browsing is about to change, why building a browser is harder than it looks, and what it’s like to create a new one with AI coding tools like Codex.If you found this episode interesting, please like, subscribe, comment, and share! Want even more?Sign up for Every to unlock our ultimate guide to prompting ChatGPT here: https://every.ck.page/ultimate-guide-to-prompting-chatgpt. It’s usually only for paying subscribers, but you can get it here for free.To hear more from Dan Shipper:Subscribe to Every: https://every.to/subscribe Follow him on X: https://twitter.com/danshipper Move fast, don’t break thingsMost AI coding tools don’t know which line of code will actually break your system. Try Augment Code, which understands your entire codebase, including the repos, languages, and dependencies that actually runs your business, and use their playbook to learn more about their framework, checklists, and assessments. Ship 30% faster with 40% shorter merge times.[Playbook at https://www.augmentcode.com/]Timestamps: 00:01:57 - Introduction00:11:51 - Designing an AI browser that’s intuitive to use00:15:24 - How the web changes if agents do most of the browsing00:25:06 - Why traditional websites will not become obsolete00:29:00 - A browser that stays out of the way versus one that shows you around00:39:51 - How the team uses Codex to build Atlas00:44:47 - The craft of coding with AI tools00:52:33 - Why Goodger and Fisher care so much about browsersLinks to resources mentioned in the episode:Ben Goodger: Ben Goodger (@bengoodger) Darin Fisher: Darin Fisher (@darinwf) OpenAI’s browser, Atlas: Introducing ChatGPT Atlas
Summary
- 🚀 Agentic Browsing Revolution: Atlas integrates ChatGPT as a seamless companion for web tasks, automating settings navigation and providing page-aware advice to enrich shopping, research, and form-filling.
- ⚙️ Tedious Task Automation: Users bypass complex interfaces like AWS or Google Docs by delegating to AI agents, reducing activation energy for infrequent but frustrating operations.
- 🎯 UX Discovery Balance: Progressive features like Cursor Chat empower but challenge discovery; onboarding must introduce power without overwhelming familiar browser flows.
- 🔬 AI Accelerates Development: Codex authors most code, speeds prototyping, and aids legacy navigation, enabling small teams to build sophisticated browsers rapidly.
- 🌐 Blended Web Future: Agentic browsers complement human exploration, evolving web standards for scalable, semantic agent interactions without replacing direct user engagement.
Insights
Why does embedding ChatGPT context directly into web pages make browsing feel like having a knowledgeable companion?
Time: 5:10 – 7:18
Category: AI in Everyday LifeAnswer: Unlike separate ChatGPT tabs requiring copy-paste, Atlas provides instant page-aware responses, enabling confident shopping with best deals, brainstorming viewpoints, or querying without repetition. This enriches research and dynamic interactions across the web. (Start at 5:10)
How does an agentic browser like Atlas eliminate the frustration of navigating complex settings panels in web apps?
Time: 8:09 – 10:23
Category: AI in Everyday LifeAnswer: Users can delegate tedious tasks like managing AWS permissions or generating Google Forms to the AI agent, bypassing manual clicks and reducing activation energy for infrequent tasks. This shifts browsing from manual drudgery to seamless automation, saving time on high-stakes or repetitive actions. (Start at 8:09)
What UX challenges arise when introducing powerful AI features like Cursor Chat without overwhelming users?
Time: 12:27 – 13:30
Category: AI in Everyday LifeAnswer: Features like field-specific AI assistance are under-discovered despite hints, requiring balanced progressive disclosure during onboarding to avoid confusion while rewarding exploration. Balancing familiarity with hidden power is key to intuitive adoption. (Start at 12:27)
How might the web evolve to better support personal AI agents acting on user behalf?
Time: 15:21 – 22:11
Category: AI Governance & LawsAnswer: Beyond screen-reading, declarative HTML enables semantic understanding, but scaling to multi-tasking requires new signals distinguishing user-directed agents from crawlers, potentially shifting content creation for agent consumption. AI bootstraps compatibility without immediate changes. (Start at 15:21)
Will agentic browsers complement or replace traditional web exploration?
Time: 24:32 – 28:26
Category: AI Utopias vs. DystopiasAnswer: They act as delegates for tasks and thought partners for ambiguity but won’t eliminate user desire for direct browsing, window shopping, or personal involvement in entertainment and discovery. A blended future persists, like autonomous vs. manual driving. (Start at 24:32)
How are AI coding tools like Codex revolutionizing browser development velocity and prototyping?
Time: 38:44 – 42:02
Category: AI in Workforce DisruptionAnswer: Over 75% of new code is AI-generated, enabling rapid prototyping in minutes, querying legacy codebases like Chromium, and deciding feature viability quickly with small teams. This accelerates iteration from idea to build, focusing humans on judgment and refinement. (Start at 38:44)