---
title: "AI agents for personal: 86 real examples"
canonical: "https://agenticfeats.com/roles/personal/"
receipts: 86
shown: 44
page: 1
pages: 2
---

> From Agentic Feats: sourced examples of AI agents at work. Map of the site for agents: https://agenticfeats.com/llms.txt

# AI agents for personal: 86 real examples

Agentic Feats lists 86 sourced examples of AI agents in personal work; 44 link the artifact; most common agent: Claude Code (26). Newest first.

## Feats, newest first

- [Blood test PDFs to dashboard](https://agenticfeats.com/c/blood-test-pdfs-to-dashboard.md) (Other; Shown; 2026-10-13): 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.
- [Restaurant search with computer use](https://agenticfeats.com/c/restaurant-search-with-computer-use-claude-computer-use.md) (Claude computer use; Shown; 2026-10-13): Claude's computer-use agent searched Google for vegetarian restaurants near Bond Street and saved results to a notepad file on a remote machine. Result: It created the text file as asked, but after clicking a result it took a screenshot too early and hallucinated the answer.
- [Flight booking with computer use](https://agenticfeats.com/c/flight-booking-with-computer-use-claude-computer-use.md) (Claude computer use; Shown; 2026-10-13): Claude's computer use, running in a Docker container, opened Firefox and tried to book a New Delhi to Mumbai flight on MakeMyTrip. Result: Claude opened MakeMyTrip, cleared a sign-in popup after a second prompt, and began filling the search fields; no finished booking is shown.
- [Hands-on Operator test](https://agenticfeats.com/c/hands-on-operator-test.md) (Operator; Numbers; 2026-10-13): Casey Newton tested OpenAI's Operator on walking tours, a Gatsby lesson plan, Instacart groceries, and an Uber price check. Result: Operator handled tour search and lesson plan but was slow; adding three grocery items took 15 minutes and an Uber price check took five.
- [Operator concert and product research](https://agenticfeats.com/c/operator-concert-and-product-research.md) (Operator; Shown; 2026-10-13): Operator, OpenAI's browser agent, was tried on finding Berlin classical concerts and researching Anki competitors, using prompts and screen recordings. Result: Both tasks failed. The concert search returned three wrong concerts after 33 minutes, and the Anki competitor list had incorrect data.
- [Operator concert restaurant booking](https://agenticfeats.com/c/operator-concert-restaurant-booking.md) (Operator; Claim; 2026-10-13): Operator, tested by a member of Allie Miller's team, found a gluten-free restaurant near a Minneapolis concert venue and made a reservation. Result: Operator completed the restaurant search and booked the reservation, but a keto meal plan and a quilt pattern search came back weak.
- [Blog drafts from Obsidian notes](https://agenticfeats.com/c/blog-drafts-from-obsidian-notes-cursor.md) (Cursor; Claim; 2026-10-13): The author set Cursor to imitate their note.com writing style and read their Obsidian vault, then had it draft blog articles quoting past reading highlights. Result: Cursor drafted an article on their reading trends in their style, citing Kindle highlights from the vault. The author edited it by hand.
- [Comet browser grocery and pizza orders](https://agenticfeats.com/c/comet-browser-grocery-and-pizza-orders-perplexity-comet.md) (Perplexity Comet; Shown; 2026-10-13): Perplexity's Comet browser assistant built a charcuterie shopping list, added items to an Instacart cart, and tried to order a gluten-free pizza on Seamless. Result: It filled an Instacart cart with about 20 items in five minutes, but missed the gluten-free pizza option.
- [Restaurant list and home search](https://agenticfeats.com/c/restaurant-list-and-home-search-chatgpt-agent.md) (ChatGPT agent; Shown; 2026-10-13): ChatGPT agent picked 10 restaurants in the author's vacation city, found signature dishes, and saved them as a Google Maps list with notes. Result: Built the 10-restaurant Maps list in 23 minutes and exported 13 Marbella home listings to Excel, with data the author checked as accurate.
