# Machine

> The AI command center for your company. Every agent, skill, and memory is a file in one versioned repo you own — a workforce of AI agents that does real work, shared across your whole team from Slack, Teams, the web, or the CLI. Any model, your keys.

Canonical site: https://themachine.myapps.ai
Full corpus: https://themachine.myapps.ai/llms-full.txt
Structured content index: https://themachine.myapps.ai/api/ai

## Core pages
- [Machine – The AI Command Center for Your Company](https://themachine.myapps.ai/markdown/index.md): The AI command center for your company. Every agent, skill, and memory is a file in one versioned repo you own — a workforce of AI agents that does real work, shared across your whole team from Slack, Teams, the web, or the CLI. Any model, your keys.
- [About Machine](https://themachine.myapps.ai/markdown/about.md): We build self-driving companies. Humans verify, steer, and govern while agent teams do work across engineering, product, operations, finance, support, and growth.
- [Machine for developers](https://themachine.myapps.ai/markdown/developers.md): Build with Machine from the terminal: drive projects, sessions, and agents through the CLI and SDK, wire triggers and connectors, and land every change through a reviewed change request.
- [Machine Enterprise](https://themachine.myapps.ai/markdown/enterprise.md): Scale, security, and your deployment.
- [Machine pricing](https://themachine.myapps.ai/markdown/pricing.md): Current plans and included features.
- [Machine Agent Computer](https://themachine.myapps.ai/markdown/agent-computer.md): Every Machine session gets its own computer: an isolated Linux machine that clones your repo, cuts a branch named after the session, and runs OpenCode. Work lands through a change request a person approves.
- [Machine Agents & Skills](https://themachine.myapps.ai/markdown/agents-and-skills.md): A Machine agent is a markdown persona with a deny-by-default reach into connectors, secrets and skills. A skill is the markdown that encodes how your company does one job. Both are files in your repo, versioned and reviewed.
- [Machine Automations](https://themachine.myapps.ai/markdown/automations.md): Cron schedules and signed webhooks start Machine sessions with nobody present. Each trigger names the agent it runs as, carries a prompt template, and lands its work through a change request a person approves.
- [Machine Channels](https://themachine.myapps.ai/markdown/channels.md): Connect Slack or Microsoft Teams to a Machine project and a message in a thread starts a session. The agent works on its own cloud computer and replies in the same thread. Email and voice are in preview.
- [Company as Code](https://themachine.myapps.ai/markdown/company-as-code.md): A Machine project is a git repo, and that repo is the company. One project config and the OpenCode config define it; agents, skills and memory are files beside your code. Every change is a commit a person approves.
- [Machine connectors](https://themachine.myapps.ai/markdown/connectors.md): Connect 3,000+ apps, MCP servers, OpenAPI, GraphQL and raw HTTP once for the whole company. Agents reach them through one scoped token — credentials stay server-side, every action is allowed, gated, or blocked, and every call is logged.
- [Machine Security](https://themachine.myapps.ai/markdown/security.md): How Machine is built to survive a security review: an isolated machine per session, connector credentials brokered server-side that never enter that machine, permissions for people and agents, human approval gates, and a change request between an agent and main.
- [Machine Solutions by role](https://themachine.myapps.ai/markdown/solutions.md): One platform, eight teams with completely different work. What sales, marketing, product, engineering, finance, people, IT and data science can each hand off — and what comes back.
- [Machine for sales teams](https://themachine.myapps.ai/markdown/solutions/sales.md): Give a sales agent the research, the pre-call brief, the CRM updates and the follow-up draft. Nothing sends until you approve it, and every action it takes is written down.
- [Machine for marketing teams](https://themachine.myapps.ai/markdown/solutions/marketing.md): Your voice, your approved claims and your banned words live in the repo as a skill file every session reads first. Marketing work lands as a draft in a change request, so review is a diff.
- [Machine for product teams](https://themachine.myapps.ai/markdown/solutions/product.md): Turn scattered feedback into a spec with the evidence attached, keep the tracker honest, and write release notes from the actual diff. Everything lands as a document a person reviews.
- [Machine for engineering teams](https://themachine.myapps.ai/markdown/solutions/engineering.md): Every Machine session gets its own cloud computer and its own branch. The agent reproduces the bug, writes the patch, runs the tests and opens a change request. Merge is default-deny for agents.
- [Machine for finance teams](https://themachine.myapps.ai/markdown/solutions/finance.md): Reconciliation, variance analysis and the schedules behind the close, run on a machine that shows its working. Every figure traces to a source, and posting to a system of record can wait for your approval.
- [Machine for people and recruiting teams](https://themachine.myapps.ai/markdown/solutions/people.md): Interview kits, scheduling, onboarding runs and policy answers from your own handbook. Machine handles the coordination. A person makes every decision about a person.
- [Machine for IT teams](https://themachine.myapps.ai/markdown/solutions/it.md): Access reviews, joiner-mover-leaver runs and service desk triage, run as sessions on isolated machines. Plus the straight answers IT needs before approving an agent platform at all.
- [Machine for data science teams](https://themachine.myapps.ai/markdown/solutions/data-science.md): Every Machine session is a real Linux machine, so an analysis agent can install a package, run the query and commit the notebook. The analysis lands in the repo as a change request, so anyone can re-run it.

## Documentation
- [Accounts & tokens](https://themachine.myapps.ai/markdown/docs/accounts.md): An account holds your projects, your teammates, and your billing.
- [Machine as a Backend](https://themachine.myapps.ai/markdown/docs/backend.md): Start and manage Machine sessions from your backend with explicit connector, model, context, and secret scope.
- [CLI](https://themachine.myapps.ai/markdown/docs/cli.md): The machine command line, its auth model, the dev loop, and every command.
- [Approval rules](https://themachine.myapps.ai/markdown/docs/code/approval-rules.md): Decide which agent actions go ahead on their own and which wait for your OK.
- [Automations](https://themachine.myapps.ai/markdown/docs/code/automations.md): Put agents on a timer, start them from a webhook, run them in Machine Cloud on a schedule, and resume work after a usage limit.
- [Browser and design mode](https://themachine.myapps.ai/markdown/docs/code/browser.md): Preview your app in the built-in browser, point the agent at elements with design mode, choose where links open, and snap your screen into a chat.
- [The machine-ide command](https://themachine.myapps.ai/markdown/docs/code/cli.md): Start, follow, and script Machine Code agents from your terminal.
