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
- 86
- Shown
- 4451%
- Agents
- 16
- Updated
- Oct 13
Agents used here16
Industries here2
The tool flagged abnormal values and gave general health insights, built in about five minutes from a single prompt.
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.
It created the text file as asked, but after clicking a result it took a screenshot too early and hallucinated the answer.
Restaurant search with computer use
Claude's computer-use agent searched Google for vegetarian restaurants near Bond Street and saved results to a notepad file on a remote machine.
Claude opened MakeMyTrip, cleared a sign-in popup after a second prompt, and began filling the search fields; no finished booking is shown.
Flight booking with computer use
Claude's computer use, running in a Docker container, opened Firefox and tried to book a New Delhi to Mumbai flight on MakeMyTrip.
Operator handled tour search and lesson plan but was slow; adding three grocery items took 15 minutes and an Uber price check took five.
Hands-on Operator test
Casey Newton tested OpenAI's Operator on walking tours, a Gatsby lesson plan, Instacart groceries, and an Uber price check.
Both tasks failed. The concert search returned three wrong concerts after 33 minutes, and the Anki competitor list had incorrect data.
Operator concert and product research
Operator, OpenAI's browser agent, was tried on finding Berlin classical concerts and researching Anki competitors, using prompts and screen recordings.
Operator completed the restaurant search and booked the reservation, but a keto meal plan and a quilt pattern search came back weak.
Operator concert restaurant booking
Operator, tested by a member of Allie Miller's team, found a gluten-free restaurant near a Minneapolis concert venue and made a reservation.
Cursor drafted an article on their reading trends in their style, citing Kindle highlights from the vault. The author edited it by hand.
Blog drafts from Obsidian notes
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.
It filled an Instacart cart with about 20 items in five minutes, but missed the gluten-free pizza option.
Comet browser grocery and pizza orders
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.
Built the 10-restaurant Maps list in 23 minutes and exported 13 Marbella home listings to Excel, with data the author checked as accurate.
Restaurant list and home search
ChatGPT agent picked 10 restaurants in the author's vacation city, found signature dishes, and saved them as a Google Maps list with notes.
The agent completed whole Amazon purchases from a wrapper photo and a short instruction, until Amazon blocked agent access.
Buying on Amazon by photo
The author used ChatGPT Agent to buy items on Amazon from a photo of the old item, handling the full purchase.
A five-story AI news brief arrived by email from one prompt; the author says plain LLMs only draft text and cannot send it.
Emailed AI news briefing
Perplexity Comet searched major outlets for the day's AI news, picked the top five stories, and emailed the author a brief.
The agent completed the purchase after the author confirmed it, and Southwest sent a booking confirmation email moments later.
Booking a flight with Comet
Perplexity Comet searched flights, then booked the one the author chose on Southwest.com while logged in, filling fare class and passenger details.
Get five like these every week
The week's strongest feats, each with its receipt, plus a short roundup of AI news. Free.
You're on the list.
A free weekly newsletter. See what's in it
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.
Consulting jargon minigame collection
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.
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.
Flight search comparison, Atlas vs 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.
About two minutes after the setup worked, a dozen FSA reimbursement claims had been submitted automatically.
FSA claims from Amazon invoices
Claude Code with Playwright MCP read Amazon PDF invoices and filed healthcare FSA reimbursement claims on the benefits portal.
The author came away with a health plan tailored to their genes and current health, built from the combined datasets.
Genetic and bloodwork health plan
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.
Three weeks without opening a personal laptop; Claude handles trash lookup, a 48-hour daily brief, an inspection booking, and a bakery stop.
Personal assistant via Claude Skills
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.
The assistant nudges the couple with date suggestions when too much time has passed. Booking reservations is a possible next step.
Date night planning assistant
Claude Code, set up as an executive assistant, suggests date nights and double dates using the author's calendar and place lists.
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.
Self-hosted home server setup
Claude Code, installed on a Beelink mini PC over SSH, set up Docker, Caddy, and a set of self-hosted services at home.
It filled the grocery cart and produced a Notion recipe page, replacing a routine of 45+ minutes of watching, list-making, and cart-filling.
YouTube recipe to grocery cart
Claude Cowork pulled recipes from a YouTube video, matched ingredients to past-invoice brands, filled a grocery cart, and wrote a Notion meal plan.
Replacing one byte ($88 to $EA, DEY to NOP) kept the lives counter fixed at 3 when tested in an emulator.
Unlimited lives in River Raid
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.
Best run added 24 of 42 items for £71.76, then stopped early. The author still had to finish the basket and check out.
Weekly ASDA grocery basket
Claude in Chrome (Haiku) tried to fill an ASDA basket from a Claude-built Google Sheet of 40+ items, over five attempts.
The author handled complicated legal and medical insurance forms while feeding their newborn daughter, with Claude doing the filling.
Insurance paperwork from hospital records
Claude Cowork read a folder of hospital record PDFs and filled out the author's insurance paperwork on their insurer's website.