- [Buying on Amazon by photo](https://agenticfeats.com/c/buying-on-amazon-by-photo-chatgpt-agent.md) (ChatGPT agent; Claim; 2026-10-13): The author used ChatGPT Agent to buy items on Amazon from a photo of the old item, handling the full purchase. Result: The agent completed whole Amazon purchases from a wrapper photo and a short instruction, until Amazon blocked agent access.
- [Emailed AI news briefing](https://agenticfeats.com/c/emailed-ai-news-briefing-perplexity-comet.md) (Perplexity Comet; Shown; 2026-10-13): Perplexity Comet searched major outlets for the day's AI news, picked the top five stories, and emailed the author a brief. Result: A five-story AI news brief arrived by email from one prompt; the author says plain LLMs only draft text and cannot send it.
- [Booking a flight with Comet](https://agenticfeats.com/c/booking-a-flight-with-comet-perplexity-comet.md) (Perplexity Comet; Claim; 2026-10-13): Perplexity Comet searched flights, then booked the one the author chose on Southwest.com while logged in, filling fare class and passenger details. Result: The agent completed the purchase after the author confirmed it, and Southwest sent a booking confirmation email moments later.
- [Consulting jargon minigame collection](https://agenticfeats.com/c/consulting-jargon-minigame-collection-cursor.md) (Cursor; Shown; 2026-10-13): Alvin Leung used ChatGPT to refine a game concept, then Cursor Agent mode to generate a four-minigame Python tkinter game themed on consulting life. Result: A playable game with four minigames, persistent high scores, and no external dependencies was built in a couple of hours, with source code on GitHub.
- [Flight search comparison, Atlas vs Comet](https://agenticfeats.com/c/flight-search-comparison-atlas-vs-comet-perplexity-comet.md) (Other, Perplexity Comet; Numbers; 2026-10-13): 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.
- [FSA claims from Amazon invoices](https://agenticfeats.com/c/fsa-claims-from-amazon-invoices-claude-code.md) (Claude Code; Claim; 2026-10-13): Claude Code with Playwright MCP read Amazon PDF invoices and filed healthcare FSA reimbursement claims on the benefits portal. Result: About two minutes after the setup worked, a dozen FSA reimbursement claims had been submitted automatically.
- [Genetic and bloodwork health plan](https://agenticfeats.com/c/genetic-and-bloodwork-health-plan-claude-code.md) (Claude Code; Claim; 2026-10-13): Claude Code analyzed the author's 23andMe raw genetic file, bloodwork, artery plaque scans, and supplement routine in a two-hour back and forth about health. Result: The author came away with a health plan tailored to their genes and current health, built from the combined datasets.
- [Personal assistant via Claude Skills](https://agenticfeats.com/c/personal-assistant-via-claude-skills-claude-code.md) (Claude Code; Claim; 2026-10-13): Claude Code, run through a self-built phone UI, writes skills that handle the author's household errands, a daily brief, and a car inspection booking. Result: Three weeks without opening a personal laptop; Claude handles trash lookup, a 48-hour daily brief, an inspection booking, and a bakery stop.
- [Date night planning assistant](https://agenticfeats.com/c/date-night-planning-assistant-claude-code.md) (Claude Code; Claim; 2026-10-13): Claude Code, set up as an executive assistant, suggests date nights and double dates using the author's calendar and place lists. Result: The assistant nudges the couple with date suggestions when too much time has passed. Booking reservations is a possible next step.
- [Self-hosted home server setup](https://agenticfeats.com/c/self-hosted-home-server-setup-claude-code.md) (Claude Code; Shown; 2026-10-13): Claude Code, installed on a Beelink mini PC over SSH, set up Docker, Caddy, and a set of self-hosted services at home. Result: The author runs 14 containers including Vaultwarden, Immich, Plex, and Readeck, with daily USB and weekly S3 Glacier backups costing about twenty cents per month.
- [YouTube recipe to grocery cart](https://agenticfeats.com/c/youtube-recipe-to-grocery-cart-claude-cowork.md) (Claude Cowork, Claude in Chrome; Shown; 2026-10-13): Claude Cowork pulled recipes from a YouTube video, matched ingredients to past-invoice brands, filled a grocery cart, and wrote a Notion meal plan. Result: It filled the grocery cart and produced a Notion recipe page, replacing a routine of 45+ minutes of watching, list-making, and cart-filling.
