How to use Claude to build an Android tracking app
The author reports a working Android MVP in four days, with background processing, push notifications, scraping, charts, and a ten-level alert system.
AddedAnthropic’s Claude includes a chat assistant, Claude Code, a command-line coding agent, and Cowork for delegated desktop work with files and tools.
Maker: Anthropic
Writing, research, coding and desktop work.
The author reports a working Android MVP in four days, with background processing, push notifications, scraping, charts, and a ten-level alert system.
AddedThe author reduced the workflow from four instances to three, reported a five-file cleanup with 149 deletions and 29 additions, and said clearer ownership reduced most merge conflicts.
AddedThe author reports the Anthropic bill fell from $312 to $156 after checkpointing, cached summaries, and compensating actions were added. A simultaneous-run race remained unresolved.
AddedAn author used Claude Code over several sessions to build a Yosemite-area house-hunting dashboard from a detailed spec. The tool collects Zillow listings via RealtyAPI and offers property stages, price history and days-on-market analysis.
AddedAkbar gave Claude Code his resume, transcript and application data to run an internship search. He reports more than 228 submissions, Google Sheets tracking, resume routing and LinkedIn outreach that produced a direct HR contact.
AddedThe author used Gemini Pro for architecture and Claude Code for implementation, enforcing Vitest tests before deploying My DigitAlly to serve 200+ active users.
AddedPayMind uses specialized agents to analyze invoices, draft reminders, and interpret replies, with a dashboard approval step before sending generated emails.
AddedTwo engineers used Claude Code and other development tools to build Unpitched in a five-week co-founder trial, saving planning documents as implementation context.
AddedKelora is an experimental Rust log processor whose code and tests were generated by Claude CLI and Codex CLI, with the author supplying ideas and reviewing docs.
AddedThe author watched Claude Code fix a database pool type error and a bad migration through RunOS, redeploying until the application ran without intervention.
AddedClaude helped code Uppercut on Mac OS X Tiger, with explicit prompts excluding newer Objective-C features unavailable in Xcode 2.5.
AddedA player built a Claude Minecraft bot with chat participation, memory, custom MCP tools, Mineflayer wrappers, and support for land claims and shops.
AddedAn engineering leader gave Claude CI artifact access and pass-rate tooling, let it investigate and rerun flaky tests overnight, and reviewed its proposed fixes during the day.
AddedThe author used Claude Code to maintain recipes, retrieve USDA nutrition information, suggest weekly combinations, and produce categorized shopping lists and daily nutrient reports.
AddedTwo Claude Code instances coordinated podcast and UI work by posting status to Discord, setting timers, checking peer updates, and choosing their next actions.
AddedAn author built separate-context research, Git, and Bash sub-agents that return condensed findings instead of full files, raw diffs, and logs, reporting a 90–95% token reduction on heavy operations.
AddedAn author used Claude Code to build Goatpad without opening an IDE, while handling repository setup, sprites, uploads and DNS manually. Goats eat notes, creating a loss risk the author says helped with focus.
AddedAn author reports using Claude for a public water data site and expanding to nine more sites, with automated weekly traffic analysis and article updates. Backlink outreach remained a planned human task.
AddedClaude Code analyzed a messy application through its invariants, prioritized remediation plans and implemented backend and frontend changes. The author reported a stable result but needed a simpler explanation of the analysis.
AddedA developer compared Claude trading decisions using current briefings, prices, web search and stale briefings. The latest reported run favored current context, but the author highlighted bearish-window bias and inconclusive sample size.
AddedClaude worked overnight from a goal file defining a weighted metric, constraints, and an improvement loop; the author reported 12 commits and a score of 83.
AddedA Claude SDK agent used Playwright and a small Python TOTP implementation to configure MFA and verify an authentication change in a preview instance.
AddedClaude Code split a testing backlog into non-overlapping tasks, launched 26 subagents, and helped the author review the resulting tests over several days.
AddedThe author reports a GUI library and several working media scripts produced over a weekend, validated through demos while acknowledging likely undiscovered bugs.
Added