Claudette controls the lights and speaks through Google Home speakers in an ElevenLabs voice, shown in a live demo.
Home Assistant AI agent with persona
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.
The initial sort took a few minutes and left no loose files in the main directory, in about 20 minutes of active work.
Downloads folder cleanup
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.
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.
Claude Code composes original music
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.
The author debugged a custom WhatsApp integration hands-free while brushing their teeth, using the voice stack running locally on an M4 Pro.
Hands-free voice for Claude Code
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.
The author now has two dense, searchable knowledge bases, one from YouTube videos and one from research papers, which they say speeds up understanding.
Agent-built research knowledge bases
OpenClaw learned to use a YouTube summariser, a paper extraction tool, and QMD, then built searchable Markdown knowledge bases for videos and research papers.
A working personal agent that sends an 8am brief and updates a vibe-coded Kanban dashboard in real time as it works.
OpenClaw personal agent setup
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.
The author replaced abandoned finance apps and a spreadsheet with a git-synced assistant that tracks portfolio, decisions, and plans.
Personal finance assistant in Markdown
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.
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.
Portfolio optimization plan from brokerage CSVs
Claude Code parsed the author's brokerage CSVs and notes, then built a phased portfolio optimization plan with tax analysis and fund swaps.
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.
YouTube research into Obsidian graph
Claude Code searched YouTube, loaded 20 videos into NotebookLM, asked cited questions, and saved everything to Obsidian as linked notes.
Ryan completed real purchases delivered to his door, replaced his Alexa buying flow, and passed the Amazon challenge on a live podcast demo.
OpenClaw buys from Amazon
OpenClaw agent used the buy-anything skill and Rye's checkout API to find, check out, and order products for Ryan Eade.
The author shipped five projects in about two weeks, with public repos and a finance tracker running nightly on a Raspberry Pi.
Personal apps on a Raspberry Pi
Claude Code built five personal tools for a non-coder, including a multiplayer game, a WhatsApp scheduler, and a finance tracker.
The agent negotiated a $4,200 dealer discount, bringing the car to about $56k, and the buyer never visited a showroom.
Car purchase negotiation
OpenClaw researched Palisade prices, contacted nearby dealers, and played their quotes against each other by email for AJ Stuyvenberg.
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.
Personal memory from data exports
OpenClaw, fed ChatGPT, Google and Instagram history via context-use, books restaurants and sends daily recommendations.
The agent produced a complete 8D music video with seven locally rendered images timed to the lyric structure.
AI-made 8D music video
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.
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.
Claude computer use on Mac
Claude used its new computer use feature to take over a Mac, open the Chess app, and try to play a game.
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.
Reviving a 1991 assembly game
Claude Code CLI with Sonnet helped the author recompile their 1991 DOS assembly code using UASM and run it in DOSBox.
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.
Complex personal tax return
OpenClaw read years of tax records and entity documents, built a summary, then guided the author through filing a complex return in TurboTax.
One agent now does the CRM management and customer email drafting that cost about 10 paid hours a week last year.
Nine OpenClaw agents
Claire Vo built nine OpenClaw agents covering sales, business operations, scheduling, family logistics, and kids' education, after starting with a single executive-assistant agent.
The author reports Claude Code operated apps that have no API, completing the Calculator-to-Notepad task and saving result.txt to the Desktop.
Claude Code desktop app control
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.
The associate confirmed the refund and the author got $15 back within about five minutes, while the author watched it happen.
Amazon subscription refund
Codex running GPT-5.5 cancelled an Amazon subscription, opened the live chat with an associate, and argued for an immediate refund.
Inspectors confirmed 11 of 14 predicted violations plus 3 more, and the landlord was fined $2,800, per the author.
Tenant complaints to housing board
A Claude Code agent researched building violations and filed 14 staggered 311 complaints with the NYC housing board for the author's apartment.
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.
Robotic arm designed with Claude Code
Claude Code wrote the FreeCAD Python geometry for a 5-DOF servo arm, which later gained voice and camera control.
Codex returned a complete, classified list of missed email threads where Claude missed many; it also deployed a vacation site researched from hotel availability.
Codex email audit and trip site
Codex, driven by two authors, audited a month of missed emails, built a vacation planning site from a phone, and shopped for a dishwasher.
Hotel comparison, four tax PDFs, and an 18-item cart under $80 worked. Subscription cancellation failed.
Chrome auto browse five-task test
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.
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.
Indie platformer from scratch
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.
Opus found no tear where the doctor reported a Grade III partial-thickness tear. The author is unsure which reading to trust.
MRI second opinion
Claude Code with Opus 4.8 read a DICOM shoulder MRI export, then ran a subagent-based arbitration against the human radiology report.
Codex sorted 240 dinner recipes down to 62 family-fit picks, rated them, and produced an index, a spreadsheet, and a Google Drive folder.
Comms tasks with Codex
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.
No feats match this filter. Show all.
Proof marks:Shown artifact linked·Numbers a specific number stated·Claim claim only