- [Unlimited lives in River Raid](https://agenticfeats.com/c/unlimited-lives-in-river-raid-claude-code.md) (Claude Code; Shown; 2026-10-13): Claude, connected to Ghidra through an MCP server, analyzed an unlabeled Atari 8-bit ROM and found the code that decrements the player's lives. Result: Replacing one byte ($88 to $EA, DEY to NOP) kept the lives counter fixed at 3 when tested in an emulator.
- [Weekly ASDA grocery basket](https://agenticfeats.com/c/weekly-asda-grocery-basket-claude-in-chrome.md) (Claude in Chrome; Numbers; 2026-10-13): Claude in Chrome (Haiku) tried to fill an ASDA basket from a Claude-built Google Sheet of 40+ items, over five attempts. Result: Best run added 24 of 42 items for £71.76, then stopped early. The author still had to finish the basket and check out.
- [Insurance paperwork from hospital records](https://agenticfeats.com/c/insurance-paperwork-from-hospital-records-claude-cowork.md) (Claude Cowork; Shown; 2026-10-13): Claude Cowork read a folder of hospital record PDFs and filled out the author's insurance paperwork on their insurer's website. Result: The author handled complicated legal and medical insurance forms while feeding their newborn daughter, with Claude doing the filling.
- [Home Assistant AI agent with persona](https://agenticfeats.com/c/home-assistant-ai-agent-with-persona-openclaw.md) (OpenClaw; Shown; 2026-10-13): OpenClaw, running in a Proxmox LXC beside Home Assistant via ha-mcp, became an always-on agent with persistent markdown memory and a raccoon persona named Claudette. Result: Claudette controls the lights and speaks through Google Home speakers in an ElevenLabs voice, shown in a live demo.
- [Downloads folder cleanup](https://agenticfeats.com/c/downloads-folder-cleanup-claude-cowork.md) (Claude Cowork; Shown; 2026-10-13): Claude Cowork scanned a Downloads folder of 2,200 loose files, proposed an 11-folder structure, and sorted the files after the author approved the plan. Result: The initial sort took a few minutes and left no loose files in the main directory, in about 20 minutes of active work.
- [Claude Code composes original music](https://agenticfeats.com/c/claude-code-composes-original-music.md) (Claude Code; Shown; 2026-10-13): Claude Code wrote Python from scratch to synthesize original songs, a rock track with vocals, matching music videos, and a five-track album with cover art. Result: Produced a five-track album plus EDM and rock songs with visualizations, all from one-shot prompts; a sampling attempt and getting English vocals were weaker.
- [Hands-free voice for Claude Code](https://agenticfeats.com/c/hands-free-voice-for-claude-code.md) (Claude Code; Claim; 2026-10-13): The author built a local speech-to-text and text-to-speech stack with a custom MCP so Claude Code can be driven by voice through AirPods. Result: The author debugged a custom WhatsApp integration hands-free while brushing their teeth, using the voice stack running locally on an M4 Pro.
- [Agent-built research knowledge bases](https://agenticfeats.com/c/agent-built-research-knowledge-bases-openclaw.md) (OpenClaw; Shown; 2026-10-13): OpenClaw learned to use a YouTube summariser, a paper extraction tool, and QMD, then built searchable Markdown knowledge bases for videos and research papers. Result: The author now has two dense, searchable knowledge bases, one from YouTube videos and one from research papers, which they say speeds up understanding.
- [OpenClaw personal agent setup](https://agenticfeats.com/c/openclaw-personal-agent-setup.md) (OpenClaw; Shown; 2026-10-13): The author runs OpenClaw on an old MacBook Air, talks to it through Slack, and set up a daily morning brief and a task dashboard. Result: A working personal agent that sends an 8am brief and updates a vibe-coded Kanban dashboard in real time as it works.
- [Personal finance assistant in Markdown](https://agenticfeats.com/c/personal-finance-assistant-in-markdown-claude-code.md) (Claude Code; Shown; 2026-10-13): Claude Code, with the Baselight MCP and a CLAUDE.md plus Markdown and YAML files, became a personal finance and investment assistant with no application code. Result: The author replaced abandoned finance apps and a spreadsheet with a git-synced assistant that tracks portfolio, decisions, and plans.
