So far in this series, the agent generated the whole solution in a single call: you gave it the spec and the tests, and the model returned the entire function. That works when the whole task fits in a prompt. But in a real repository you don't know in advance which files you'll need, and you can't f
Hi, im working at a restaurant as a man, and recently they needed an updated website. I have the website, but I have <meta name="developer" content="First Last"> (not actually First Last)in the head to show I made it for the future, but I am a trans woman and go by a different name. If i use m
An agent loop is the cycle in which a language model decides an action, that action runs, and the result feeds back in as context for the next decision, until a stopping condition is met. That repetition—decide, act, observe, repeat—is what separates an agent from a chat. A chat answers each message
I shipped a bug in a script I sell. I had also reported that script as
"verified across four scenarios."
I had verified it. In a way that verified nothing.
What was broken
The script cleans up git worktree directories once their branch is merged.
Part of the decision was detecting squash
“Runs in your browser” is easy to put on a landing page. It is harder to make it a property of the whole OCR pipeline.
An OCR page can have a static interface and still send the selected file to an API. It can keep the image local but put the extracted text into error reporting. It can avoid both a
A voice agent that books appointments is a system where someone talks, a model understands what they are asking for, calls real tools, and hangs up with an appointment on a calendar. I built one in a lab repo: ElevenLabs Agents handles the voice—transcription, turn-taking, synthesis—Cal.com handles
What do you do when Claude Code proposes one solution, Codex a different one, and Gemini a third? The usual move is to pick an agent up front and take whatever it produces. Orca changes that dynamic: it runs all three at once, each isolated in its own git worktree, and lets you compare the results a
I built OBSCURA OS, a workspace suite (docs, sheets, slides, notes, file storage, forms, calendar) that runs entirely client side in the browser. No backend database for user content, no accounts, no server round trips for your data. State lives in memory during the session and users export their ow
Why can't we get an agent scheduler that supports all of the following:- git compatible- agent agnostic- 100% open source- os and system-agnostic- multi-runner support- support mcp/ui/http- unlimited routines/cronsSo I built one, moadim.io is a local Rust daemon you install in the target machine, gi