Software & DevOps AI agent use cases
198 real things people got AI agents to do in Software & DevOps, each with what they asked, how it went, and the prompt to copy.
Add a third-party API integration via Devin PR
Devin opened a PR with the endpoint and backend wiring that was merged, but missed API key logic, code style and abstraction, needing review fixes.
Add agentic forgetting to an agent's memory
Someone implemented a rudimentary version of Tim Kellogg's agentic forgetting approach and reports it works impressively even in its simplest form.
Assign website tweaks to Copilot coding agent
An author gave the Copilot coding agent two small changes on their own site; it opened draft PRs and the spacing change was good enough to merge.
Attempt to build a navigation app (did not finish)
A poster tried to build a navigation app with Manus but spent a month of credits and over 8 hours without a working app.
Audit a codebase for redundant dependencies and polyfills
An MCP server lets an agent check a codebase for redundant dependencies and polyfills, usable remotely or as a local stdio server.
Audit a feature's issues and hand them to an engineer's agent
An AI agent listed all issues with a feature and sent them to an engineer, whose own agent then addressed most of them automatically.
Audit hundreds of pull requests with a terminal coding agent
In an independent test, Muse Code audited 222 pull requests in under five minutes for about ten cents, but also built a plan on a Google project that doesn't exist.
Auto-generate a searchable help video library for an app
Used Replit Agent to build a /help page that generates tutorial videos via scenes, Playwright recording, TTS narration and ffmpeg stitching.
Auto-open fix PRs from Sentry and log alerts
A Grok Bot called Sentinel monitors Sentry and logs and opens PRs on several repositories when triggers fire; still very early.
Automate web configuration from coding sessions
Commenters use Claude in Chrome to carry out web configuration requests that arise from coding sessions and other browser operations.
Autonomously test an entire iOS app and report bugs
A tool lets Claude Code drive an iOS app through the accessibility tree, tap every screen, and return a structured bug summary.
Build a bare-bones Windows VNC client from an email brief with Claude
The author emailed Claude a spec for a minimal VNC viewer targeting Windows 10 over a local SSH tunnel, to be built on a Mac and delivered with a checksum.
Build a book donation app and demo video in a buildathon
A user used Replit Agent to build the GiveABook app and its demo video within a 24-hour buildathon.
Build a booking and payment app for tattoo artists
A former programmer used Replit Agent over a weekend to build a booking app with calendar, Google OAuth, Stripe deposits and notifications, though time zones and UI needed back-and-forth.
Build a budgeting app from a single prompt
A low-coder used Replit Agent to build a 'Budget Buddy' with category budgets, a spending dashboard and expense log in about 20 minutes, using half their monthly credits.
Build a C compiler with a team of parallel agents with Claude
Anthropic's engineering write-up on tasking Opus 4.6 agent teams with building a C compiler.
Build a Chrome extension for presenting webinars
A Replit forum user built a Chrome extension so they could keep notes in view while presenting webinars, and published it to the Chrome Web Store.
Build a clinic app with booking and trackers
A doctor with no coding experience used Replit to build a clinic app in 5 days with booking integration, prescription requests, health trackers and an AI symptom checker.
Build a deals page step by step with Devin
An engineer had Devin implement a deals page in steps; it opened a PR in under 10 minutes, but CI failed, it added unnecessary changes and gave a false answer about a library.
Build a dramatic digital envelope app for asking friends for money
Used Replit Agent and Design Mode to build an app with decoy messages, drum rolls and live status tracking for a buildathon.
Build a first real project with Replit Agent
A student completed a real build with Replit Agent, spending about $65 in agent usage and finding the cost unexpected.
Build a full CRM with email, video and calendar
A community member used Replit Agent over a couple of weeks to build a CRM with email integration, video sales letter recording and meeting scheduling.
Build a full web app with database, storage and landing page
The author used Replit Agent to build a Postgres-backed web app with image storage, analytics and a landing page; an S3 switch failed and was reverted.
Build a homepage from Figma designs via MCP
The author connected Figma to Cursor over MCP to build a new homepage for a font archive, with great results after Lovable disappointed.