- [Code editor](https://themachine.myapps.ai/markdown/docs/code/code-editor.md): Edit code yourself in Machine Code, with language smarts, project search, and inline AI.
- [Connectors, tasks, and your project](https://themachine.myapps.ai/markdown/docs/code/connectors-and-project.md): Use the apps you connected in Machine from Machine Code, turn issues into tasks, and manage your Machine project's secrets, models, and agents.
- [Your first task](https://themachine.myapps.ai/markdown/docs/code/first-task.md): Add a project, start a task, choose where it runs, and follow the agent while it works.
- [Machine Code](https://themachine.myapps.ai/markdown/docs/code.md): The desktop app for building software with Machine agents, on your own computer or in Machine Cloud. Start here if you are new.
- [Install Machine Code](https://themachine.myapps.ai/markdown/docs/code/install.md): What you need, how to download and install Machine Code on Windows or Mac, how to sign in, and how updates work.
- [Machine Cloud](https://themachine.myapps.ai/markdown/docs/code/machine-cloud.md): Run agents in Machine Cloud sandboxes from Machine Code, follow them from the app, and move work between your computer and the cloud.
- [Models and engines](https://themachine.myapps.ai/markdown/docs/code/models.md): Which models Machine Code can use, who pays for each, the engine setting, your own Claude, ChatGPT or Cursor plan, comparing models, and the Usage view.
- [Remote computers](https://themachine.myapps.ai/markdown/docs/code/remote-computers.md): Run Machine Code agents on another computer you reach over SSH, like a build server or a dev box.
- [Review and ship](https://themachine.myapps.ai/markdown/docs/code/review-and-ship.md): Read an agent's changes, get a second review, commit, open a pull request, and let Machine Code watch it until it's green.
- [Keyboard shortcuts](https://themachine.myapps.ai/markdown/docs/code/shortcuts.md): The Machine Code keyboard shortcuts you'll use most.
- [Troubleshooting and FAQ](https://themachine.myapps.ai/markdown/docs/code/troubleshooting.md): Fixes for common Machine Code problems, where it keeps its files, and answers to common questions.
- [Working with agents](https://themachine.myapps.ai/markdown/docs/code/working-with-agents.md): Side chats, goals, the Running view, chat details, background work, and the command center.
- [Computer Tunnel](https://themachine.myapps.ai/markdown/docs/connect/computers.md): Connect your machine through the permissioned Machine Agent Tunnel.
- [Connectors](https://themachine.myapps.ai/markdown/docs/connect/connectors.md): How connectors and connections give agents scoped access to external tools.
- [Glyph: live voice](https://themachine.myapps.ai/markdown/docs/connect/glyph.md): Talk with your agent out loud from any session, through your own Glyph account. The whole call lands in the session when you hang up.
- [Connect & automate](https://themachine.myapps.ai/markdown/docs/connect.md): Connectors, channels, computers, and triggers reach outside a project.
- [Inkbox: iMessage, SMS, email & calls](https://themachine.myapps.ai/markdown/docs/connect/inkbox.md): Text, email, or call your agent. It does the work and replies the same way.
- [Pixio: images, video & audio](https://themachine.myapps.ai/markdown/docs/connect/pixio.md): Let your agents make images, video, music, and voice with your own Pixio account.
- [Slack & channels](https://themachine.myapps.ai/markdown/docs/connect/slack.md): Connect Slack to a project and control sessions from a channel.
- [Triggers](https://themachine.myapps.ai/markdown/docs/connect/triggers.md): A trigger starts a session on a schedule, from a webhook, or from a monitor.
- [Create an automation](https://themachine.myapps.ai/markdown/docs/desktop/automations/create.md): Schedule a bot to do a job, once or on repeat. Quick create on the calendar, the full editor, every repeat option, and how to write instructions that work unattended.
- [Manage automations](https://themachine.myapps.ai/markdown/docs/desktop/automations/manage.md): Run, edit, pause, move, and delete automations, read run logs, and find the results of each run.
- [Automations](https://themachine.myapps.ai/markdown/docs/desktop/automations/overview.md): Have a bot do work on a schedule, in the cloud, even when your computer is off. What automations are good for, where to find them, and how the page is laid out.
- [Archive or remove a bot](https://themachine.myapps.ai/markdown/docs/desktop/bots/archive-and-remove.md): The difference between archiving a bot (reversible, only hides it in your app) and removing it from Machine (permanent, everywhere), and how to do each.
- [Bot settings](https://themachine.myapps.ai/markdown/docs/desktop/bots/bot-settings.md): The bot's profile card, every section of a bot's settings, what each one controls, and which settings follow you to your other devices.
- [Create a bot](https://themachine.myapps.ai/markdown/docs/desktop/bots/create-a-bot.md): Make a new bot from a ready-made role or from scratch, decide between a new bot and a new thread, and copy an existing bot.
- [Group chats](https://themachine.myapps.ai/markdown/docs/desktop/bots/group-chats.md): Put several bots in one conversation, decide who answers, use @mentions and hand-offs, write group instructions, and use group chats on all your devices.
- [Marketplace](https://themachine.myapps.ai/markdown/docs/desktop/bots/marketplace.md): Browse skills and project templates, add one to a bot or start a new bot from it, and switch on more marketplaces.
- [Bot recipes](https://themachine.myapps.ai/markdown/docs/desktop/bots/recipes.md): Add a ready-made team of bots, with their roles, skills, and group chats, in one click. Find, preview, import, and switch on a recipe, or share your own team as one.
- [Responsibilities](https://themachine.myapps.ai/markdown/docs/desktop/bots/responsibilities.md): Give a bot goals it looks after without being asked, with an optional daily or weekly check-in, and see its routines and webhooks in one place.
- [The sidebar](https://themachine.myapps.ai/markdown/docs/desktop/bots/sidebar.md): Everything in the sidebar, what the status dots mean, the Needs you inbox, the bot menu, teams, and how to keep it tidy.
- [Skills and memory](https://themachine.myapps.ai/markdown/docs/desktop/bots/skills-and-memory.md): Skills give a bot extra know-how for specific tasks; memory lets it remember things. Review and turn skills on and off, have a bot draft new skills, and read or edit a bot's memory.
- [Write a bot's Soul](https://themachine.myapps.ai/markdown/docs/desktop/bots/soul.md): The Soul is a bot's standing instructions. Learn what to put in it, see examples for common roles, and let the bot write its own.
