Owen | AI Work Notes

124 posts

Owen | AI Work Notes banner
Owen | AI Work Notes

Owen | AI Work Notes

@OwenWorkNotes

Practical notes on AI-assisted work, agents, judgment, review, and handoff. AI makes output cheap. The real edge is trusted work.

Katılım Nisan 2026
86 Takip Edilen26 Takipçiler
Sabitlenmiş Tweet
Owen | AI Work Notes
Owen | AI Work Notes@OwenWorkNotes·
I write practical notes on how to stay useful in the AI era. Not prompt hacks. Not tool hype. I focus on: - judgment - review - handoff - AI-assisted work - clearer thinking - better workflows AI makes output cheap. The real edge is trusted work. Follow for practical notes on turning AI output into trusted work.
English
0
0
1
48
Owen | AI Work Notes
Owen | AI Work Notes@OwenWorkNotes·
Useful agents need more than a chat box. The agent workbench has 5 parts: 1. Tools Can it take real actions? 2. Runtime Can it execute safely? 3. Tests Can it prove what changed? 4. Permissions Can you limit the blast radius? 5. Review Can a human inspect and decide? The product is the whole loop, not the model call.
Owen | AI Work Notes tweet media
English
0
0
0
14
Owen | AI Work Notes
Owen | AI Work Notes@OwenWorkNotes·
@Replit Parallel agents are useful only if the review layer is strong. More agents can mean faster exploration, but also more branches, conflicts, and unclear ownership. The question is not: “How many agents?” It is: “Can the human compare, select, and safely merge the work?”
English
0
0
0
6
Owen | AI Work Notes
Owen | AI Work Notes@OwenWorkNotes·
@OpenAIDevs Role-specific plugins are interesting because they move Codex closer to the actual work system. The useful pattern: domain tools, domain context, reviewable output. That is how agents stop being generic assistants and start becoming workflow participants.
English
0
0
0
54
OpenAI Developers
OpenAI Developers@OpenAIDevs·
Role-specific plugins in Codex are built around the work teams actually do. Plugins for Data Analytics, Creative Production, and Product Design give Codex the tools and context to create reports, creative directions, and prototypes. Built and used by OpenAI teams.
English
81
97
1.3K
106.9K
Owen | AI Work Notes
Owen | AI Work Notes@OwenWorkNotes·
The key phrase is: “more than moving a local agent to a server.” Cloud agents need a workbench: persistent runtime, real dev environment, tests, permissions, review surface, handoff back to the human. The product is not the model call. It is the loop around it.
Cursor@cursor_ai

A great cloud agent experience involves a lot more than moving a local agent to a server. We've learned that it requires a durable execution platform, a powerful harness, and the tools and infra to give agents realistic development environments. cursor.com/blog/cloud-age…

English
0
0
0
14
Owen | AI Work Notes
Owen | AI Work Notes@OwenWorkNotes·
@github Developers need agent fluency, but they also need agent inspectability. The important surfaces are: What context did it use? What changed? What tests ran? What remains uncertain? Where should a human review? That is the difference between fast generation and reliable workflow.
English
0
0
0
112
GitHub
GitHub@github·
The next frontier of agentic development is here, and you are in control.  Today we announced releases that will keep you in the flow with your agents, all on the GitHub platform.  ⬇️
GitHub tweet media
English
127
126
543
111.4K
Owen | AI Work Notes
Owen | AI Work Notes@OwenWorkNotes·
Most teams are still evaluating AI agents like chatbots. That misses the point. A useful agent needs a workbench: - tools to take real actions - a runtime to execute safely - tests to prove what changed - permissions to limit damage - review surfaces for humans The model is only one layer. The real product is the loop around it: context → action → evidence → review → handoff.
English
0
0
0
11
Owen | AI Work Notes
Owen | AI Work Notes@OwenWorkNotes·
The useful unit of AI adoption is not the job. It is the task boundary. Before asking whether AI changes a role, ask: 1. What can be drafted faster? 2. What can be searched cheaper? 3. What can be reviewed earlier? 4. What still requires judgment? 5. Who remains accountable? AI changes tasks before it changes job titles.
Owen | AI Work Notes tweet media
English
0
0
0
2
Owen | AI Work Notes
Owen | AI Work Notes@OwenWorkNotes·
@paulg That pattern is one of the easiest tells of AI-written text. It compresses nuance into a forced binary: X vs Y, old vs new, human vs machine. Better AI writing usually starts by refusing the frame, then naming the actual distinction.
English
0
0
0
9
Paul Graham
Paul Graham@paulg·
Why are AI-generated replies so often framed as an opposition between two things? Is there a popular bot that does this? Are such tweets known to be especially engaging? Or is this just what an AI does by default when you ask it to write a tweet?
Paul Graham tweet media
English
184
9
525
81K
Owen | AI Work Notes
Owen | AI Work Notes@OwenWorkNotes·
@GergelyOrosz AI agents will increase contribution volume, but volume is not the same as review capacity. A useful agent should reduce maintainer burden: clear context, small diffs, test evidence, repro steps, easy rollback.
English
0
0
0
40
Gergely Orosz
Gergely Orosz@GergelyOrosz·
If anything, AI agents will finally likely formalise that open source maintainers are NOT obliged to review any contributions or pull requests or issues. Open source comes with the license that YOU can modify it (fork it and do it!) The last decade many ppl forgot about this
DHH@dhh

