Execution engine without an IDE: tickets from the dashboard to any repo
This is the part we’re genuinely proud of: you can now kick off a code change without opening a single IDE. You’re in the boostN dashboard, you write a ticket for Project A — your website, say — and send it off. The change happens on exactly that repository. Five seconds later you write the next ticket that fixes a bug in your web app. A few seconds after that, one for the app you’re currently working on. It all runs through our execution engine, which sends each task to the right repository.
What actually changed
- No IDE needed: you work from the boostN dashboard, not from an editor.
- Multi-repo: every ticket lands on the repository it belongs to.
- Parallel and fast: a ticket to Project A, seconds later one to Project B — both run.
- Automatic routing: the execution engine sends the work to the right repo; you don’t switch anything.
How it was before
Changing something in a project meant: open the editor, clone or switch to the right repository, build up the context — and only then start working. Every additional project began the same way. Anyone trying to get things done across three repos at once spent a good chunk of their time switching and setting up rather than on the actual task.
How it works now
1. You write a ticket — done. In the dashboard you describe what should happen and send it off. No local setup, no editor, no cloning. The ticket is the task.
2. The execution engine routes it to the right repo. You don’t have to specify how the work is technically carried out or pick the branch by hand. The system knows which project the ticket belongs to and runs the change there.
3. Multiple projects, no context switching. This is where you feel it: a ticket for the website (Project A), seconds later one for a bug in the web app, right after that one for the app itself. Three tickets, three different repositories — and not a single editor launch in between. This now works cleanly in our day-to-day.
Why it matters
The real bottleneck in development was rarely the typing. It sat in everything around it: finding the right project, getting the environment up, resetting your head from one repo to the next. That part is gone now. The question shifts from “Where am I working?” to “What should happen?”.
To be honest about it: a ticket has to be clear enough for the result to be right — the engine routes and executes, you still do the thinking. But the expensive part, the constant switching between projects and tools, is out.
What you can do now
If you work across several repos: add your projects to boostN and trigger changes by ticket instead of switching editors for each repo.
If a small fix comes up: write the ticket, send it, carry on. You don’t have to leave your current context to change something in another project.
If you want to see it first: take a non-critical repo and file a small ticket — a text change, a minor bugfix. That way you watch the routing in action before relying on it for the projects that matter.
Learn more
- boostN — the web app at a glance
- What boostN can do — features
- Documentation & guides
- Google Gemini is now available as an agent
Entdecke mehr
Saving Tokens with Claude: 6 Principles That Make Experts Twice as Fast
How I turned my CLAUDE.md from a style guide into a token budget — 6 principles for lower cost, less waiting, and more honest reporting.
GlossarAider
Aider is an open-source AI pair programmer for the command line that edits code directly in the Git repository and commits every change automatically.
LexikonHuman-in-the-Loop — Approval Gates for AI Agents
What human-in-the-loop means in agent workflows: approval gates, intervention points before critical actions, and why they are mandatory for irreversible steps.