Have an agent test your feature on a real Android phone and in browsers at once
Some bugs only show up on a real phone even when tests pass, so a developer built duet: an AI agent tests a feature on a real Android phone and in browsers at the same time while you watch.
Source
@AdiSinghWork on X · 2026-10-19
Written in our own words. Credit to the original author. Link checked 2026-10-19.
What they did
Some bugs only show up on a real phone even when tests pass, so a developer built duet: an AI agent tests a feature on a real Android phone and in browsers at the same time while you watch.
Result (as claimed)
Open source.
Tools they used
Cost: Pricing depends on the tools you pick; check each official pricing page.
Set it up
Pick a contained repo or task
Start on a branch or side project where mistakes are cheap.
Install and configure
Set up Claude, Android. Read what it can run on your machine and limit permissions where possible.
Run it on a real task
Give it a well-scoped issue and let it work. Review the diff like any pull request.
Add guardrails
Keep tests and CI in the loop, and never let an agent push to main or touch production secrets unattended.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: Have an agent test your feature on a real Android phone and in browsers at once What the original author did: Some bugs only show up on a real phone even when tests pass, so a developer built duet: an AI agent tests a feature on a real Android phone and in browsers at the same time while you watch. Reported result (as claimed by the author): Open source. Source: https://x.com/AdiSinghWork/status/2112137865555853619 Tools they used: Claude, Android Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: Have an agent test your feature on a real Android phone and in browsers at once What the original author did: Some bugs only show up on a real phone even when tests pass, so a developer built duet: an AI agent tests a feature on a real Android phone and in browsers at the same time while you watch. Reported result (as claimed by the author): Open source. Source: https://x.com/AdiSinghWork/status/2112137865555853619 Tools they used: Claude, Android Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: Have an agent test your feature on a real Android phone and in browsers at once What the original author did: Some bugs only show up on a real phone even when tests pass, so a developer built duet: an AI agent tests a feature on a real Android phone and in browsers at the same time while you watch. Reported result (as claimed by the author): Open source. Source: https://x.com/AdiSinghWork/status/2112137865555853619 Tools they used: Claude, Android Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
The Daily 5
Get five new use cases tomorrow morning
Free. Real sources. Unsubscribe any time.
Guides for this use case
Related use cases
Let Claude, Codex or Antigravity drive a real Android phone
NexusAndroid is one MCP server that lets Claude, Codex and Antigravity see and drive a real Android phone over plain ADB, with no root and no app on the phone.
Manage your domain's DNS records from Claude or Codex
Tired of clicking through the LWS panel, the author built lws-mcp, an open-source MCP server so you can say "Add Stripe's DNS records" in Claude, Codex or Cursor and have it done and verified.
Have Grok Bot review while Claude codes through GitHub issues
Grok Bot runs a review team for code, security and design while Claude executes the work and checks in, all through GitHub issues.
Let Claude design schematics and PCBs in KiCad
Konnect is a KiCad 10 plugin that lets Claude and other assistants design schematics and PCBs over MCP: 228 tools for schematic capture, layout, routing, ERC/DRC checks, JLCPCB part search and manufacturing exports, with skills that teach Claude KiCad conventions.