- [Portfolio optimization plan from brokerage CSVs](https://agenticfeats.com/c/portfolio-optimization-plan-from-brokerage-csvs-claude-code.md) (Claude Code; Claim; 2026-10-13): Claude Code parsed the author's brokerage CSVs and notes, then built a phased portfolio optimization plan with tax analysis and fund swaps. Result: Over several sessions it produced a phased plan with tax impact analysis, fund swaps, and before-and-after allocation grids, comparable to an advisor's plan.
- [YouTube research into Obsidian graph](https://agenticfeats.com/c/youtube-research-into-obsidian-graph-claude-code.md) (Claude Code; Shown; 2026-10-13): Claude Code searched YouTube, loaded 20 videos into NotebookLM, asked cited questions, and saved everything to Obsidian as linked notes. Result: The author turned 20 videos into a browsable knowledge graph of sources and topics in their vault. A citation audit found about 60% strong matches.
- [OpenClaw buys from Amazon](https://agenticfeats.com/c/openclaw-buys-from-amazon.md) (OpenClaw; Shown; 2026-10-13): OpenClaw agent used the buy-anything skill and Rye's checkout API to find, check out, and order products for Ryan Eade. Result: Ryan completed real purchases delivered to his door, replaced his Alexa buying flow, and passed the Amazon challenge on a live podcast demo.
- [Personal apps on a Raspberry Pi](https://agenticfeats.com/c/personal-apps-on-a-raspberry-pi-claude-code.md) (Claude Code; Shown; 2026-10-13): Claude Code built five personal tools for a non-coder, including a multiplayer game, a WhatsApp scheduler, and a finance tracker. Result: The author shipped five projects in about two weeks, with public repos and a finance tracker running nightly on a Raspberry Pi.
- [Car purchase negotiation](https://agenticfeats.com/c/car-purchase-negotiation-openclaw.md) (OpenClaw; Numbers; 2026-10-13): OpenClaw researched Palisade prices, contacted nearby dealers, and played their quotes against each other by email for AJ Stuyvenberg. Result: The agent negotiated a $4,200 dealer discount, bringing the car to about $56k, and the buyer never visited a showroom.
- [Personal memory from data exports](https://agenticfeats.com/c/personal-memory-from-data-exports-openclaw.md) (OpenClaw; Claim; 2026-10-13): OpenClaw, fed ChatGPT, Google and Instagram history via context-use, books restaurants and sends daily recommendations. Result: The agent found and booked a restaurant the author visited, and recommended a book that the author read and liked before a trip to Kerala.
- [AI-made 8D music video](https://agenticfeats.com/c/ai-made-8d-music-video-hermes-agent.md) (Hermes Agent; Claim; 2026-10-13): Hermes-Agent wrote lyrics, generated music, vocals and stems, made images from the lyrics, and added audio-reactive effects to produce a full music video. Result: The agent produced a complete 8D music video with seven locally rendered images timed to the lyric structure.
- [Claude computer use on Mac](https://agenticfeats.com/c/claude-computer-use-on-mac.md) (Claude computer use; Claim; 2026-10-13): Claude used its new computer use feature to take over a Mac, open the Chess app, and try to play a game. Result: Claude opened Chess and reported the board state, but never played a game, and half an hour of use drained the five-hour Claude Pro allotment.
- [Reviving a 1991 assembly game](https://agenticfeats.com/c/reviving-a-1991-assembly-game-claude-code.md) (Claude Code; Claim; 2026-10-13): Claude Code CLI with Sonnet helped the author recompile their 1991 DOS assembly code using UASM and run it in DOSBox. Result: All the author's old utilities, such as picture converters and sprite extractors, now compile and run in DOSBox. The main game does not compile yet.
- [Complex personal tax return](https://agenticfeats.com/c/complex-personal-tax-return-openclaw.md) (OpenClaw; Numbers; 2026-10-13): OpenClaw read years of tax records and entity documents, built a summary, then guided the author through filing a complex return in TurboTax. Result: Filed a 137-page federal return for $129 in software and $23.90 in tokens versus an $8,000 CPA bill, in about 6 hours.
