Use Manus to plan, mock up, and code a new feature area
Mufasa used Manus to inspect an older version of Genesis, test mockups for a new AI automation section, and generate code for v2.0.
Agent Uses · 1,321 real examples
Coding agents that build, review, test, migrate and ship software. Each entry shows what the person asked for, how it went, and a prompt to try it yourself.
The day's AI news plus 3 agent uses you can try, with ready-to-paste prompts. Free; unsubscribe anytime.
Mufasa used Manus to inspect an older version of Genesis, test mockups for a new AI automation section, and generate code for v2.0.
A developer used Replit Agent to launch a tenant-based SaaS in 15 days, then spent a lot of time checking for security and deployment mistakes.
Using Replit’s agent, a first-time mobile builder shipped Loopi, which converts images, typed input, and speech into reminders, notes, and expense records.
A developer used Replit Agent to make Snippra, letting it help with design, copy, planning, debugging, and naming while they directed the process.
A non-technical founder used Replit Agent to test code quality, remove duplication, and add protections to a Stripe app that had already sold about £20k.
Gemini CLI can change macOS settings and help install developer tools by showing each command for approval first.
A reviewer uses Manus to code, then send changes to GitHub so Vercel publishes them on their site.
A Dot monitors bug reports, tests a fix in the cloud, and opens a draft pull request with a short video for review.
A developer let Claude computer use implement a feature on its own, but the output broke and they abandoned the branch.
A developer had a dot track down a build crash, patch the app, test it, and resubmit it from a remote conversation.
teivz built a local app that watches Codex and Claude Code account usage and shifts a chat to another account when one reaches its cap.
Claude Code inspected a working app, generated a Playwright test, and fixed a locator conflict before a person checked the result.
A developer used Claude Code to bring a pull request in line with a repo’s style, but it only altered comments and left the code unchanged.
A developer used Claude Code to update a reset feature, but the review work and cleanup erased most of the speed gains.
A developer uses Claude Code to edit one NixOS config repo for several self-hosted machines, then reviews the diff and applies changes by hand.
They pointed a coding agent at two annoying software behaviors and had it debug one and add a self-improvement feature to the other.
They chained six Grok bots to map issues, make small code edits, test them, review the diff, and open draft pull requests.
Grok Bot can set up and publish a mailbox app for a bot address, then return the live link and password.
A developer added a basic forgetting layer to an agent’s memory and said it worked extremely well right away.
One developer had an agent inspect a feature for problems, then handed the issue list to an engineer whose agent fixed most of them.
They used a custom crawler so Claude could save a 60-page docs site as Markdown without crowding the chat.
A SpaceXAI engineer used five Grok bots to watch for breakage, dispatch fixers, and leave ready-to-review pull requests by morning.
They paired with Claude and Jules while coding locally, then copied changes back and forth instead of sharing a live editor.
Use an agent to sort Slack feedback, draft fixes as PRs, and help debug infrastructure with read-only access.