- [Threads and folders](https://themachine.myapps.ai/markdown/docs/desktop/bots/threads-and-folders.md): Start, find, rename, link, and delete threads, and group a bot's threads into folders.
- [Today](https://themachine.myapps.ai/markdown/docs/desktop/bots/today.md): One page that answers "what's going on?" Ask a bot for your brief, answer everything that needs you, and see who's working, what runs later, what came back, and your latest threads.
- [Attachments](https://themachine.myapps.ai/markdown/docs/desktop/chat/attachments.md): Give a bot files to work with. How to attach, which file types and sizes work, what happens to your files, and how to view and save files a bot makes.
- [Find, share, and export](https://themachine.myapps.ai/markdown/docs/desktop/chat/find-share-export.md): Search inside a conversation, compact a long thread, share a website a bot is running, share a single run as a page, and export a conversation as Markdown.
- [Message actions, mentions, and commands](https://themachine.myapps.ai/markdown/docs/desktop/chat/message-actions.md): Edit, copy, reply to, pin, regenerate, and branch from messages, comment on part of a reply, mark up an image, @mention bots, and use slash commands.
- [Send messages and watch a bot work](https://themachine.myapps.ai/markdown/docs/desktop/chat/sending-messages.md): The chat screen, the message box, sending and stopping, what a bot shows while it works, and how replies look.
- [Voice](https://themachine.myapps.ai/markdown/docs/desktop/chat/voice.md): Talk to your bots instead of typing. Dictate into the message box, send a voice message, record a meeting for notes, choose a dictation engine, and set up your microphone.
- [Write good requests](https://themachine.myapps.ai/markdown/docs/desktop/chat/writing-requests.md): How to ask a bot for what you want and get it the first time. Plain advice, before-and-after examples, and templates you can copy.
- [Cost and sleep](https://themachine.myapps.ai/markdown/docs/desktop/cloud-computer/cost-and-sleep.md): When a bot's computer is awake, asleep, and billing, how to see which computers are running, and how to stop them.
- [Files on the bot's computer](https://themachine.myapps.ai/markdown/docs/desktop/cloud-computer/files.md): Browse the files a bot made, view documents, data, images, and video right in the app, download them, and ask the bot about any file.
- [The bot's computer](https://themachine.myapps.ai/markdown/docs/desktop/cloud-computer/overview.md): Every thread runs on its own computer in the cloud. What that means, how to open the computer panel, what its tabs do, and how to unstick a bot.
- [Preview websites and use the terminal](https://themachine.myapps.ai/markdown/docs/desktop/cloud-computer/preview-and-terminal.md): See a website a bot is running on its computer, and open a command line on the bot's computer yourself.
- [Deployments](https://themachine.myapps.ai/markdown/docs/desktop/deployments.md): Put a website or app a bot built on the internet, with its own link and optionally your own domain. Deploy, redeploy, configure, stop, and delete.
- [Frequently asked questions](https://themachine.myapps.ai/markdown/docs/desktop/faq.md): Short answers to the questions new Machine Desktop users ask most, with links to the pages that explain each one in full.
- [The app window](https://themachine.myapps.ai/markdown/docs/desktop/get-started/app-window.md): Find your way around the Machine Desktop window, and learn how closing, the tray, quitting, zoom, menus, and Machine links work.
- [How Machine works](https://themachine.myapps.ai/markdown/docs/desktop/get-started/concepts.md): The few ideas behind everything in Machine Desktop, explained in plain words. Read this first if you are new.
- [Your first 15 minutes](https://themachine.myapps.ai/markdown/docs/desktop/get-started/first-steps.md): A guided walkthrough for brand-new users. Install the app, make your first bot, give it a real task, find what it made, and learn the controls you will use every day.
- [Install Machine Desktop](https://themachine.myapps.ai/markdown/docs/desktop/get-started/install.md): What you need, how to download and install Machine Desktop on Windows or Mac, and how to uninstall it.
- [Sign in](https://themachine.myapps.ai/markdown/docs/desktop/get-started/sign-in.md): Sign in to Machine Desktop with an emailed code or a password, fix common sign-in problems, and sign out.
- [Updates](https://themachine.myapps.ai/markdown/docs/desktop/get-started/updates.md): How Machine Desktop finds, downloads, and installs new versions, how to check yourself, and what to do if an update fails.
- [The welcome tour](https://themachine.myapps.ai/markdown/docs/desktop/get-started/welcome-tour.md): What each welcome screen asks, what your first bot learns about you, what the guided tour shows you, the first-week tips, and how to replay the tours.
- [Build and publish a website](https://themachine.myapps.ai/markdown/docs/desktop/guides/build-a-website.md): Have a bot build a small website, preview it, share a link while you work on it, then put it online with your own domain.
- [Get a briefing every weekday](https://themachine.myapps.ai/markdown/docs/desktop/guides/daily-briefing.md): Set up an automation that has a bot write you a morning briefing every weekday, then check how each run went.
- [Fill in forms in your browser](https://themachine.myapps.ai/markdown/docs/desktop/guides/fill-forms-in-your-browser.md): Let a bot fill in a web form in your own Chrome, where you're already signed in, and take the browser back when it's done.
- [Organize files on your PC](https://themachine.myapps.ai/markdown/docs/desktop/guides/organize-files-on-your-pc.md): Let a bot sort, rename, and tidy files in one folder on your own computer, with you approving each step.
- [Get a research report](https://themachine.myapps.ai/markdown/docs/desktop/guides/research-report.md): Ask a bot to research a topic, watch it work, and download the finished report from its computer.
- [Build a team in a group chat](https://themachine.myapps.ai/markdown/docs/desktop/guides/team-in-a-group-chat.md): Make a few bots with different jobs, put them in one group chat, and have them work together on a task.
- [Machine Desktop](https://themachine.myapps.ai/markdown/docs/desktop.md): A desktop app where you give work to AI bots that use real computers to get it done. Start here if you are new.
- [Inkbox from Machine Desktop](https://themachine.myapps.ai/markdown/docs/desktop/inkbox/from-machine-desktop.md): Everything Machine Desktop shows and does with Inkbox, the Channels row, /call, text-me check-ins on goals, and seeing Inkbox steps in a thread.
- [Inkbox](https://themachine.myapps.ai/markdown/docs/desktop/inkbox.md): Reach a bot by iMessage, text message, email or phone call, from any phone, without opening Machine. What Inkbox does, what it costs, and how it fits with Machine Desktop.
