Real examples of AI agents in software companies.https://agenticfeats.com/enhttps://agenticfeats.com/c/one-month-testing-devin/https://agenticfeats.com/c/one-month-testing-devin/Devin was connected to the RunLLM GitHub repo and given small bug fixes and one larger full-stack task over a month. Result: Small scoped fixes took about five minutes to test and merge versus roughly an hour by hand; the full-stack task failed and was rewritten. Evidence: Numbers. Source: https://frontierai.substack.com/p/one-month-of-using-devinTue, 13 Oct 2026 15:29:03 GMTDevinCodinghttps://agenticfeats.com/c/docs-maintenance-with-devin/https://agenticfeats.com/c/docs-maintenance-with-devin/Devin handled a docs team's recurring work: weekly changelog setup, GitHub issue and PR fixes, a multi-file term rename, and code explanations. Result: Devin found nearly every old term in a docs-wide rename, but the edits still needed 20+ manual commits. Evidence: Numbers. Source: https://neon.com/blog/ai-workflows-for-docs-devinTue, 13 Oct 2026 15:29:03 GMTDevinMarketing and Contenthttps://agenticfeats.com/c/mental-models-framework-built-with-agents-claude-code/https://agenticfeats.com/c/mental-models-framework-built-with-agents-claude-code/A solo founder gave Claude, ChatGPT, Windsurf, and Cursor defined roles to build and deploy a 120-model mental models framework. Result: The author shipped 120 models, an MCP server for Claude Desktop, and 140 chaos tests with a 100% pass rate over 22 months. Evidence: Numbers. Source: https://news.ycombinator.com/item?id=46061679Tue, 13 Oct 2026 15:29:03 GMTClaude CodeCursorOtherCodinghttps://agenticfeats.com/c/devin-builds-devin/https://agenticfeats.com/c/devin-builds-devin/Devin handles Cognition's own engineering work across Slack, Linear, and the web app: PRs, code review, bug triage, debugging, and design system audits. Result: Cognition merged 659 Devin PRs into its own codebase in one week, up from 154 in its best week of 2025. Evidence: Numbers. Source: https://nader.substack.com/p/how-cognition-uses-devin-to-buildTue, 13 Oct 2026 15:29:03 GMTDevinCodinghttps://agenticfeats.com/c/devin-building-devin/https://agenticfeats.com/c/devin-building-devin/Cognition's team uses Devin across Slack, Linear, web, CLI and API to write, review, triage and debug code in its own codebase. Result: Cognition merged 659 Devin-authored PRs into its own codebase in one week, up from 154 in its best week of 2025. Evidence: Shown. Source: https://cognition.com/blog/how-cognition-uses-devin-to-build-devinTue, 13 Oct 2026 15:29:03 GMTDevinCodinghttps://agenticfeats.com/c/local-browser-testing-loop-claude-code/https://agenticfeats.com/c/local-browser-testing-loop-claude-code/Claude Code with the Chrome extension builds features, then opens localhost in the author's real Chrome session to test, read console errors, and fix issues. Result: On a dashboard filter task, Claude fixed URL query param handling in three iterations without the author touching the browser. Evidence: Claim. Source: https://test-lab.ai/blog/claude-code-chrome-extension-local-testingTue, 13 Oct 2026 15:29:03 GMTClaude CodeClaude in ChromeCodinghttps://agenticfeats.com/c/devin-cloud-testing-of-prs/https://agenticfeats.com/c/devin-cloud-testing-of-prs/Devin writes a test plan, runs the app on a cloud VM with computer use, and returns annotated test videos and reports. Result: Test runs approved per day on Devin more than doubled in a couple of months, and engineers run 10 to 20 Devins in parallel. Evidence: Numbers. Source: https://cognition.ai/blog/testing-developmentTue, 13 Oct 2026 15:29:03 GMTDevinCodinghttps://agenticfeats.com/c/world-cup-reels-for-app-signups-openclaw/https://agenticfeats.com/c/world-cup-reels-for-app-signups-openclaw/OpenClaw tracked World Cup results and had Claude post a templated Instagram trial reel after each match. Result: Ben Guez reports over one million views and 200 DMs within a few days, with replies routed to his language app. Evidence: Shown. Source: https://techcrunch.com/2026/07/02/yep-were-using-openclaw-to-date-nowTue, 13 Oct 2026 15:29:03 GMTClaude CodeOpenClawMarketing and Contenthttps://agenticfeats.com/c/internal-sales-ai-for-cursor-reps-custom-agent/https://agenticfeats.com/c/internal-sales-ai-for-cursor-reps-custom-agent/Cursor's Head of Enterprise Growth built ChatGTM, an internal chat tool that pulls CRM, call, and web data to draft outreach and research accounts. Result: Used across Cursor's 400+ person sales org, it reportedly helps SDRs book 3x more qualified meetings and cuts AE ramp time by over 50%. Evidence: Numbers. Source: https://thesignal.club/p/chatgtmTue, 13 Oct 2026 15:29:03 GMTCustom agentSaleshttps://agenticfeats.com/c/engineer-bots-managing-cloud-agents-grok-bot/https://agenticfeats.com/c/engineer-bots-managing-cloud-agents-grok-bot/A SpaceXSI engineer runs five Grok Bot engineer bots that spin up Cursor cloud agents, review PRs via a Notion database, and auto-merge low-risk changes. Result: The fleet manages over 200 cloud agents at once, up from 15 managed by hand, and built Grok Bot iOS v0 in three weeks. Evidence: Numbers. Source: https://x.ai/bot/guides/grok-bot-for-engineeringTue, 13 Oct 2026 15:29:03 GMTGrok BotOtherCodinghttps://agenticfeats.com/c/million-line-codebase-refactor-hermes-agent/https://agenticfeats.com/c/million-line-codebase-refactor-hermes-agent/Hermes Agent split a million-line Python repo into 36 groups and dispatched 1,393 subagents in git worktrees to refactor it. Result: Non-test Python fell from 1,063,826 to 698,363 lines (34.4%), gateway/run.py from 34,847 to 5,512 lines, and functions over 300 lines from 192 to 2. Evidence: Shown. Source: https://nousresearch.com/refactoring-hermes-with-1393-agentsTue, 13 Oct 2026 15:29:03 GMTHermes AgentCodinghttps://agenticfeats.com/c/openai-build-fix-agent-on-openclaw/https://agenticfeats.com/c/openai-build-fix-agent-on-openclaw/An OpenAI engineer reports an internal OpenClaw agent, Androidclaw, working across Git, GitHub and logs to trace broken builds back to their causes. Result: Androidclaw traces broken builds to the relevant pull request and incident, and sometimes prepares and merges fixes itself. Evidence: Claim. Source: https://venturebeat.com/orchestration/openclaw-launches-free-enterprise-control-plane-for-persistent-ai-agents-backed-by-openai-red-hat-and-nvidiaTue, 13 Oct 2026 15:29:03 GMTOpenClawCodinghttps://agenticfeats.com/c/hospital-style-agent-pipeline-ships-db2-support-custom-agent/https://agenticfeats.com/c/hospital-style-agent-pipeline-ships-db2-support-custom-agent/Cockroach Labs ran a multi-role coding agent pipeline modeled on a teaching hospital to add Db2 support to its MOLT migration tool. Result: Db2 support shipped in under two days for a $4172 token bill, versus 9 months and about $160K for Oracle; 27 PRs merged. Evidence: Shown. Source: https://cockroachlabs.com/blog/experiment-running-hospital-codeTue, 13 Oct 2026 15:29:03 GMTCustom agentCodinghttps://agenticfeats.com/c/month-of-devin-tasks/https://agenticfeats.com/c/month-of-devin-tasks/Devin was given more than 20 real coding, research, and code-modification tasks over a month by an Answer.AI team to test its autonomy. Result: Out of 20 tasks, Devin had 14 failures, 3 successes, and 3 inconclusive results, with no pattern predicting which would work. Evidence: Numbers. Source: https://answer.ai/posts/2025-01-08-devin.htmlTue, 13 Oct 2026 15:29:03 GMTDevinCodinghttps://agenticfeats.com/c/agent-workforce-for-unstaffed-functions-lindy/https://agenticfeats.com/c/agent-workforce-for-unstaffed-functions-lindy/Ankor's CEO built Lindy agents covering lead research, technical support, content and marketing, and meeting prep, work too small to justify dedicated hires. Result: Ten agents were live in the first week and 20-30 run today. The CEO estimates at least a 5x return on investment. Evidence: Numbers. Source: https://lindy.ai/case-study/ankorTue, 13 Oct 2026 15:29:03 GMTLindyBusiness