Build a mental models framework with a multi-agent dev team with Claude
A solo founder used Claude, ChatGPT, Windsurf and Cursor as role-based team members to design, test and deploy a 120-model mental-models framework and MCP server.
Build a mobile app turning photos and voice into reminders
The poster built Loopi, an app that turns photos, text and voice into reminders, notes and expenses, in about 45 days using Replit and AI agents.
Build a multi-tenant SaaS with an agent
The poster built a production multi-tenant SaaS in 15 days with Replit Agent, but hit issues like RLS bypasses and production pointing at the dev database, so checking its work was essential.
Build a multilingual typing app for language learning
A buildathon participant used Replit Agent for the first time to create LingoType, a typing app for mastering new languages.
Build a name-and-face quiz site from a spreadsheet
Scott Wu had Devin build and deploy a mobile-friendly React quiz from a TSV of speaker names and photos, plus a QR-code site to share it.
Build a phone voice agent that answers in under half a second
A from-scratch voice agent averaging about 400ms end to end, with streaming speech-to-text, LLM, and text-to-speech and clean barge-ins.
Build a Pokemon-style dog collecting app
A user had Replit Agent build a catch-em-all dog app whose rarity comes from scraped American Kennel Club regional population data.
Build a Pong game and website from scratch
A tester asked Devin to create a basic Pong-style game and a website, and it finished both in under 20 minutes.
Build a project management tool with a 24-hour agent run
Ran a Cursor agent continuously for 24 hours to build a project management tool; the app fully works but is not production ready.
Build a searchable map of funded companies
A software engineer had Replit Agent build a searchable map of Wefunder brick-and-mortar companies in about 3 hours for about $22.
Build a WordPress marketing site from Figma overnight
bnistordev connected Devin to a Figma file via MCP and had it build an entire WordPress marketing site overnight.
Build a working coding agent in R from three tools
Author builds a functional coding agent in R starting from three tools, then adds tools to make it safer and more efficient.
Build an AI to-do list web app in 9 hours with Replit Agent
The poster used Replit Agent V2 to build a fully functional AI to-do list web app in about nine hours.
Build an email inbox app for the bot's address
Grok Bot built and deployed a mail-style inbox app on Vercel in 23 minutes, with database and sync, and sent back the link and password.
Build an iCloud skill with a Muse agent
A screen-reader user asked their Muse agent to build an iCloud skill and it produced something, but accessibility problems with the text field and conversation navigation got in the way.
Build an invitation card website purely by prompting
A user built a frontend-only invitation site with animations, images and navigation for his girlfriend, giving instructions to Cursor without touching the code.
Build and deploy a Game of Life simulation site
In a vendor launch demo, Devin built an interactive Game of Life website, added requested features step by step, and deployed it to Netlify.
Build and deploy a Hacker News scraper app
Replit Agent generated a scraper, database models, API endpoints and front end that stores and shows Hacker News items, then deployed it.
Build and deploy a meeting app from a prompt
A user had Replit Agent create a meeting app with dashboard, logic and analytics, and deploy it live without manual code changes.
Build and deploy an app over a weekend
The author had Devin build and deploy an app, finding it quick on PR feedback but weak on legacy monorepos and costly on broad requests.
Build and launch a code-snippet sharing app
The poster built the Snippra app with Replit Agent, which handled UI copy, feature planning, debugging and naming while they guided it.
Build and publish a BaZi chart reading agent
Built solo with coding agents, an agent computes BaZi charts, interprets them, detects language and takes on-chain payments for readings.
Build and ship a micro-SaaS in three hours
A developer used paid Replit to build and deploy a micro-SaaS to production in about 3 hours, with database, domain, hosting and monitoring handled.
Build and submit a family quest app to the App Store
A user built Kogoto Quest, which turns family reminders into quests, with Replit Agent and submitted it for App Store review.
Build and test a simple endpoint project with Devin
A reviewer had Devin set up a project, write code, install dependencies, test endpoints and add error handling in about 4 minutes on a simple task.
Build apps, debug repos and set up CI/CD with Devin
A review lists Devin building a full-stack to-do app, debugging a public repo with a PR, and doing Docker setup, deployment and CI/CD.