- [Phone calls](https://themachine.myapps.ai/markdown/docs/desktop/inkbox/phone-calls.md): Call your bot on its Inkbox number, or have it phone a business for you with /call. What happens during and after each call.
- [Set up Inkbox](https://themachine.myapps.ai/markdown/docs/desktop/inkbox/set-up.md): Step by step, connect a bot to your Inkbox account, choose who may reach it, connect your phone for iMessage, and check it in Machine Desktop.
- [Text and email your bot](https://themachine.myapps.ai/markdown/docs/desktop/inkbox/text-and-email.md): What to send a bot by iMessage, SMS or email, how follow-ups and fresh starts work, how the bot remembers you, and how to read the conversation in Machine Desktop.
- [Inkbox troubleshooting](https://themachine.myapps.ai/markdown/docs/desktop/inkbox/troubleshooting.md): Fixes for texts, emails and calls that don't reach the bot, replies that don't arrive, and setup errors.
- [Who can reach your bot](https://themachine.myapps.ai/markdown/docs/desktop/inkbox/who-can-reach-your-bot.md): How Inkbox allow-lists work, why they matter, which channels can be faked, and how to keep a bot that answers texts and email safe.
- [Channels](https://themachine.myapps.ai/markdown/docs/desktop/integrations/channels.md): Let people reach a bot from outside Machine, on Slack, by text, email or phone with Inkbox, and by live voice with Glyph. Connect, manage, and disconnect a channel.
- [Connected apps](https://themachine.myapps.ai/markdown/docs/desktop/integrations/connected-apps.md): Let bots work in the tools you use, like Gmail, Google Calendar, GitHub, Notion, and Slack. Connect, check, and disconnect apps.
- [Secrets and webhooks](https://themachine.myapps.ai/markdown/docs/desktop/integrations/secrets-and-webhooks.md): Give a bot the API keys and passwords it needs, safely, with write-only secrets, and see the webhooks that can start a bot.
- [After the call](https://themachine.myapps.ai/markdown/docs/desktop/live/after-the-call.md): The call card in the thread, what's in a transcript, how the bot follows up on what you said, and how to read, copy, or call again.
- [During a call](https://themachine.myapps.ai/markdown/docs/desktop/live/during-a-call.md): What's on the call screen, how to mute, interrupt, and hold to talk, what the bot can make while you talk, and how to hang up.
- [Live](https://themachine.myapps.ai/markdown/docs/desktop/live.md): Talk to a bot out loud in a real-time voice call, and watch it work on its own computer. What Live is, what you need, and where to start.
- [Live settings](https://themachine.myapps.ai/markdown/docs/desktop/live/live-settings.md): Choose a bot's call voice and language, hands-free or hold to talk, when it answers, and how to stop it answering its own echo.
- [The Live view](https://themachine.myapps.ai/markdown/docs/desktop/live/live-view.md): Watch a bot work on its computer as a desktop with windows, a dock and its mascot. Open it, read each app, replay steps, upload by dropping files, and message the bot.
- [Make a call](https://themachine.myapps.ai/markdown/docs/desktop/live/make-a-call.md): Start a Live call with a bot from any thread, on Machine Desktop or your phone, and allow the microphone the first time.
- [Set up Glyph](https://themachine.myapps.ai/markdown/docs/desktop/live/set-up-glyph.md): Connect a Glyph API key to a bot so you can call it. Where to get the key, two places to paste it, and how to change or remove it.
- [Live troubleshooting](https://themachine.myapps.ai/markdown/docs/desktop/live/troubleshooting.md): Fixes for Live calls that won't start, can't hear you, drop, answer themselves, or come back without Glyph's tools, and for an empty Live view.
- [The bot's computer on a phone](https://themachine.myapps.ai/markdown/docs/desktop/mobile/bots-computer.md): Open a bot's computer from your phone to browse and download files, check its status, and wake, stop or restart it.
- [Chat on your phone](https://themachine.myapps.ai/markdown/docs/desktop/mobile/chat-on-your-phone.md): The chat screen in Machine Mobile, sending and stopping, the More menu, message actions, approvals and questions, and what's different from desktop.
- [Find your way around](https://themachine.myapps.ai/markdown/docs/desktop/mobile/find-your-way-around.md): The Bots, Routines and Settings tabs, your bots and threads, search, teams, the New menu, and every gesture in Machine Mobile.
- [Mobile apps](https://themachine.myapps.ai/markdown/docs/desktop/mobile.md): Machine on Android, iPhone and iPad. Get the app, what you can do on your phone, and how it differs from Machine Desktop.
- [iPad](https://themachine.myapps.ai/markdown/docs/desktop/mobile/ipad.md): Machine on iPad gives you the full desktop layout with the sidebar, chat and panels side by side, including the Live view.
- [Live on your phone](https://themachine.myapps.ai/markdown/docs/desktop/mobile/live-on-your-phone.md): Make Live calls on Machine Mobile. The Live button, the full-screen call, the thumb bar, shrinking a call to a bar, the transcript sheet, and the microphone permission.
- [Routines on your phone](https://themachine.myapps.ai/markdown/docs/desktop/mobile/routines.md): See, create, run, pause and edit your automations from Machine Mobile's Routines tab.
- [Settings on your phone](https://themachine.myapps.ai/markdown/docs/desktop/mobile/settings.md): Machine Mobile's Settings tab. Profile, language, sounds, quiet hours, notifications, updates, appearance, usage, people, and signing out.
- [Share, notifications and offline](https://themachine.myapps.ai/markdown/docs/desktop/mobile/share-notifications-offline.md): Share links and text from other apps to a bot, get notified when a bot finishes, and what happens when your phone loses its connection.
- [Sign in on your phone](https://themachine.myapps.ai/markdown/docs/desktop/mobile/sign-in.md): Sign in to Machine Mobile with an emailed code or your password, and what "This device" means.
- [Mobile troubleshooting](https://themachine.myapps.ai/markdown/docs/desktop/mobile/troubleshooting.md): Fixes for Machine Mobile, from signing in and missing replies to Live calls, notifications and sharing.
- [Approvals](https://themachine.myapps.ai/markdown/docs/desktop/models/approvals.md): Decide whether a bot asks before it acts, set rules for each kind of action, and read and answer an approval request.
