34 stories
Startups that have had explosive AI-driven revenue growth might be in trouble. This is a consequence of the exact same open-weight model and AI sovereignty dynamics that are driving hype and discussion across twitter right now.
Even though we are living in 2026, it feels like folks have forgotten the lessons of 2006: software belongs in the cloud, not on individuals’ desktops.
I'll describe how to build a code review agent, and how to have the quality of reviews it produces automatically improve over time as part of a cloud software factory.
Software development is shifting from interactive coding agents to cloud software factories — systems that automate major parts of the SDLC while improving security, compliance, and measurable ROI.
This is my second post in a series on how to build out a fully automated cloud software factory. In this post, I’ll show how you can add spec-driven development for issues that are too complex or ambiguous to one-shot. The goal of these posts is to build a fully working...
This post is the first in a series I’m doing on how to set up your own cloud software factory using skills and loops. It’s easier than it sounds to get something simple and effective running so you can start to automate significant parts of your team’s development flow.
This post shows how to create a loop with automated feedback that an agent can run to optimize its own Skills. It uses an automated grader with computer use to assess how well a Skill is performing, and then iteratively improves the Skill.
While we’re waiting for someone to re-invent Github I put together a useful skill that can help folks better understand agent (or human) generated PRs.
This is the memo I shared with the Warp team about what building Warp needs to look like. We will focus less on interactive coding and more own automating software factories, and work with other companies to help them do the same.
There’s been a lot of chatter about using “loops” lately to drive agents, and I think this has been accompanied by a bit of “what actually is a loop”?
Rectangle Health used Oz to build a self-improving AI teammate that takes issues from triage through merged PR. The teammate, named Rex, currently ships 35K+ lines of code per week and has written over 50% of it's own code.
Use Skills to guide agents through product specs, technical specs, implementation, and validation so spec-driven development is repeatable and reviewable.
Our marketing site sees over 10 million visitors a year. This past week, we launched a brand-new version — rebuilt from scratch so agents can work on it as fluidly as humans do.
Today we’re releasing one of the most requested updates from the Warp community: more control over inference.
With Oz, engineering teams can now integrate, orchestrate, control, and improve any cloud agent at scale including Claude Code, Codex, Warp Agent, and whatever comes next.
For agents doing judgement-heavy work, the starting prompt is only the beginning. The best agents learn what good looks like from the team and improve themselves over time.
Showing 34 of 34 stories
You're all caught up.
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts
