What people got done with Other.https://agenticfeats.com/enhttps://agenticfeats.com/c/blood-test-pdfs-to-dashboard/https://agenticfeats.com/c/blood-test-pdfs-to-dashboard/Claude took several unstructured blood test PDFs exported from MyChart and built an interactive browser tool to explore the results over time. Result: The tool flagged abnormal values and gave general health insights, built in about five minutes from a single prompt. Evidence: Shown. Source: https://mattstockton.com/2024/07/18/unstructured-medical-data-with-llms.htmlTue, 13 Oct 2026 15:29:03 GMTOtherPersonal and Familyhttps://agenticfeats.com/c/ai-agents-play-free-games/https://agenticfeats.com/c/ai-agents-play-free-games/Seven AI agents, each with a Linux computer and a group chat, tried to complete as many online games as possible in a week. Result: No agent won a game. Gemini 2.5 Pro made the most progress, reaching veteran footman rank in the idle game Progress Knight. Evidence: Shown. Source: https://lesswrong.com/posts/89qhQH8eHsrZxveHp/claude-plays-whatever-it-wantsTue, 13 Oct 2026 15:29:03 GMTClaude CodeOtherResearchhttps://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/flight-search-comparison-atlas-vs-comet-perplexity-comet/https://agenticfeats.com/c/flight-search-comparison-atlas-vs-comet-perplexity-comet/The author gave ChatGPT Atlas and Perplexity Comet the same nonstop SFO to NYC flight search for a wedding trip, with airline and airport preferences. Result: Atlas returned 11 round-trip combinations with times, airports and prices. Comet gave general statements and pointed to aggregator sites instead of pulling live data. Evidence: Numbers. Source: https://medium.com/@amurray101/chatgpt-atlas-vs-perplexity-comet-on-flight-booking-f580f8bd6e14Tue, 13 Oct 2026 15:29:03 GMTOtherPerplexity CometPersonal and Familyhttps://agenticfeats.com/c/ai-browser-shopping-test-perplexity-comet/https://agenticfeats.com/c/ai-browser-shopping-test-perplexity-comet/DreamHost tested five AI browsers on one Amazon task: research grinder coffee makers under $100, tabulate five, add two to cart. Result: Perplexity Comet completed the task and stopped at the cart. ChatGPT Atlas also reached checkout but was too slow to be usable. Evidence: Shown. Source: https://dreamhost.com/blog/ai-web-browserTue, 13 Oct 2026 15:29:03 GMTChatGPT agentOtherPerplexity CometResearchhttps://agenticfeats.com/c/scout-automates-crm-pipeline-hygiene/https://agenticfeats.com/c/scout-automates-crm-pipeline-hygiene/Microsoft Scout, an agent built on OpenClaw, opened a browser, inspected CRM opportunity records, exported a summary to SharePoint, and posted compliance findings to Teams. Result: A CRM pipeline check that needed a manual export plus a separate analysis tool now runs end to end, with out-of-compliance entries flagged in Teams. Evidence: Shown. Source: https://copilotatwork.substack.com/p/microsoft-scout-is-not-just-anotherTue, 13 Oct 2026 15:29:03 GMTOtherSaleshttps://agenticfeats.com/c/36-second-video-from-one-image/https://agenticfeats.com/c/36-second-video-from-one-image/The author used Grok Imagine's Agent Mode with a single image and a simple prompt to produce a short video with matching scenes and subtitles. Result: A 36-second video with multiple camera angles, a visual storyline, and subtitles, made in about five minutes. Evidence: Shown. Source: https://x.com/xfreeze/status/2078833307207483764Tue, 13 Oct 2026 15:29:03 GMTOtherCreativehttps://agenticfeats.com/c/bazi-fortune-agent-on-marketplace/https://agenticfeats.com/c/bazi-fortune-agent-on-marketplace/The author built a BaZi fortune-telling agent with AI agents doing the coding, then listed it on the OKX AI Marketplace with pay-per-call USDT pricing. Result: The agent went from spec to live listing in under a week and has settled 20+ real on-chain transactions across four paid services. Evidence: Shown. Source: https://x.com/ducktumay/status/2076933094628876322Tue, 13 Oct 2026 15:29:03 GMTOtherBusinesshttps://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/school-homework-to-calendar/https://agenticfeats.com/c/school-homework-to-calendar/Meta's Muse agent logs into a school information system through a credential vault, collects homework and due dates, and adds them to a child's calendar. Result: Set up to run daily, it creates calendar entries with a day-before reminder and a link. The author calls the first run not bad. Evidence: Claim. Source: https://news.ycombinator.com/item?id=49796524Tue, 13 Oct 2026 15:29:03 GMTOtherPersonal and Familyhttps://agenticfeats.com/c/faster-rust-ml-code-via-benchmarks-codex/https://agenticfeats.com/c/faster-rust-ml-code-via-benchmarks-codex/Coding agents wrote Rust ML algorithms like UMAP from scratch, then iteratively optimized them against criterion benchmarks. Result: Each model pass added about 1.5x to 2.0x speedup, reaching roughly 7.5x to 32x over baseline; one implementation beat xgboost on speed. Evidence: Shown. Source: https://minimaxir.com/2026/09/agentic-iterationTue, 13 Oct 2026 15:29:03 GMTCodexOtherCodinghttps://agenticfeats.com/c/chatgpt-dots-day-one-test/https://agenticfeats.com/c/chatgpt-dots-day-one-test/Julian Goldie tested OpenAI's new ChatGPT Dots agent on launch day with research, a website build, computer use, and a restaurant booking. Result: Research, site build and restaurant booking worked, but computer use was very slow and the call button failed. Evidence: Shown. Source: https://juliangoldie.com/chatgpt-dotsTue, 13 Oct 2026 15:29:03 GMTOtherResearchhttps://agenticfeats.com/c/ai-built-online-store/https://agenticfeats.com/c/ai-built-online-store/Ryan Robinson used Bluehost's AI store builder to generate a retail store for Little River Studios from one product description. Result: The author launched a store taking real payments in one sitting and ran a test order. Five agents now watch orders and stock. Evidence: Shown. Source: https://ryrob.com/run-online-store-with-aiTue, 13 Oct 2026 15:29:03 GMTOtherBusinesshttps://agenticfeats.com/c/backlink-outreach-for-promptslove/https://agenticfeats.com/c/backlink-outreach-for-promptslove/The author's ChatGPT Dot, Jamie, researched publishers, drafted pitches, sent outreach and form submissions, and tracked results for Promptslove's digital PR campaign. Result: Jamie reported 13 outreach actions and zero live links early on; the author later verified the first live nofollow directory backlink. Evidence: Shown. Source: https://promptslove.com/blog/openai-dots-guideTue, 13 Oct 2026 15:29:03 GMTOtherMarketing and Contenthttps://agenticfeats.com/c/email-calendar-scheduling-assistant/https://agenticfeats.com/c/email-calendar-scheduling-assistant/The author's AI assistant reads forwarded emails in a labeled Gmail inbox, emails recipients to coordinate times, and adds Zoom bridges. Result: After a few months of iterations, the author has a working assistant, open sourced so others can have their AI configure it for their needs. Evidence: Shown. Source: https://x.com/edsoehnel/status/2107574500984287570Tue, 13 Oct 2026 15:29:03 GMTOtherFinance and Adminhttps://agenticfeats.com/c/movie-ticket-booking-skill-openclaw/https://agenticfeats.com/c/movie-ticket-booking-skill-openclaw/The author had their Muse agent build a reusable skill that books movie tickets, handling calendar checks, seat choice, purchase, and a reminder to leave. Result: The agent built a skill that checks the calendar, buys the ticket via its wallet, adds the event, and sends a leave-time message. Evidence: Claim. Source: https://x.com/jjenglert/status/2108260489197130058Tue, 13 Oct 2026 15:29:03 GMTOpenClawOtherPersonal and Familyhttps://agenticfeats.com/c/office-documents-built-by-agents-claude-code/https://agenticfeats.com/c/office-documents-built-by-agents-claude-code/AI agents use the OfficeCLI binary to create and edit Word, Excel, and PowerPoint files, and check them through HTML or PNG rendering. Result: The repo shows sample decks, Word documents, and Excel workbooks, all created by agents with no templates and no manual editing. Evidence: Shown. Source: https://github.com/iOfficeAI/OfficeCLITue, 13 Oct 2026 15:29:03 GMTClaude CodeCursorGitHub Copilot agentOtherSetup and Metahttps://agenticfeats.com/c/household-errands-with-always-on-bots-grok-bot/https://agenticfeats.com/c/household-errands-with-always-on-bots-grok-bot/Eleanor Konik used Muse and Grok Bot for library requests, dishwasher shopping, marketplace scans, party planning, grant research, and publishing a landing page. Result: Bought a new KitchenAid dishwasher within days, found a $25 armchair, caught a last-show date night, and published a landing page via Cloudflare. Evidence: Shown. Source: https://eleanorkonik.com/p/muse-was-my-gateway-drug-to-grokTue, 13 Oct 2026 15:29:03 GMTGrok BotOtherPersonal and Familyhttps://agenticfeats.com/c/microsoft-365-on-linux/https://agenticfeats.com/c/microsoft-365-on-linux/A Nix flake runs Microsoft 365 and Office Home 2024 on Linux through umu-launcher and GE-Proton, with shims fixing Wine crashes. Result: Word starts and draws its ribbon, OneNote signs in and saves edits, and a retail Home 2024 key activated through account sign-in. Evidence: Shown. Source: https://github.com/Tombert/office365_flakeTue, 13 Oct 2026 15:29:03 GMTOtherOps and IThttps://agenticfeats.com/c/sqlite-like-engine-in-rust-claude-code/https://agenticfeats.com/c/sqlite-like-engine-in-rust-claude-code/Claude, Codex, and Gemini workers, two of each, built a SQLite-style database engine in Rust by claiming tasks through git lock files. Result: About 19k lines of Rust across 154 commits in three days. The engine passes 64 SQLLogicTest queries and 282 AI-written unit tests. Evidence: Shown. Source: https://kiankyars.github.io/machine_learning/2026/02/12/sqlite.htmlTue, 13 Oct 2026 15:29:03 GMTClaude CodeCodexOtherCoding