- [Choose a model](https://themachine.myapps.ai/markdown/docs/desktop/models/choosing-a-model.md): What an AI model is, how to pick the right one for a task, and how to change the model for a thread or a whole bot.
- [Use your own subscription](https://themachine.myapps.ai/markdown/docs/desktop/models/own-subscriptions.md): Run bots on your own Claude or Cursor plan instead of your Machine balance. How to connect, how the models appear, and the rules for shared threads.
- [Questions, runs, and replays](https://themachine.myapps.ai/markdown/docs/desktop/models/questions-and-runs.md): Answer a bot's multiple-choice questions, read the line under a finished reply, replay or share a run, and save a run that worked as a reusable skill.
- [Reasoning effort](https://themachine.myapps.ai/markdown/docs/desktop/models/reasoning-effort.md): Tell a model to think longer for hard problems, or less for quick ones. Where the effort control is, what the levels mean, and when to change it.
- [Connect Pixio](https://themachine.myapps.ai/markdown/docs/desktop/pixio/connect.md): Create a Pixio API key and connect it to a bot in Machine Desktop. Check the account and free uses, replace the key, or disconnect.
- [Credits and spending](https://themachine.myapps.ai/markdown/docs/desktop/pixio/credits-and-spending.md): How bots choose Pixio models by your price, quote before generating, ask before expensive runs, never charge twice, and stay within your budget.
- [Pixio](https://themachine.myapps.ai/markdown/docs/desktop/pixio.md): Let a bot make images, video, music, voice and 3D with your own Pixio account. What Pixio is, what bots can make, and where to start.
- [Make images, video and audio](https://themachine.myapps.ai/markdown/docs/desktop/pixio/make-media.md): How to ask a bot for images, video, music, voice and 3D with Pixio, with example requests, tips for better results, and what you get back.
- [Pixio troubleshooting](https://themachine.myapps.ai/markdown/docs/desktop/pixio/troubleshooting.md): Fixes for a missing Pixio row, rejected keys, running out of credits, too many jobs, and results you can't find.
- [Your files and key](https://themachine.myapps.ai/markdown/docs/desktop/pixio/your-files-and-key.md): Where Pixio results are saved, why links expire, editing your own photos and videos, and how your Pixio key is kept safe.
- [Privacy and security](https://themachine.myapps.ai/markdown/docs/desktop/privacy-and-security.md): What runs on Machine and what runs on your computer, what leaves your computer, how your sign-in and secrets are kept, and how you stay in control when a bot works on your own computer.
- [Appearance](https://themachine.myapps.ai/markdown/docs/desktop/settings/appearance.md): Change how Machine Desktop looks with skins and mascot styles, and choose whether to show thread lists, tool calls, and how dense the sidebar is.
- [General settings](https://themachine.myapps.ai/markdown/docs/desktop/settings/general.md): How to open Settings, and every option in the General section, from your profile and language to quiet hours, Simple mode, updates, diagnostics, and your account.
- [Languages](https://themachine.myapps.ai/markdown/docs/desktop/settings/languages.md): Change the language of Machine Desktop, and which languages are available.
- [Notifications](https://themachine.myapps.ai/markdown/docs/desktop/settings/notifications.md): Get told when a bot finishes, has a question, needs approval, or hits an error. Turn notifications on or off per bot, set quiet hours, and other ways the app gets your attention.
- [People](https://themachine.myapps.ai/markdown/docs/desktop/settings/people.md): See who is on your Machine team, invite someone by email as a Member or Admin, change roles, remove people, and resend or cancel invites.
- [Usage and billing](https://themachine.myapps.ai/markdown/docs/desktop/settings/usage-and-billing.md): What costs money in Machine, where to see your balance, how to see what each bot and model has cost, export your usage, and add credits.
- [Command palette and quick switcher](https://themachine.myapps.ai/markdown/docs/desktop/shortcuts/command-palette.md): Two fast ways to get anywhere. Search every bot, group chat, and message with the command palette, or jump to a bot, or ask it something, from any app with the quick switcher.
- [Keyboard shortcuts](https://themachine.myapps.ai/markdown/docs/desktop/shortcuts/keyboard-shortcuts.md): Every keyboard shortcut in Machine Desktop, for Windows and Mac.
- [Use your own Chrome](https://themachine.myapps.ai/markdown/docs/desktop/this-pc/chrome-extension.md): Let a bot work in your own browser, signed in as you, with the Machine extension. Install it, ask for it, see what's happening, and take your browser back.
- [Fast mode](https://themachine.myapps.ai/markdown/docs/desktop/this-pc/fast-mode.md): Let a small, fast browser-driving AI finish long web jobs in one go, using your own OpenRouter key. How it works, what it costs, how to set it up, and how it stays safe.
- [Mac permissions](https://themachine.myapps.ai/markdown/docs/desktop/this-pc/mac-permissions.md): The two macOS permissions a bot needs to see your screen and use the mouse and keyboard, and how to turn them on.
- [This PC](https://themachine.myapps.ai/markdown/docs/desktop/this-pc/overview.md): Let a bot work with the files, programs, and screen of your own computer. What it's for, how to set it up, what a bot can do, and every setting in the folder menu.
- [Safety and stopping](https://themachine.myapps.ai/markdown/docs/desktop/this-pc/safety-and-stop.md): How you stay in control when a bot works on your computer. What each protection does, how to answer permission requests, and every way to stop a bot instantly.
- [Troubleshooting](https://themachine.myapps.ai/markdown/docs/desktop/troubleshooting.md): What to do when a bot is stuck, a message shows ⚠, the app can't connect, an update fails, This PC or voice won't work, and how to contact support.
- [Getting started](https://themachine.myapps.ai/markdown/docs/getting-started.md): Create an account, find your way around, and set up your first project — everything before the everyday loop.
- [Customizing your project](https://themachine.myapps.ai/markdown/docs/guides/customizing-your-project.md): Shape what your agents know and can do — agents, skills, connectors, secrets, channels, models, members, and settings.
- [Deploying a website](https://themachine.myapps.ai/markdown/docs/guides/deploying-a-website.md): Take a site from your project to a live URL — and connect your own domain — in a few minutes.
- [Reviewing changes](https://themachine.myapps.ai/markdown/docs/guides/reviewing-changes.md): Review what an agent produced and merge it into your project — the gate every change passes through.
- [Running a session](https://themachine.myapps.ai/markdown/docs/guides/running-a-session.md): Start an agent on a task, watch it work, steer it, and review what it changed — all from the project workspace.