Build custom real estate tools for offers and deal tracking
A rental owner used Codex to build tools for formulating offer prices, building property analysis reports with field photos, and tracking transactions under contract.
Build old and new apps with coding agents
Terence Tao describes using modern coding agents to create or revive apps, based on the post title.
Build SQLite with a swarm of parallel coding agents
The author recounts using parallel coding agents to build a SQLite implementation and shares experience from it.
Catch cloud outage risks before they happen
An autonomous ReAct agent that queries real data to stop cloud outages before they occur, built for the Sanity Challenge.
Catch intent conflicts between parallel coding agents
Agents publish planned changes before editing so conflicting architecture changes across parallel worktrees get flagged before code is written.
Click through apps to verify its own work
With computer use, Devin built and played a desktop game, ordered on Amazon, and tested its own work by clicking through the app.
Click through macOS app builds to catch visual bugs
A developer used Claude Code computer use to compile, launch, and click through macOS app screens to find layout bugs.
Code from your phone
A write-up on a setup for using Claude Code on the go.
Code in the terminal with an agent
The poster uses Grok as a terminal coding agent that reads, edits, runs tools and spawns sub-agents.
Code with Manus and auto-deploy via GitHub and Vercel
A G2 reviewer uses Manus mostly for coding, pushing code to GitHub, which is linked to Vercel so work goes live on their website.
Configure a local AI lab and build a knowledge graph by chat
Users had Hermes Agent set up a local AI stack (liteLLM, Postgres, Prometheus, Grafana) and install Gbrain as an MCP server to build a personal knowledge graph.
Configure macOS and dev tooling from the terminal
Gemini CLI ran defaults write commands to set Dock auto-hide, and was also used to install Docker and configure Git GPG signing.
Control a browser to fill forms and debug sites
A tutorial describes Scout opening sites, filling forms, clicking, uploading files, extracting page info, and reading console logs and network requests.
Convert React MUI components to Tailwind with Devin
Lumos used Devin for routine tasks like MUI-to-Tailwind conversion, which went well, and its unit-test feedback loop reduced rewrites.
Coordinate sub-agents to monitor PRs and fix prod bugs
A Cursor Projects coordinator agent delegates to sub-agents, watches new PRs and production bugs, spins up agents to fix issues, and surfaces questions to the user.
Crawl documentation into clean Markdown for AI agents
The author built a documentation crawler for their AI agents that pulled 60 pages of clean Markdown in 49 seconds.
Create accounts, buy domains, and deploy without a human
Cloudflare's announcement that agents can now create Cloudflare accounts, buy domains, and deploy.
Create and read issues from Claude Code via a Tangled MCP server
The author started building an MCP server so Claude Code can create and read issues on Tangled.
Debug code hands-free by voice with Claude Code
Author built a local speech-to-text and text-to-speech stack hooked to Claude Code via MCP, and used it to debug a WhatsApp integration hands-free while brushing teeth.
Debug frontend UI bugs with a browser agent with Claude in Chrome
A frontend developer pairs Claude in Chrome with Claude Code to open the app, click through it, read the DOM, check console errors and network requests, and fix UI bugs.
Debug overnight with a long-running agent
The author leaves Codex CLI running for hours to add debug prints and test hypotheses against a reproducing unit test, often only to find the bug.
Debug prod pods and docker-compose with Cursor
A DevOps engineer uses Cursor with a Kubernetes MCP to pull prod logs and suggest fixes, and to repair a broken docker-compose file.
Debug Windows crash dumps with an AI agent via MCP
ForensicDbg is a post-mortem debugger for native Windows x64/x86 crashes with an MCP server so AI agents can debug from interpreted, interlinked crash data.
Delegate web research from Claude Code to Comet
An MCP server lets Claude Code hand web navigation, login-walled pages and research to Comet while it keeps coding, then returns results.
Deliver a software feature autonomously (partial)
Claude computer use produced 70 files for a planned feature but the code didn't work, so the author went back to manual work.
Diagnose a killed process on a server with Codex
Codex CLI over SSH found the OOM killer in kernel logs on a 2 GB droplet with no swap and listed fixes by risk without changing anything.
Diagnose and roll back bad config during outages
Google SREs use Gemini CLI to pull logs, find a bad config push, generate a reverting changelist, and file postmortem action items via MCP.
