Agents In UseBuilding, testing, debugging and maintaining software or infrastructure, with code review and checks before changes reach users.
424 use casesShowing 49–72
Preparing search…
news.ycombinator.comThe author watched Claude Code fix a database pool type error and a bad migration through RunOS, redeploying until the application ran without intervention.
Added
Claudevia Claude Codenews.ycombinator.comClaude helped code Uppercut on Mac OS X Tiger, with explicit prompts excluding newer Objective-C features unavailable in Xcode 2.5.
AddedClaudenews.ycombinator.comA developer used Codex and Claude Sonnet 4 for nearly all of a SCUMM-like engine, with intermittent direction, manual design fixes, and a major human refactor.
Added
Codexnews.ycombinator.comAn Orca experiment compared Codex and Pi teams building chess coaches. Codex finished faster, while Pi’s engine won 18 of 20 games and drew two.
AddedCodexnews.ycombinator.comAn 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.
AddedClaudevia Claude Codenews.ycombinator.comTwo Claude Code instances coordinated podcast and UI work by posting status to Discord, setting timers, checking peer updates, and choosing their next actions.
AddedClaudevia Claude Codenews.ycombinator.comAn 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.
AddedClaudenews.ycombinator.comClaude 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.
AddedClaudevia Claude Codenews.ycombinator.comThe InputRight founder used an architecture LLM, an engineer LLM and Gemini CLI to build an open-source voice intake MVP. Users verify transcribed data in a form by confirming or editing it.
Added
Geminivia Gemini CLInews.ycombinator.comClaude 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.
AddedClaudenews.ycombinator.comClaude Code split a testing backlog into non-overlapping tasks, launched 26 subagents, and helped the author review the resulting tests over several days.
AddedClaudevia Claude Codenews.ycombinator.comThe author reports a GUI library and several working media scripts produced over a weekend, validated through demos while acknowledging likely undiscovered bugs.
AddedClaudenews.ycombinator.comThe author reports numerous runtime additions, expanded tests, parallel execution under two seconds, and performance improvements while reviewing every line.
AddedClaudenews.ycombinator.comThe author reports that Claude resolved output differences between the C and C++ versions, including restoring original behavior where apparent fixes broke byte equivalence.
AddedClaudenews.ycombinator.comThe author reports a two-month rewrite with fewer bugs, strong performance and easier feature development, while describing difficult reviews and substantial overtime.
Added Fablenews.ycombinator.comThe author reports that test_failure_53 passed after Deebo investigated GROUPTOP-related failure hypotheses; the fix remained under review.
Added Deebonews.ycombinator.comThe author reports several recent fixes passed tests and compiled on the first change set, with additional documentation, test, and configuration edits.
Added Qoder
x.comThe author bought an old Dell Wyse on Grok Bot's advice, installed Ubuntu Server, and granted SSH access. The bot then set up Tailscale and installed a repository they had been working on.
Added
Grok Botnews.ycombinator.comThe author reports 40,000 generated Rust lines and estimates 90% progress after two weeks of nightly iteration, while explicitly expecting additional fixes before the result works.
Added
GitHub Copilotvia GitHub Copilot Agent mode
theregister.comThe article reports a completed Rust runtime rewrite across over 135 releases, with workload-specific performance and memory improvements and a few dozen resulting regressions.
AddedGitHub Copilotvia GitHub Copilotnews.ycombinator.comThe author estimates about 25% of issue-to-Copilot PRs are mergeable as-is and about 50% after comments, while reporting setup compliance and manual verification limitations.
AddedGitHub Copilotvia GitHub Copilotnews.ycombinator.comThe author and a coworker report fixing over 200 failing integration tests for parity with the old code in one week, followed by another code review before launch.
AddedClaudenews.ycombinator.comThe author reports rebuilding the app, adding mobile clients with feature parity, and reducing monthly costs from about $20 to $0. They also describe remaining code quality issues.
AddedClaudevia Claude Codenews.ycombinator.comThe author reports a core systems-language prototype in two weeks, followed by context and supervision problems that led them back to manual coding.
AddedClaudevia Claude Code