- [Team & access](https://themachine.myapps.ai/markdown/docs/guides/team-and-access.md): Invite people, assign roles, and control who can do what — at both the account and project level.
- [Using agents & skills](https://themachine.myapps.ai/markdown/docs/guides/using-agents.md): Pick the right agent for a task, shape your own, and give them reusable skills — so the work fits how your team actually operates.
- [Driving Machine from Slack](https://themachine.myapps.ai/markdown/docs/guides/using-slack.md): Connect a Slack workspace so your team can start and steer agent work without leaving chat.
- [Working with projects](https://themachine.myapps.ai/markdown/docs/guides/working-with-projects.md): Create projects from scratch or from a GitHub repo, organize them, and browse their files.
- [Machine](https://themachine.myapps.ai/markdown/docs/index.md): Machine is the AI command center for your company.
- [Agents](https://themachine.myapps.ai/markdown/docs/project/agents.md): An agent is a markdown file that OpenCode runs; the manifest only governs its access.
- [Your project](https://themachine.myapps.ai/markdown/docs/project.md): A project is a git repository that holds your agent's config and state.
- [Legacy kortix.toml](https://themachine.myapps.ai/markdown/docs/project/legacy-toml.md): Support status and the migration path from v1 kortix.toml to v2 kortix.yaml.
- [Manifest reference](https://themachine.myapps.ai/markdown/docs/project/manifest.md): Every kortix.yaml v2 key, with defaults, limits, and validation rules.
- [Models](https://themachine.myapps.ai/markdown/docs/project/models.md): How Machine picks a model, the models Machine manages, and how billing works for managed models, your own keys, and your own plans.
- [Secrets](https://themachine.myapps.ai/markdown/docs/project/secrets.md): How Machine stores project credentials and controls where each value is allowed to go.
- [Quickstart](https://themachine.myapps.ai/markdown/docs/quickstart.md): Install the CLI, run a session, and merge your first change request.
- [Apps](https://themachine.myapps.ai/markdown/docs/sdk/apps.md): Deploy a project's websites to Vercel from the manifest, the CLI, or the SDK.
- [Authentication](https://themachine.myapps.ai/markdown/docs/sdk/auth.md): Authenticate the SDK with a personal access token or a service account.
- [Full example](https://themachine.myapps.ai/markdown/docs/sdk/example.md): One file that lists projects, starts a session, and streams a reply.
- [TypeScript SDK](https://themachine.myapps.ai/markdown/docs/sdk.md): Install, authenticate, and send your first message with the typed SDK.
- [React hooks](https://themachine.myapps.ai/markdown/docs/sdk/react.md): Run a Machine session in React with the useSession hook.
- [SDK reference](https://themachine.myapps.ai/markdown/docs/sdk/reference.md): The full @kortix/sdk API surface — client methods, modules, turns, and distribution.
- [Sessions](https://themachine.myapps.ai/markdown/docs/sdk/sessions.md): Run a session, stream its events, and handle the errors it can throw.
- [Change requests](https://themachine.myapps.ai/markdown/docs/work/change-requests.md): How session work reaches the default branch through review.
- [Running work](https://themachine.myapps.ai/markdown/docs/work.md): How work moves from prompt to merged change, and the three ways it starts.
- [Runtime & sandbox](https://themachine.myapps.ai/markdown/docs/work/runtime.md): Sandbox lifecycle, injected environment, token families, and the image a session boots from.
- [Sessions](https://themachine.myapps.ai/markdown/docs/work/sessions.md): A session is a git branch and a sandbox where the agent works.

## Blog
- [Machine vs QM: two open agent platforms, two different units of work](https://themachine.myapps.ai/markdown/blog/kortix-vs-qm.md): QM and Machine both give teams persistent agents, isolated computers, Slack and web access, and self-hosting. The decisive difference is deeper: QM organizes work around people and rooms; Machine organizes it around git-backed projects and reviewable sessions.
- [The only moat that matters: why your AI platform needs a learning loop, not a better model](https://themachine.myapps.ai/markdown/blog/the-only-moat-that-matters.md): Every AI product is converging on the same architecture. The only defensible advantage is a data flywheel — a learning loop where every interaction makes your system better. Here is what that means, and why Machine is built for it.
- [Your company needs two kinds of capital: human and token](https://themachine.myapps.ai/markdown/blog/two-kinds-of-capital.md): Satya Nadella’s frontier-ecosystem framework reveals the most important strategic idea in AI: every company must build human capital and token capital, and they compound together.
- [The test of sovereignty: can you swap the model without losing what you built?](https://themachine.myapps.ai/markdown/blog/the-test-of-sovereignty.md): The most important question for any company adopting AI: can you switch out the model without losing the institutional expertise you have built? A sovereignty checklist for evaluating your AI platform.
- [Static software is dead: the shift from code to feedback loops](https://themachine.myapps.ai/markdown/blog/static-software-is-dead.md): The way we build software is fundamentally changing. Static software no longer creates a defensible advantage. The shift is to dynamic software that improves through feedback loops.
- [Every AI product is the same: the convergence nobody is talking about](https://themachine.myapps.ai/markdown/blog/the-convergence-of-ai-products.md): Open any agent platform — they are architecturally identical. The marginal differences are not defensible. The only thing that diverges is the learning loop.
- [A frontier without an ecosystem is not stable](https://themachine.myapps.ai/markdown/blog/the-frontier-ecosystem.md): The first phase of globalization hollowed out industrial economies. The AI era cannot repeat that. The priority has to be building a frontier ecosystem, not just a frontier model.
- [Good businesses don’t need moats (and why that’s fine)](https://themachine.myapps.ai/markdown/blog/good-businesses-dont-need-moats.md): The startup world is obsessed with moats. Every pitch deck has a slide. Every investor asks. But most great businesses do not have a true moat, and they are still great businesses.
- [What Machine actually is: the AI Management System, layer by layer](https://themachine.myapps.ai/markdown/blog/open-source-ai-management-system.md): One git repo is the source of truth for the agents, the skills, the memory and the connector config. Every session gets its own isolated machine and its own branch. Any model, your keys. Work lands through a change request. Self-hosted or managed cloud. The long version of that sentence.
- [Machine vs Poetic: both turn workflows into code — the difference is who owns the code](https://themachine.myapps.ai/markdown/blog/kortix-vs-poetic.md): Poetic compiles your procedures into a purpose-built language it runs for you. Machine keeps the workflow as ordinary code in a repo you own, and gates the boundary where it touches the world. A technical comparison of two answers to the same problem.