Diagnose Kubernetes alerts with MCP servers
An n8n agent triggered by Alertmanager queries Kubernetes, Grafana and other MCP servers and posts a diagnostic report with root-cause hypotheses in a Mattermost thread.
Diagnose Swift errors with ChatGPT from symptoms and code with ChatGPT
A Swift developer feeds error symptoms and code to ChatGPT to get a starting lead on the cause, then reviews the code it produces.
Draft pull request reviews for you to edit and send
The poster built a review inbox where Claude Code drafts reviews for piled-up PRs and the user can discuss, rewrite or delete findings before sending.
Edit site design visually and have an agent write the code
CSS Studio lets designers tweak a site visually in the browser and streams the changes via MCP to an existing coding agent that implements them in the codebase.
Find and fix flaky tests in a broken CI pipeline overnight
Claude monitors CI pass rates, identifies worst flaky tests, reproduces them and proposes fixes overnight; pipeline got 20 minutes faster and pass rate rose 35%, with some bad fixes discarded.
Find code faster with a local search agent
A small local agent navigates ColGrep multivector code search and reads files to find things quicker and cheaper, and can be plugged into Claude Code.
Fix a broken API website
A user says Claude Cowork fixed their API website after another agent kept breaking it, explaining the problem and working through changes with them.
Fix a broken Delete button in a GitHub repo
The author had Jules clone a repo and fix a Delete button so it disables deletion of content older than two hours, with tests added unprompted; the author reviewed and published the branch.
Fix a production boolean-flag bug with Devin
A reviewer had Devin fix a bug on a production site; it returned a PR in about ten minutes but included unrelated changes like removing a safeguard check.
Fix and resubmit a rejected app remotely
MaakCode had a dot investigate a rejected app submission, fix the issue, test, open a PR and resubmit.
Fix app bugs, harden security and ship fixes autonomously
Omar used Hermes Agent to fix priority bugs in his health app while at work, isolate browser logins, design an infographic banner, and ship production fixes with verified health checks.
Flag documentation drift from merged PRs weekly
A weekly Hermes cron job checks merged PRs for changes to tool schemas, CLI commands, config options or env variables to flag docs needing updates.
Generate internal dashboards and data migration scripts
A backend engineer says their team uses Devin for internal dashboards and migration scripts, treating output as a starting point that saves about four hours of boilerplate.
Get Microsoft Office running on Linux via Wine
Claude Code did most of the work to make desktop Office 365 run under Wine on Linux without virtualization, packaged as a Nix flake.
Give coding agents compiler-accurate Find Usages for C#
Graphify C# lets coding agents find symbol usages in C# codebases with compiler-level accuracy.
Give coding agents git-native persistent memory
A tool that stores persistent memory for AI coding agents in git so context carries across sessions.
Hand narrow code changes to Devin for pull requests
A team used Devin for a month on small fixes like chart formatting and API edge cases, with tests and PRs; a complex full-stack task went poorly.
Hand off coding sessions between agent accounts at usage limits
A developer built an app that tracks usage across multiple Codex and Claude Code accounts and auto-hands-off conversations when one hits its limit.
Have Copilot coding agent write and push code
A developer found the agent good at context and code, but it pushed to a branch leaving main empty and spent hours checking after being told to proceed.
Investigate broken builds and merge fixes
OpenAI's internal OpenClaw agent Androidclaw uses Git, GitHub and logs to investigate broken builds, trace problems to incidents, and sometimes prepare and merge fixes.
Iterate on tasks with Copilot CLI autopilot and fleet
The author used autopilot to iterate until done and /fleet to split work across parallel subagents, noting overhead on small tasks.
Keep coding agents running autonomously for long stretches
Cursor's write-up on scaling long-running autonomous coding.
Let a custom agent change its own repository
Author's custom-built agent made its first code change to its own repository.
Let an agent extend its own code inside a Docker sandbox with Claude
An agent built on Claude and Agno implements capabilities in its own source code in Docker, with changes validated, committed, or rolled back; it reached 21+ capabilities.