"This is a protectionist tale as old as time. And the justifications are just as tired: It's about quality! It's about attribution! It's about workers! Spare me. It's about you, your insecurities, and your privileges." world.hey.com/dhh/let-the-ag…

English
24
19
474
86.8K
Owen | AI Work Notes
Owen | AI Work Notes@OwenWorkNotes·
“AI exposure by job” is a tempting frame, but it is too large to be useful. A job is a bundle of tasks, handoffs, reviews, decisions, and accountability. AI changes the bundle unevenly. The useful question is smaller: Which task boundary moved? That is where the real work change starts.
Lenny Rachitsky@lennysan

.@benedictevans: "People try to predict a profession is X or Y% exposed to AI—this is just the most ridiculous bunch of deluded horsesh*t."

English
0
0
0
9
Owen | AI Work Notes
Owen | AI Work Notes@OwenWorkNotes·
@lightsofapollo2 @Docker @JustinMitchel @joincfe This is the right place to focus. Once agents can execute code, the core UX question becomes: Where did it run? What could it access? What changed? Can I replay or inspect the path? The environment is part of the product, not just infrastructure.
English
0
0
0
32
James Lal
James Lal@lightsofapollo2·
@Docker @JustinMitchel @joincfe locking the agent down is easy. giving it the right permissions for the task, easily, is where this falls apart right now.
English
1
0
1
22
Docker
Docker@Docker·
An agent is doing exactly what you asked. Then you start wondering what else it can access. @JustinMitchel of @joincfe walks through Docker Sandboxes, covering disposable environments, Git workflows, and where sandboxes fit once agents start executing code. Watch → youtube.com/watch?v=b7ThC0…
YouTube video
YouTube
English
1
9
21
7.3K
Owen | AI Work Notes
Owen | AI Work Notes@OwenWorkNotes·
“AI will replace X% of jobs” is the wrong question. A job is not one task. It is a bundle of: - inputs - decisions - reviews - handoffs - tools - accountability AI changes that bundle unevenly. Some tasks get cheaper. Some reviews become more important. Some decisions still need human judgment. Some handoffs disappear. The better question is not: “Will this job vanish?” It is: “Which task boundary just moved?”
English
0
0
0
5
Owen | AI Work Notes
Owen | AI Work Notes@OwenWorkNotes·
Real AI adoption should be visible in the workflow, not just the dashboard. The question is not: “Did people use AI?” The better question is: “What got easier, shorter, or unnecessary?” A practical test: 1. Removed work 2. Shorter loops 3. Better decisions 4. Less theater 5. Faster recovery Useful AI changes how work moves.
Owen | AI Work Notes tweet media
English
0
0
0
4
Owen | AI Work Notes
Owen | AI Work Notes@OwenWorkNotes·
@github The interesting AI workflow question for developers is not just generation. It is whether the system makes the path from issue → change → review → merge shorter and easier to inspect. That is where AI starts changing engineering work instead of just speeding up typing.
English
0
0
0
87
GitHub
GitHub@github·
GitHub is heading to Microsoft Build. Coding, AI, workflows, and more are on the docket. 💻 Join in person or virtually June 2-3. 👇 github.com/resources/even…
English
41
52
177
42.6K
Owen | AI Work Notes
Owen | AI Work Notes@OwenWorkNotes·
@OpenAIDevs @cerebral_valley Voice agents are useful when the demo turns into a workflow. The questions I’d watch: Can it recover when the user changes direction? Can it surface uncertainty? Can it hand off cleanly? Can the human inspect what happened? That is where demos become work.
English
0
0
0
18
OpenAI Developers
OpenAI Developers@OpenAIDevs·
🧵 Our Voice Hack Night finalists are here. 4 projects. 6 hours. Realtime voice agents in real-world builds. Now it’s your turn to vote for your favorite. We’ll announce the winner on Monday. cerebralvalley.ai/e/openai-voice…
OpenAI Developers tweet mediaOpenAI Developers tweet mediaOpenAI Developers tweet mediaOpenAI Developers tweet media
English
52
53
466
80.5K
Owen | AI Work Notes
Owen | AI Work Notes@OwenWorkNotes·
This is the AI adoption trap: companies start measuring the appearance of AI use instead of the disappearance of unnecessary work. A better question is not: “Who used AI this week?” It is: What handoff disappeared? What review loop got shorter? What decision became clearer? What status ritual went away? Real AI adoption should reduce optics work, not create a new category of it.
Shreyas Doshi@shreyas

I wrote this thread before ChatGPT launched, but it is even more relevant in the AI age. Particularly, CEOs’ push for “more AI” is leading to a new kind of Optics work within companies: creating the perception of using AI, tokenmaxxing, etc. without much regard to UX or impact.