- [AGI-ready architecture: what it really means, and how Machine is built for it](https://themachine.myapps.ai/markdown/blog/agi-ready-architecture.md): AGI-ready doesn't mean an architecture that produces AGI. It means one that absorbs a 100× capability jump without losing state or granting uncontrolled access. How Machine is built for it.
- [Machine vs Glean: search or an agent platform that runs work?](https://themachine.myapps.ai/markdown/blog/kortix-vs-glean.md): Glean is the best permission-aware enterprise search. But search finds work — it doesn't do it. Here's where you outgrow it, and the open runtime alternative.
- [How to give AI agents tool access safely](https://themachine.myapps.ai/markdown/blog/secure-ai-agent-tool-access.md): How to give AI agents production tool access without raw API keys: scoped connectors, approval policies, server-side credentials, and reviewed work.
- [AI transformation needs a company OS](https://themachine.myapps.ai/markdown/blog/ai-transformation-company-os.md): Why consultancies and AI-transformation teams need one Git-backed workspace for agents, memory, connectors, policy, and auditable work.
- [Machine vs Claude Cowork: a desktop assistant, or a company-wide agent platform?](https://themachine.myapps.ai/markdown/blog/kortix-vs-claude-cowork.md): Claude Cowork is the best agent on the desktop. But it runs one assistant per person, on Anthropic's models, with your data on their cloud. Here's where you outgrow it — and what an open, company-wide agent platform looks like.
- [Personal AI agents vs a company OS: Machine, OpenClaw, and Hermes](https://themachine.myapps.ai/markdown/blog/personal-ai-agents-vs-company-os.md): OpenClaw and Hermes are capable personal agents. But a personal "Jarvis" and a governed company platform are different things. Here is exactly where the line is.
- [Beyond the chat box: why ChatGPT, Claude, and Grok aren't an AI workforce](https://themachine.myapps.ai/markdown/blog/beyond-the-chat-box.md): Chat assistants answer; a workforce does the work. Why input-output tools — however brilliant — aren’t the same as a fleet of agents that run your company, own the data, and run on any model.
- [Introducing Machine: the AI command center for your company](https://themachine.myapps.ai/markdown/blog/introducing-kortix.md): A workforce of AI agents that do real work across your tools — defined as files in a git repo, run in isolated sandboxes, governed by review, and built enterprise-first. Here is the whole thing, A to Z.

## Use cases
- [How we handle access requests](https://themachine.myapps.ai/markdown/use-cases/access-requests.md): Someone asks for access in Slack and an agent checks the policy, looks up their role and drafts the smallest grant that fits. A person approves every grant, and each one is logged.
- [How we keep watch over our ad performance](https://themachine.myapps.ai/markdown/use-cases/ad-performance.md): Our ads agent reads Google Ads and Meta Ads each day, spots pacing problems, CPA and ROAS drift and weak ads or keywords, and posts ranked fixes to Slack. It never edits budgets, campaigns or ads.
- [How we process vendor invoices the moment they arrive](https://themachine.myapps.ai/markdown/use-cases/ap-invoice-processing.md): Every 15 minutes our payables agent pulls new invoices from Gmail, reads them, checks them against POs and the ledger in Google Sheets, and sends them to Slack for approval. It never pays anything.
- [How we follow up on invoices that are past due](https://themachine.myapps.ai/markdown/use-cases/ar-chaser.md): Our receivables agent on Machine works with Stripe, email and the accounting ledger. It spots late invoices, sends the right reminder, records each contact and reconciles payments as they arrive.
- [How we keep track of who's talking about our brand](https://themachine.myapps.ai/markdown/use-cases/brand-monitor.md): Each day an agent scans news, social sites and forums for fresh mentions of our brand, sorts them by sentiment, and posts the important or negative ones to Slack with a draft reply for a person to review.
- [How we find candidates for our open roles](https://themachine.myapps.ai/markdown/use-cases/candidate-sourcing.md): Each day our sourcing agent on Machine searches LinkedIn for people who fit an open role, skips anyone already in Greenhouse, and writes a tailored email that the recruiter reviews and sends.
- [How we spot accounts that might churn](https://themachine.myapps.ai/markdown/use-cases/churn-risk.md): Each day an agent scores every account on early churn warnings from product usage, support and billing, then posts a ranked list to Slack with the reason and a suggested next step for each.
- [How we catch cloud cost spikes long before the bill arrives](https://themachine.myapps.ai/markdown/use-cases/cloud-cost-anomaly.md): Our cost agent reads AWS Cost Explorer each day, learns normal spend for every service and account, flags anything that breaks pattern with its likely cause, and alerts Slack. It never touches a resource or budget.
- [How we keep an eye on competitors](https://themachine.myapps.ai/markdown/use-cases/competitor-watch.md): Every day an agent reads competitor websites, changelogs and pricing pages, compares them with yesterday's copy, and drops a short note in Slack about anything that moved.
- [How we catch compliance drift](https://themachine.myapps.ai/markdown/use-cases/compliance-monitoring.md): Each day an agent checks our cloud setup against policy, flags public buckets, missing tags and roles with too much access, and suggests every fix as a change a person approves.
- [How we keep our content from going stale](https://themachine.myapps.ai/markdown/use-cases/content-refresh.md): Once a week an agent on Machine spots blog and marketing pages that are slipping in Search Console, freshens their copy, numbers and internal links, and opens a pull request for review.
- [How we do first-pass contract review](https://themachine.myapps.ai/markdown/use-cases/contract-review.md): Drop a contract into a Drive folder and an agent reads it, flags any clause that breaks our playbook, posts a summary for legal and drafts redlines a lawyer must approve.
- [How we keep our CRM clean](https://themachine.myapps.ai/markdown/use-cases/crm-hygiene.md): Each night an agent merges duplicate HubSpot contacts, fills in blank fields from enrichment data, flags deals that went cold and posts a tidy-up report. Big bulk edits wait for a person.
- [How we help new customers reach activation](https://themachine.myapps.ai/markdown/use-cases/customer-onboarding.md): A daily agent on Machine checks every new account's onboarding progress in Postgres, writes a nudge email when one gets stuck, and gives the account's CSM the full story in Slack.