Let terminal agents make phone calls
A CLI tool built on Twilio gives terminal agents a voice to make calls, with a dashboard for questions they can't answer.
Lint, fix, commit and push code from the terminal
Scout runs a linter, fixes a syntax error, re-runs it, reviews staged changes, writes a commit message and pushes to a new branch, shown as a walkthrough.
Maintain a profitable Stripe-backed app with Replit
A commenter's Replit-built app reached about £20k in sales, and they use the agent to hunt duplications, organize code and add security like reCAPTCHA.
Manage Canvas courses in plain English
The author built a Canvas LMS tool with Claude Code that lets educators list courses, find missing submissions, monitor forums, schedule announcements and export the gradebook.
Manage NixOS server configs with Claude Code
The author uses Claude Code to maintain the NixOS config repo for their self-hosted machines, blocked from running nixos-rebuild switch and reviewing each change before applying it manually.
Migrate 180 microservices to a new framework version
Brex built Cursor-based self-correcting agents that let one engineer migrate 180 microservices to a newer Micronaut version in about a month.
Migrate a legacy product stack with Claude Code
An engineer ran a proof-of-concept that consolidated 4 repos into 2, moved MySQL to PostgreSQL, upgraded frameworks and replaced the auth model, in about 15 work days.
Migrate a password reset flow to modern libraries
A developer had Claude Code migrate a legacy web app's password reset flow; it needed close supervision, drifted off task, and ended up slower than doing it by hand.
Migrate a SaaS from AWS to DigitalOcean
A developer used Claude Code as a pair programmer for provisioning, database seeding, SSL, DNS cutover and production debugging, finishing in about four hours with zero downtime by his account.
Migrate an Electron app from Vue 2 to Vue 3
Kearney gave Devin repo access to migrate a production Electron app to Vue 3 and update npm packages, committing after every five components.
Migrate toolchain, architecture and site design with Claude Code
A developer had Claude Code switch a monorepo to oxlint/oxfmt, restructure the architecture and redesign a site, validating in a loop; the redesign took days instead of weeks.
Migrate WordPress posts to MDX
Claude Code pulled posts from the WordPress REST API and converted them to MDX with frontmatter, migrating 367 posts and 5 pages in one session.
Monitor tasks and open pull requests with long-running agents
A commenter runs a persistent script that watches tasks and uses Cursor to open pull requests, building a documentation summarizer and a data pipeline.
One-shot a CLI coding agent on top of a Python LLM library
Simon Willison had the Fable model more or less one-shot a CLI coding agent built on his LLM Python library.
Optimize CUDA kernels with agents that benchmark and profile
AI agents run a C++ CUDA test harness, get benchmarks, and profile with Nsight to optimize kernels, built with LangGraph.
Orchestrate a multi-phase RAG migration with Gemini
A walkthrough of using Gemini CLI to coordinate a complex, multi-phase cloud migration project.
Pair-program with LLMs on personal projects with Claude
The author uses Claude web and Jules (Gemini with GitHub integration) as pair-programming partners, navigating while coding locally and submitting back.
Patch annoying software behavior by pointing an agent at it
Author had an agent debug a Hyper-V vmconnect fullscreen bug with a hook system, and pointed Codex at the Codex app to add features.
Port a Chrome extension to Safari
The author had ChatGPT take the Session Buddy extension source from Chrome, port it to Safari and install it, taking about 20 minutes.
Port Claude Code hooks to pi extensions
After leaving Claude, the author pointed an agent at their Claude hooks folder and had it rebuild them as a pi extension, which it did quickly.
Port Claude Code skills to Codex
The author moved 201 Claude Code skills to Codex in an afternoon using a skill inside Claude Code, and reports what transferred and what broke.
Port the Copilot runtime to Rust agentically
Microsoft reportedly used agents to port its Copilot runtime to Rust for $120K, according to the headline.
Prototype product features as a non-coding PM
A founder used Cursor agents to find prototype gaps, draw ASCII wireframes, and plan and implement a feature with parallel agents in worktrees.
Queue maintenance and bug fixes for Cursor background agents
A developer authorized the GitHub app so Cursor background agents cloned repos into sandboxes, branched, and worked through a day's queue of maintenance, features and bug fixes.
