You wouldn't let your agent do that. Now you can. Building the plane as we fly withaileron.ai.
Joined January 2009
- Tweets 10,814
- Following 1,593
- Followers 5,464
- Likes 4,243
Photos and videos
Jun 9
> Start issue 965
That's my "loop". Don't let the timeline nonsense make you feel like you're missing anything. Here's what I do, none of it's magic, and you can ramp up to it pretty easily. 👇
1
368
Jun 9
The PR checks are the safeguards. It's where I protect for code coverage, dependencies, code review, deployments, etc.
1
84
Jun 9
Then after merge I'm pulling things down and using it. Reviewing it. Finding what I don't like. And more conversations with the agent to file issues to fix or improve or move forward.
That's it. I don't think I'm missing some big secret except there's folks doing remarkable orchestration as a layer above, and that's another world I'll write about someday once I figure it out.
85
Jun 8
Your monthly reminder.
May 26
Using AI tools ≠ Taste and judgment
122
ALR retweeted
Jun 5
Chat-first work tools are not the answer. The flaws are baked into the system, you can't undo them. It would be like asking a kangaroo to fly. It can get off the ground, and look like flight for a moment, but it comes crashing right down.
Here's why:
37signals.com/group-chat-pro…
Jun 4
I wish Slack was:
- Agent-first
- Beautiful to use
- Integrated with agents natively so your Hermes or OpenClaw lives inside it
- Huddles worked seamlessly and were fun
- Built for teams of 1-3, not just teams of 300
- Truly a second brain similar to Obsidian
- Searchable without wanting to throw your laptop
- Designed around async, not constant interruption
- Voice first for mobile
- A place where I could see who's working on what right now without asking anyone
- Smart enough to know the difference between "I need you right now" and "whenever you get to this"
- A workspace where my agent could tap someone else's agent on the shoulder and coordinate without involving either human
- Designed so the new hire on day 1 has the same context as the person who's been there 3 years
-Something that felt like walking into a room of people building, not walking into a room of people typing
- A place where decisions are first-class objects
- Able to auto generate SOPs, skills, agents etc from conversation history
- Something that rewards deep work instead of punishing it with 47 unread notifications
33
29
354
102,003
Jun 5
Aileron is about teams building damn good workflows, sharing them, improving them.
“This is a defining moment in AI adoption, and the gap between super-users and laggards is widening fast,” - @DanSchawbel
Systems built for collaboration are just better.
2
214
Jun 4
Most people do not want to wrangle AI infrastructure to be more efficient at work.
66
Jun 3
"If you're prompting Claude Code, you're using it wrong".
That's literally what this thing was built to do. My bet with Aileron is that most work can be accelerated with AI, and most people don't want to touch an agent to do it.
138
May 20
Lots of dunking today. I’m not among them.
Empathize with every customer who lost business and real dollars. At the same time:
Running infra at this scale means relying on partners, and I saw Railway and @JustJake do everything to remediate and communicate.
Google? Hard to reach, slow to respond to their customer.
Google Cloud has blocked our account, making some Railway services unavailable. We have escalated this directly with Google. The Railway Platform team has since confirmed access to Google Cloud and is working on restoring access to all workloads.
We have access to some of our Google Cloud–hosted infrastructure and are working to restore the rest of the service. We apologize for the disruption.
1
399
May 16
Another great example of innovation outpacing standards and norms.
May 16
This is the most insane shit I have ever seen. Look at all the possible skill folder installation locations
Why does IBM bob have its own skill folder?
What the hell is CodeArts Agent? Why can't they all use .agents??
1
323
May 15
Agents make mistakes every day. Here's one from today.
The great mistake we accepted was to put rules into context rather than deterministic guardrails. Rules are suggestions.
444
May 15
I want my agents to fly and --dangerously-skip-permissions.
I *think* if we capture the LLM Gateway and OS sandbox both, we can intercept everything we need for policy to let the agents off the leash.
Anyone taking this approach?
1
141
May 15
@ibuildthecloud You seem hip to this kind of nerdery lately. Would love your thoughts before I burn a lake's worth of tokens prototyping it out.
78
May 14
"Write a 1-sentence elevator pitch for how Aileron will accelerate a team's AI transformation. Send it to email@address.com"
1
107
May 12
Yes.
Yes.
Yes.
Yes.
Yes.
Yes.
Yes.
Yes.
Yes.
No no no, you did it all wrong!
- Computer Programming, 2026.
98