Bookmark: How OpenAI's new ChatGPT agent can do the research for you - access it here

How OpenAI’s new ChatGPT agent can do the research for you - access it here
OpenAI’s introduction of the Deep Research agent in ChatGPT marks a significant advancement in AI capabilities, offering users a tool that can autonomously conduct comprehensive research. This feature, powered by an optimized version of OpenAI’s o3 model, excels in multi-step research processes by gathering and synthesizing information from the web into detailed reports in a matter of minutes, a task conventionally demanding hours from a human researcher. Deep Research is particularly beneficial for professions that require intensive knowledge work, like finance and engineering, as it can efficiently locate niche information through myriad online resources. However, OpenAI cautions users to verify the generated information, as the agent may, albeit at a lower rate than previous models, hallucinate facts or make incorrect inferences. Initially available to ChatGPT Pro users, Deep Research will be extended to other subscription tiers, reflecting OpenAI’s phased rollout strategy. The tool’s performance, notably surpassing other AI models in benchmark tests, demonstrates its potential to redefine digital research capabilities. Despite its high utility, OpenAI highlights the necessity of human oversight, especially in discerning authoritative information.
Featured writing
Why customer tools are organized wrong
This article reveals a fundamental flaw in how customer support tools are designed—organizing by interaction type instead of by customer—and explains why this fragmentation wastes time and obscures the full picture you need to help users effectively.
Infrastructure shapes thought
The tools you build determine what kinds of thinking become possible. On infrastructure, friction, and building deliberately for thought rather than just throughput.
Server-Side Dashboard Architecture: Why Moving Data Fetching Off the Browser Changes Everything
How choosing server-side rendering solved security, CORS, and credential management problems I didn't know I had.
Books
The Work of Being (in progress)
A book on AI, judgment, and staying human at work.
The Practice of Work (in progress)
Practical essays on how work actually gets done.
Recent writing
We always panic about new tools (and we're always wrong)
Every time a new tool emerges for making or manipulating symbols, we panic. The pattern is so consistent it's almost embarrassing. Here's what happened each time.
Dev reflection - February 03, 2026
I've been thinking about constraints today. Not the kind that block you—the kind that clarify. There's a difference, and most people miss it.
When execution becomes cheap, ideas become expensive
This article reveals a fundamental shift in how organizations operate: as AI makes execution nearly instantaneous, the bottleneck has moved from implementation to decision-making. Understanding this transition is critical for anyone leading teams or making strategic choices in an AI-enabled world.
Notes and related thinking
Bookmark: OpenAI's ‘Deep Research’ Can Actually Make Professional Reports With Citations
Unlock the power of OpenAI's Deep Research to generate professional reports with citations, saving you hours on complex research tasks.
Bookmark: Goodbye digital transformation, hello AI-first business transformation
Embrace AI-first transformation to innovate and streamline business operations, breaking down silos and enhancing decision-making for exponential growth.
Bookmark: Rumors are swirling that OpenAI is on the brink of AGI and ASI
OpenAI may be nearing breakthroughs in AGI and ASI, with hints of self-improving models and industry anticipation for significant updates.