Rebuild a platform and add RAG features in one day
A user had Replit Agent rebuild a full-stack platform, add 7 features to a live RAG app, and make a demo video in about 12 hours.
Recompile a 1991 assembly PC game with Claude Code
The author uses Claude Code CLI with Sonnet to get the source of their 1991 386+ assembly game compiling again.
Refactor a million-line repo with 1,393 subagents
A Nous Research developer had Hermes dispatch 1,393 subagents over about 19 hours to clean up its own repo, cutting non-test Python source by 34.4% in a merged PR.
Replace token-heavy Jira and GitLab MCPs with CLI skills
The author had Claude run --help on Atlassian and GitLab CLIs, saved the actions as Markdown, and built lightweight agent plugins that cut token use.
Resolve a Slack-reported issue with a coding agent
A Codex agent resolved an issue passed to it in about 40 minutes, and an ops agent verified the fix back in Slack.
Resolve git merge conflicts and push a fix
A tutorial shows Scout comparing both sides of merge conflicts, proposing a merged file for review, then committing and pushing to a branch.
Restyle a pull request to match repo house style
A developer asked Claude to update a PR to the repo's house style, but it only rewrote comments to be lowercase and less useful, making no code changes.
Reverse engineer legacy systems without source code
Thoughtworks consultants used Gemini 2.5 Pro in a two-week pilot to produce validated blueprints of legacy systems' functionality.
Review GitHub pull requests automatically
An n8n AI agent triggers on each new PR, fetches diffs, calls an LLM for a review, and posts comments and labels back on the PR.
Review GitHub pull requests for bugs and security
A Hermes tutorial reads a PR diff and returns a structured review of bugs, security and code quality, then turns it into a skill that watches repos and sends summaries.
Review Linux kernel patches
Google engineers launched Sashiko, an agentic AI code reviewer for the Linux kernel.
Rewrite a README after a rearchitecture
Devin scanned a rearchitected codebase and delivered a new README as a PR with accurate setup and API details, but struggled with design rationale and purpose.
Rewrite a runtime from TypeScript to Rust with agents
GitHub engineers used Copilot tools to have agents write most of an 800,000-line Rust rewrite of the Copilot runtime across 128 PRs, fixing a few regressions.
Route Linear tickets to PRs across multiple repos
A developer sends tasks via Telegram/OpenClaw into Linear, where Cyrus routes each to the right repo and model and opens PRs for review.
Run a coding agent on a live Excalidraw canvas
Drawgent is a coding agent that works on a live Excalidraw canvas.
Run a fleet of engineer bots that fix CI and ship PRs
A SpaceXAI engineer runs five specialized Grok bots that launch cloud agents, fix failing CI and security issues, trigger reviews, and ship PRs overnight, handling over 200 agents at once.
Run a multi-bot team that opens draft PRs
A Grok setup of research, classifier, builder, tester, reviewer, and security bots maps repos, makes minimal changes, runs tests and lint, and opens draft PRs; the author reports over 1,000 PRs.
Run a self-hosted, sandboxed software factory with Codex
One developer's build log of an almost fully self-hosted, sandboxed agentic pipeline for producing software.
Run agents that work Jira tickets, review PRs and send updates
Luke runs several Hermes agents that read Jira tickets, write code, review PRs, track costs, summarize docs and send updates.
Run an AI software factory that opens, reviews, and merges PRs
A guide to building agents that open, review, and merge pull requests.
Run builds, tests and PR creation with shell commands
A guide shows Scout running build, test, lint and gh commands, listing or creating PRs, and handing diff reviews and test runs to background sub-agents.
Run coding agents like a medical team to fix bugs
Over five months, the author treated bugs like patients and organized coding agents as a hospital-style team to diagnose and fix them.
Run multi-stage PR reviews with parallel sub-agents
A Claude Code plugin that reviews pull requests in stages with sub-agents and validation passes, with optional ensemble review via Codex.
Run OpenClaw agents for Terraform infra and GitOps from Telegram
Several OpenClaw agents with separate identities set up Terraform infrastructure, did coding work, code reviews, merges and built a CD and GitOps system.
