The agent platform where your team builds the future. Coding + knowledge work agents. Multiplayer, any model, own your agent’s memory. Free during early access.
Austin, TX
Joined May 2025
- Tweets197
- Following347
- Followers122
- Likes1.2K
LatchLoop retweeted
If you are excited to try OpenAI Dots right now, including the multiplayer team collaboration in a platform that works with any model and provider, LatchLoop is available to everyone now.
My team has been working this way since Feb 2025.
Free to start.
latchloop.com
LatchLoop retweeted
Expectation: the age of the IDE is over
Reality: we’re going to need a bigger IDE
(imo).
It just looks very different because humans now move upwards and program at a higher level - the basic unit of interest is not one file but one agent. It’s still programming.
LatchLoop retweeted
What people don't realize is how wild the coding agent landscape is about to become.
You might think, "This is impressive, but Ramp is valued at $32 billion, so it makes sense they could build this."
What about the small bootstrapped team?
Here's a screenshot of LatchLoop. The coding agent I built for my team to ship faster. It runs on web, mobile web, and desktop, and it isn't a UI over Claude Code, OpenCode, Codex, etc. It is a custom-built harness that allows my team to ship faster.
My individual usage is close to a billion tokens per month. I expect that number will be much higher by the end of 2026.
The craft of engineering is rapidly changing. At @tryramp, we built our own background coding agent to accelerate faster.
We call it Inspect. It wrote 30% of merged frontend + backend PRs in the past week.
It’s powered by @opencode, @modal and @CloudflareDev. It runs fully in the cloud, and starts in seconds, letting every builder work at the speed of thought, no setup required.
Today, we’re open sourcing the full blueprint so anybody can build their own Inspect. Just give our spec to your current coding agent, and let it build your new favourite.
LatchLoop retweeted
Here's a real-world example of how I'm using agents to build my products. (Before the GPT-5 launch)
We'll soon see how different this will be with GPT-5.
LatchLoop retweeted
AI agents "overhearing" about a bug is now enough for them to fix it.
This is a real-world example of how I used LatchLoop to fix a bug in a production app with 500k lines of code while in a meeting.
LatchLoop retweeted
I got tired of waiting for a coding agent that fit my workflow so I built one
Since it seems like everyone is announcing code agents this week, here we go:
- Work on your phone, computer, or trigger from Linear/etc
- Control agents with your keyboard like playing StarCraft
- Spawn as many agents as you want to get PRs created for you
- Copy prompts with automatic code context to send anywhere
Build as fast as you can think.