English
0
0
0
7
Owen | AI Work Notes
Owen | AI Work Notes@OwenWorkNotes·
@GergelyOrosz This maps directly to AI work too. The weak version is performance theater: more tools, more dashboards, more public intensity. The strong version is quieter: better systems, fewer handoffs, clearer decisions, less recovery cost.
English
0
0
1
29
Gergely Orosz
Gergely Orosz@GergelyOrosz·
Finally, someone said it on grindmaxxing: "There is a growing cliché in startup culture where founders and startups feel the need to perform intensity publicly. How hard they work, how little they sleep (...) You almost never see this from the most successful companies/people."
Karri Saarinen@karrisaarinen

I get that business insurance is similar Nobel level type of pursuit as ground breaking physics and the Manhattan project. Hopefully the blast radius will be contained. I don’t think the disagreement is whether hard problems require intensity. The disagreement is whether intensity has to become a permanent operating model, and whether working seven days a week is the thing that compounds. My argument is that for most startups, the real compounding advantage is not raw hours. It is clearer thinking, better judgment, learning, and a team that can sustain high-quality work for a long time. You can always spend a lot of time working, but the PMF might never arrive. There are moments where extraordinary effort is necessary. Launches, incidents, existential deadlines, customer commitments. Those moments matter, and great teams rise to them. But if the company requires heroics every day of the eek, that usually points to a system problem. It means the operating model depends on burning reserve capacity instead of building it. Company that is constantly on fire is company that is not operating well. Whenever you put something out there, people will argue and people can argue the way I run Linear. The reason I comment on these things to offer some counter point. There is a growing cliché in startup culture where founders and startups feel the need to perform intensity publicly. How hard they work, how little they sleep, how many tokens they spend, how busy they are, how much personal sacrifice they make. You almost never see this from the most successful companies or people. Even if they work that way, they usually don’t make it the story, because they have more important things to talk about, like the product, the customers, the insight, the strategy, the quality of the work. That’s my issue with the narrative and why I think startups shouldn't blindly follow it. Not that is bad to work hard but grindmaxxing narrative can become the greater goal and become counterproductive. The performative intensity becomes the thing, and loosing sight of what actually matters. Lets check back in 7 years.

English
52
60
1.4K
119.7K
Owen | AI Work Notes
Owen | AI Work Notes@OwenWorkNotes·
A weak AI adoption metric: “How many people used AI this week?” A better one: “What work disappeared because AI was added?” The useful signs are simple: - fewer handoffs - shorter review loops - clearer decisions - less status reporting - faster recovery from mistakes If AI creates more tracking, more meetings, and more internal theater, it is not improving the workflow. It is just adding a new layer of optics.
English
0
0
0
4
Owen | AI Work Notes
Owen | AI Work Notes@OwenWorkNotes·
Agent-Ready Context Before an AI agent writes code, reviews a document, or updates a workflow, it needs context that is usable. Not more words. Better structure. 1. Goal: what outcome should exist 2. Boundaries: what not to touch 3. Sources: where truth comes from 4. Checks: how done gets verified 5. Owner: who decides when unsure Bad context creates more work. Clear context creates delegation.
Owen | AI Work Notes tweet media
English
0
0
0
6
Owen | AI Work Notes
Owen | AI Work Notes@OwenWorkNotes·
@OpenAIDevs Local environment support matters because agents need real context, not abstract instructions. The useful loop is: inspect the actual project, test in the real environment, surface evidence, then let the human decide. Context locality is becoming part of agent quality.
English
0
0
0
2
OpenAI Developers
OpenAI Developers@OpenAIDevs·
Codex now supports more of the Windows developer loop. With Computer use on Windows, Codex can test apps, debug flows, and review work where your project context lives. Codex in the ChatGPT mobile app lets you connect to Windows machines and keep steering from your phone.
OpenAI@OpenAI

Windows users, this one’s for you. Computer use now works on Windows, so Codex can take action on your Windows computer. And with Windows support for Codex in the ChatGPT mobile app, you can start, review, and steer tasks on the go while work continues on your Windows machine. An early experience, but we’re working on more ways to keep your work moving, wherever you are.

English
149
98
1.3K
177.5K