Run parallel Claude sessions to build and test apps
A developer runs about 10 codebase copies with Claude sessions, planning specs first, and has Claude drive phones via adb to test UIs and debug from logs. ·
Done withClaude
- What they did
- The developer keeps about 10 copies of the codebase in a /code folder, each with its own git branch, Claude session and terminal. He spends heavy time planning and specifying each task tightly so Claude can't wander. For mobile apps, he plugs phones into the laptop over USB (emulators if needed) and Claude drives the UI through adb, reads logs and debugs.
- How it went
- The source gives no measured results, only the claim that Claude moves very fast on tasks once set up this way. It reports the limit that he can only manage as many sessions as he can mentally handle.
- Worth knowing
- Prep mattered: about a year ago they split 10K+ line files into files of 2K lines or less and had Claude add per-file summaries and comments; a strictly typed language like dotnet is also needed.
Try it yourself with Claude
I'm building [describe your app] in the repo at [path]. First write a short spec and a step-by-step plan for [feature], and wait for my approval. Once I approve, implement it, run the app on my connected Android device or emulator using adb, tap through [the key screen or flow], and read the logs to fix any crashes. Stop when the flow works end to end and give me a summary of what you changed and tested.
Want help getting this working? Join the Vibe Coding Academy ↗ Run by Alex Finn, who also runs this site.
Source: HN · Nov 2, 2026
Related use cases
Build a C compiler with a team of parallel agents
Anthropic's engineering write-up on tasking Opus 4.6 agent teams with building a C compiler.
Triage support emails and draft refund-policy replies
A consultant built a Claude agent that reads support Gmail, looks up orders, applies refund policy, drafts replies for human approval and creates triage records with optional Slack alerts.
Review AI-written code with a layered agent review process
Anthropic's Claude Code team describes how it changed its code review process so Claude can write most of Claude Code's code.
Turn tickets into merged pull requests
Pulls tasks from GitHub Issues or Linear, then runs Claude Code or Codex in isolated Kubernetes pods to carry each one through to a PR.
Build a budgeting app from a single prompt
A low-coder used Replit Agent to build a 'Budget Buddy' with category budgets, a spending dashboard and expense log in about 20 minutes, using half their monthly credits.
Run a task-manager sub-agent with atomic commits
A poster built a Claude Code sub-agent that fetches the next task, marks it complete, and enforces atomic commits with a mandatory commit id.
Get 5 like this every morning
The best things people got an AI agent to do, each with the prompt to try it.