Run parallel coding agents from Markdown specs in tmux
A workflow post on running multiple coding agents in parallel using tmux and Markdown specs, based on the title.
Run parallel local coding agent sessions
A developer runs up to 10 coding agent sessions at once, using Claude Code and local models on RTX 3090s with cached contexts for daily development work.
Run production deploys and port scans from Telegram with OpenClaw
A security professional uses an OpenClaw agent with read-only prod access, PR-only changes and manual approval for restarts to deploy changes and scan a VPS for exposed ports.
Run sandboxed Claude Code fleet sharing files via MCP
A developer runs a fleet of sandboxed Claude Code instances that share files through MCP tools on a virtual filesystem, with an orchestrator handling AWS storage and audit logs.
Run terminal commands with Copilot agent mode
Users report the agent sometimes fails to read terminal output and may undo correct code; workarounds include switching shells.
Run Terraform plan and apply through an MCP agent
The author had Cursor run Terraform against Postgres via MCP; the apply hit a permissions error and he finished from the terminal.
Scaffold a new service end to end with agents
Cursor agents create Terraform, k8s manifests and CI, validate them and open a draft PR; one cleanup run wrongly deleted Terraform files.
Self-host services on a home server
A write-up on how CLI agents make running your own home server easier and more fun.
Set up weekly changelogs and fix docs from GitHub issues
Neon's docs team has Devin create the weekly changelog from a playbook and open or revise doc PRs from GitHub issues, for repetitive work only.
Shepherd PRs to merge automatically
Bots check PRs every 30 minutes, send failures back to a cloud agent, review clean PRs and auto-merge high-confidence, low-risk ones.
Ship a backlog landing page from a ticket spec
Cursor's background agent built a pricing landing page from a short spec in about 5 minutes on a new branch and opened a PR.
Ship a first iOS app to the App Store with Replit
The poster built their first app on Replit with ChatGPT help and got it approved on the App Store.
Ship a product in 72 hours with a bot team
Three SpaceX engineers used a Grok Bot team to go from an empty repo to a product with 433 PRs, with agents reproducing bugs and merging autonomously except for human gates on migrations and deploys.
Ship more pull requests with Devin across tools
Ryan Carson uses Devin from iPhone, Slack, browser, GitHub and Linear for real work and reports higher PR shipping velocity.
Spec features with AI and hand off to coding agent with ChatGPT
Author discusses a spec with an AI agent or ChatGPT, then hands it to an agent to code, and tests the outcome instead of reading every line.
Speed up Rust code by having agents iteratively optimize it
The post covers asking coding agents to make Rust code faster through repeated iteration.
Spend leftover AI quota on reviewable PRs
RemainderBot uses a founder's goals and task lists to write PRs with spare Claude and Codex quota, producing 111 PRs including call prep and prototypes.
Split a React Native to Swift migration across agents
Cognition's Jared Zoneraich uses Devin fan-out so child agents work in parallel on a migration split into six pieces.
Take ideas to implementation with a planning-command pipeline
A solo SaaS founder uses a custom five-command agent flow (intent, impact analysis, planning, execution, review) with lint guardrails to ship features in a production product.
Test API endpoints in Postman and report results
@ai_for_success used Comet to generate test payloads from context, run API endpoint tests in Postman and produce a final report.
Test Devin on integrations, migration and security review
Answer.AI tried Devin on an observability integration, an nbdev migration and a vulnerability review; it found some real issues, hallucinated others, and failed the migration.
Test Devin on pulling Notion data into Sheets
Answer.AI testers found Devin completed only 3 of 20 tasks, succeeding at moving Notion data to Google Sheets and building a planet tracker.
Test features on screen and merge fixed PRs
Ryan Carson uses Devin's Test App feature to record and narrate feature clicks, fix bugs, and merge PRs with a !land command.
Test how well coding agents can onboard to your product
ax-check.com runs coding agents in sandboxes to try onboarding to a product, then returns a scorecard, suggested fixes, and full session traces.
Test local web apps and fix errors in one session
Claude Code with Claude in Chrome writes code, opens localhost, clicks through the UI, reads console errors and fixes them without the developer touching the browser.
