Use a background agent with inbox-style approvals
They used a desktop app to run agents in the background and review results later in separate inboxes for finished work and decisions.
Agent Uses · 1,321 real examples
Real examples of people putting Custom agent to work: the task, how it went, what to watch out for, and a prompt you can adapt.
The day's AI news plus 3 agent uses you can try, with ready-to-paste prompts. Free; unsubscribe anytime.
They used a desktop app to run agents in the background and review results later in separate inboxes for finished work and decisions.
Manuel Schipper uses separate tmux panes and numbered Markdown specs to keep several coding agents moving at once.
A Chrome extension read Gmail and pulled action items from emails, invites, and follow-ups into a prioritized list.
Terence Tao used a coding agent to port old Java applets to JavaScript and to build two new math visualizations in conversation.
A mosaic-style canvas can automate video edits, generate variations, and then hand off to a timeline for manual tweaks.
Coverage Cat lets a personal agent collect details, size umbrella protection, and surface carrier quotes through its API and MCP setup.
A Raspberry Pi in a car used a local model to answer manual questions and read live diagnostics, while some vehicle controls ran through Home Assistant.
Have an agent total the landed cost, test coupons, and check buyer feedback before it reaches checkout.
A team used a voice agent for after-hours support, FAQs, and order-status checks, then pushed structured call details into their internal tools.
They used a LangGraph agent to test CUDA kernel tweaks, verify results, and profile candidates with Nsight.
They split a SQLite implementation across several coding agents working in separate branches, then merged the pieces after repeated test-and-fix loops.
An AP workflow checks incoming supplier bills against past records so a person can review problems before approval.
A desktop agent connected to a mainframe to read COBOL, submit jobs, and summarize failures from spool output.
Andon Labs used a persistent agent to operate real businesses with company tools and oversight.
A Rhino plugin let a coding agent turn a brief into editable geometry logic stored alongside the project files.
A developer had a custom agent scan public discussions and review pages, then turn the findings into a cited competitor brief and outreach plan.
A small-firm owner used an email agent to follow up on unpaid invoices and missing paperwork until there was a clear answer or payment.
A student used an AI agent to work through online class tasks inside Canvas or Blackboard while they did other things.
An in-Canvas agent helps instructors rename modules, update due dates in bulk, and rebuild pages from simple requests.
A multifamily broker uses AI to gather comps, draft property writeups, and flag missing details before outreach and early diligence.
An agent can revise .docx files by editing HTML first, then translating the result back into Word’s file format.
A landlord used AI to answer common renter questions, collect maintenance details, and draft paperwork, while a person handled exceptions.
Cardboard can assemble an editable cut from footage and a plain-language brief, then let you fine-tune the result in chat or on the timeline.
Create a multi-step system that assigns issues, tests changes, and leaves the final merge to a person.