Agents In Use1125 use casesShowing 145–168
Preparing search…
news.ycombinator.comThe GPT Investor generated stock recommendations with web-searching agents, executed 19 real-money experiments, and reported returns against SPY.
Added The GPT Investor using ChatGPT, Godmode and BabyAGI UInews.ycombinator.comClaude helped code Uppercut on Mac OS X Tiger, with explicit prompts excluding newer Objective-C features unavailable in Xcode 2.5.
Added
Claudenews.ycombinator.comA player built a Claude Minecraft bot with chat participation, memory, custom MCP tools, Mineflayer wrappers, and support for land claims and shops.
AddedClaudevia Agent SDKnews.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 OpenSeed agent audited its host platform, received rebuttals to four incorrect findings, and rewrote persistent instructions and an audit checklist.
Added OpenSeed autonomous agentnews.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.comThe author used Claude Code to maintain recipes, retrieve USDA nutrition information, suggest weekly combinations, and produce categorized shopping lists and daily nutrient reports.
AddedClaudevia Claude Codenews.ycombinator.comSimplAI reports agents handling mortgage documents, income analysis, verification, underwriting preparation, and compliance checks, with production processing falling from around 18 days to three to five.
Added SimplAInews.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.comA hobbyist used Codex to diagnose incompatible HDMI-CEC controller firmware, rewrite and test it, and upload it over the air through an ESPHome-connected setup.
AddedCodexnews.ycombinator.comPRISM-INSIGHT splits Korean stock analysis across 13 agents, generates reports, and executes strategies. The author separately reports simulation returns and real-money account performance.
Added PRISM-INSIGHTnews.ycombinator.comAn 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.
AddedClaudevia Claude Codenews.ycombinator.comAn 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.
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.comA 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.
AddedClaudenews.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.comA Claude SDK agent used Playwright and a small Python TOTP implementation to configure MFA and verify an authentication change in a preview instance.
AddedClaudevia claude-agent-sdknews.ycombinator.comTwelve autonomous agents built Forge the Kingdom with Ren’Py and OpenClaw; a disruptive security quarantine led to supervised security actions with a cooldown.
Added
OpenClawnews.ycombinator.comA gollem author-bot generated The Year Unedited through chained planning, continuity checking, and iterative drafting; the author treated it as an orchestration test.
Added gollem author-botnews.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.
AddedClaude