Triage failed GitHub Actions runs and self-heal flaky tests
A QA engineer's OpenClaw agent reads failed CI logs, classifies failures, posts analysis to GitHub and Slack and opens issues; flakiness fell from 8% to 0.8%, though it once wrongly altered an assertion.
Triage issues and open fix PRs with a GitHub bot
A cookbook shows a GitHub bot that triages issues, reviews PRs, answers questions with citations, flags AI-slop contributions, and opens patch PRs for human review.
Triage P2 bugs into draft PRs with demo videos
A Dot connected to GitHub and Slack watches #bugs, scopes and tests a fix in a cloud environment, and opens a draft PR with a short demo video.
Troubleshoot a production-only performance issue
A developer used Cursor and Warp agents to analyze NestJS database queries and recommend indexes for a production performance problem.
Turn customer feedback into tested pull requests
In OpenAI's own launch example, a Dot watches feedback for recurring requests, scopes small fixes, builds and tests them, and returns PRs with demo videos.
Turn daily X bookmarks into working tech prototypes
A bot scans a Cursor employee's X bookmarks daily, picks a new technology, drafts a prompt, and on approval starts a Cursor Cloud agent to build a prototype in about 15 minutes.
Turn one goal into an ordered plan of coding-agent tasks
Ordewell takes a single goal and breaks it into an ordered plan of tasks for coding agents.
Turn Slack and Linear tasks into PRs and fix CI
Cognition staff assign Devin work in Slack or Linear; it posts PRs, fixes bugs flagged by review bots and works CI and lint failures until checks pass.
Turn Slack feedback into PRs and debug infra
Sid Nanda's company uses Devin in Slack to triage feedback, turn user issues into PRs, debug async flows and infra read-only, and let non-technical staff coauthor PRs.
Turn tickets into merged pull requests with Claude Code
Pulls tasks from GitHub Issues or Linear, then runs Claude Code or Codex in isolated Kubernetes pods to carry each one through to a PR.
Turn tickets into merged pull requests with one-shot coding agents
Stripe describes its internal Minions coding agents that take tasks end to end into code changes; the post is a headline only.
Update a digital assets platform with Manus
Mufasa used Manus to review features, iterate on mockups, and generate code for a new AI automation sector in Genesis v2.0.
Update a docs page of AI CLI tools with Devin
A user had Devin update a page listing AI coding CLI tools; it opened a PR in 5 minutes, but a separate task needed much back-and-forth to find all files.
Update a legacy Telegram bot and refactor an app
The author used Replit Agent to update a Telegram bot to a newer API, which only worked after some iterations, and to refactor a card-collection app including a database schema change.
Upgrade site dependencies and frameworks with Cursor
Kent C. Dodds had Cursor's agent look up migration docs, plan and upgrade Remix v2 to React Router v7 and xstate in his site.
Use a bot as a QA intern on a live app
A Grok Bot clicked through an app's core flows several times a day, reported problems and drafted fix PRs; it found a real bug.
Vibe-code a pull request dashboard across Azure DevOps repos with ChatGPT
Author used ChatGPT for architecture and the Junie agent in WebStorm to build a dashboard aggregating PRs across four repos, flagging approvals, conflicts and comments, in about 3 hours.
Vibe-code and deploy an idle clicker game
Gilbert Pellegrom had his OpenClaw agent build a simple idle game from a conversation, commit it to GitHub and auto-deploy it to Vercel.
Work on mainframes and COBOL
Hopper is an agentic development environment for the mainframe systems behind banking, payments, insurance, and airlines.
Write a Linux kernel improvement with Claude Code
Linus Torvalds is working on a sizable Linux kernel patch written with Claude Code, per the headline.
Write and debug code across eight test tasks
A reviewer had Manus build a currency converter, fix a find_max bug and make a landing page, with mostly strong results.
Write better CSS with an MDN-aware helper
An MCP server that consults MDN docs, reports browser compatibility, and analyzes your CSS for the agent.
Write Playwright tests with Playwright MCP and Claude Code
A walkthrough of using Playwright MCP with Claude Code to generate Playwright tests in minutes.
Write, review and document code across a product's PRs
Founders report Devin touching all PRs at ChatPRD and being Gumroad's top contributor with over 1,500 merged PRs.