- [Nine OpenClaw agents](https://agenticfeats.com/c/nine-openclaw-agents.md) (OpenClaw; Numbers; 2026-10-13): Claire Vo built nine OpenClaw agents covering sales, business operations, scheduling, family logistics, and kids' education, after starting with a single executive-assistant agent. Result: One agent now does the CRM management and customer email drafting that cost about 10 paid hours a week last year.
- [Claude Code desktop app control](https://agenticfeats.com/c/claude-code-desktop-app-control.md) (Claude Code; Shown; 2026-10-13): Claude Code, given permission to control the author's Windows PC, opened Calculator, did a sum, and pasted the result into a saved Notepad file. Result: The author reports Claude Code operated apps that have no API, completing the Calculator-to-Notepad task and saving result.txt to the Desktop.
- [Amazon subscription refund](https://agenticfeats.com/c/amazon-subscription-refund-codex.md) (Codex; Shown; 2026-10-13): Codex running GPT-5.5 cancelled an Amazon subscription, opened the live chat with an associate, and argued for an immediate refund. Result: The associate confirmed the refund and the author got $15 back within about five minutes, while the author watched it happen.
- [Tenant complaints to housing board](https://agenticfeats.com/c/tenant-complaints-to-housing-board-claude-code.md) (Claude Code; Numbers; 2026-10-13): A Claude Code agent researched building violations and filed 14 staggered 311 complaints with the NYC housing board for the author's apartment. Result: Inspectors confirmed 11 of 14 predicted violations plus 3 more, and the landlord was fined $2,800, per the author.
- [Robotic arm designed with Claude Code](https://agenticfeats.com/c/robotic-arm-designed-with-claude-code.md) (Claude Code; Numbers; 2026-10-13): Claude Code wrote the FreeCAD Python geometry for a 5-DOF servo arm, which later gained voice and camera control. Result: The author designed, printed, and assembled a working four-servo arm in about 30 hours with almost no CAD experience, then added voice and vision control.
- [Codex email audit and trip site](https://agenticfeats.com/c/codex-email-audit-and-trip-site.md) (Codex; Shown; 2026-10-13): Codex, driven by two authors, audited a month of missed emails, built a vacation planning site from a phone, and shopped for a dishwasher. Result: Codex returned a complete, classified list of missed email threads where Claude missed many; it also deployed a vacation site researched from hotel availability.
- [Chrome auto browse five-task test](https://agenticfeats.com/c/chrome-auto-browse-five-task-test-gemini-agent.md) (Gemini agent; Numbers; 2026-10-13): Gemini's Chrome auto browse ran five real tasks for the author: hotel research, tax document downloads, grocery cart building, plumber quote forms, and subscription cancellation. Result: Hotel comparison, four tax PDFs, and an 18-item cart under $80 worked. Subscription cancellation failed.
- [Indie platformer from scratch](https://agenticfeats.com/c/indie-platformer-from-scratch-claude-code.md) (Claude Code; Shown; 2026-10-13): A content creator had Claude Code (Opus 4) build a 2D black-and-white platformer called Seek in HTML and JavaScript canvas, with no prior coding experience. Result: Claude Code produced a playable wave-based game with four enemy types; the creator reached wave 10 on camera and said it matched their vision.
- [MRI second opinion](https://agenticfeats.com/c/mri-second-opinion-claude-code.md) (Claude Code; Shown; 2026-10-13): Claude Code with Opus 4.8 read a DICOM shoulder MRI export, then ran a subagent-based arbitration against the human radiology report. Result: Opus found no tear where the doctor reported a Grade III partial-thickness tear. The author is unsure which reading to trust.
- [Comms tasks with Codex](https://agenticfeats.com/c/comms-tasks-with-codex.md) (Codex; Numbers; 2026-10-13): The author used OpenAI's Codex to build a PR coverage dashboard, sort a messy work folder, and filter a recipe site for picky kids. Result: Codex sorted 240 dinner recipes down to 62 family-fit picks, rated them, and produced an index, a spreadsheet, and a Google Drive folder.

Page 1 of 2. Older feats: https://agenticfeats.com/roles/personal/2.md