- [How we run customer support with an AI agent](https://themachine.myapps.ai/markdown/use-cases/customer-support.md): Our support agent on Machine plugs into Plain, our code and Stripe. It sorts and answers incoming threads on its own, and pauses for a person whenever something sensitive comes up.
- [How we monitor our data pipelines and warehouse health](https://themachine.myapps.ai/markdown/use-cases/data-pipeline-monitor.md): Every hour an agent on Machine checks how fresh our warehouse tables are, whether row counts look normal and whether schemas shifted, then alerts Slack and drafts a GitHub issue. It never changes data.
- [How we stop our dependencies falling behind](https://themachine.myapps.ai/markdown/use-cases/dependency-upgrades.md): Once a week a Machine agent bumps our packages, installs them clean in a private sandbox and runs every test. You only get a pull request when the whole suite is green.
- [How we keep our docs matching what the code does](https://themachine.myapps.ai/markdown/use-cases/docs-maintainer.md): Once a day a Machine agent reads every commit merged since its last pass, finds the doc pages those changes made wrong, rewrites them and sends you one pull request to review.
- [How we handle offboarding when someone leaves](https://themachine.myapps.ai/markdown/use-cases/employee-offboarding.md): A Machine agent checks Okta for new leavers, cuts their access in Okta, Google Workspace, Drive and GitHub and frees their licenses. Ownership transfers wait for approval; accounts are never deleted.
- [How we get new hires set up](https://themachine.myapps.ai/markdown/use-cases/employee-onboarding.md): When HR adds a new hire, a Machine agent prepares their Google account, groups, Slack channels and a first-week checklist in Linear. Anything that grants access waits for a person to approve.
- [How we keep our production error backlog tidy](https://themachine.myapps.ai/markdown/use-cases/error-triage.md): Every hour a Machine agent sorts new and spiking Sentry errors, checks GitHub for existing issues, drafts issues for the worst ones and posts to Slack. It never resolves, ignores or assigns.
- [How we get urgent support tickets to the right team](https://themachine.myapps.ai/markdown/use-cases/escalation-manager.md): Every 15 minutes a Machine agent checks Plain for SLA breaches, VIP accounts and severe tickets, routes each one, links a Linear issue when engineers are needed and posts to Slack. It never closes tickets.
- [How we close the books on expenses each month](https://themachine.myapps.ai/markdown/use-cases/expense-reconciliation.md): Once a month a Machine agent checks Stripe and the bank feed against our invoices, records the result in Google Sheets and posts a summary. Anything it cannot match goes to a person.
- [How we clear out old feature flags](https://themachine.myapps.ai/markdown/use-cases/feature-flag-cleanup.md): Each week a Machine agent finds feature flags that are fully rolled out or long dead, deletes them along with the code they guard, and opens a PR. A person merges; live rollouts are left alone.
- [How we catch flaky tests and put them in quarantine](https://themachine.myapps.ai/markdown/use-cases/flaky-test-triage.md): Our Machine agent reads GitHub CI history daily, ranks each test by how often it flips on unchanged code, then opens a quarantine PR and a tracking issue for a person to review.
- [How we answer GDPR data-subject requests before the deadline](https://themachine.myapps.ai/markdown/use-cases/gdpr-dsar.md): Our Machine agent checks each GDPR access or deletion request, finds the person's data across our product database, builds the report well within the SLA and hands it to legal before anything is sent.
- [How we answer HR policy questions on autopilot](https://themachine.myapps.ai/markdown/use-cases/hr-policy-qa.md): Every 15 minutes our Machine agent reads the HR inbox, answers only from our Notion policy library as a Gmail draft for HR to send, and passes anything sensitive to HR in Slack.
- [How we keep a shared inbox sorted with an AI agent](https://themachine.myapps.ai/markdown/use-cases/inbox-triage.md): An agent on Machine reads our shared Gmail inbox with a help doc and Linear to hand. It labels each email, drafts a reply or files a task, and waits for a person before a customer sees anything.
- [How we write the first draft of every incident postmortem](https://themachine.myapps.ai/markdown/use-cases/incident-postmortem.md): Once an incident is resolved, a Machine agent reads the incident channel, lines the timeline up with deploys and log spikes, and opens a postmortem draft as a doc PR for the team to review and edit.
- [How we keep interview loops on schedule](https://themachine.myapps.ai/markdown/use-cases/interview-scheduler.md): Each day our Machine agent picks up candidates who are ready to book in Greenhouse, checks the panel's Google Calendars, and drafts the time proposal and invites for a coordinator to approve.
- [How we write the first draft of our monthly investor update](https://themachine.myapps.ai/markdown/use-cases/investor-update.md): Once a month an agent on Machine reads Postgres, Stripe and last month's update, gathers our key metrics, checks them against last month and plan, and drafts the update in our format for a founder.
- [How we get back to every inbound lead](https://themachine.myapps.ai/markdown/use-cases/lead-follow-up.md): An agent on Machine works with HubSpot, email and Google Calendar. It looks into each new lead, writes a personal follow-up with a suggested call time, and waits for a person to approve the send.
- [How we get each inbound lead to the right rep](https://themachine.myapps.ai/markdown/use-cases/lead-routing.md): Every 15 minutes, our Machine agent scores fresh HubSpot leads, gives each one an owner by territory, segment or round-robin, pings that rep in Slack, and passes anything unclear to a person.
- [How we turn each meeting into notes and action items](https://themachine.myapps.ai/markdown/use-cases/meeting-notes.md): Our meeting agent on Machine works from Google Calendar, the call transcript and Linear. When a call wraps, it writes tidy notes and files each action item as a Linear ticket for the person who owns it.
- [How we run the month-end close](https://themachine.myapps.ai/markdown/use-cases/month-end-close.md): Each month our Machine finance agent works the close checklist, ties Stripe revenue to the Google Sheets ledger, flags odd numbers and missing docs, and posts open items to Slack. A person closes the books.
- [How we turn NDAs around in minutes instead of days](https://themachine.myapps.ai/markdown/use-cases/nda-turnaround.md): Every 15 minutes our Machine agent picks up new NDAs, marks up anything that strays from our standard positions, and drafts a note for counsel. It never signs and never sends. Counsel does both.
- [How we turn NPS responses into clear themes](https://themachine.myapps.ai/markdown/use-cases/nps-analysis.md): Once a week our Machine agent reads new NPS and CSAT answers from a Google Sheet, sorts the comments into themes with sentiment and detractor drivers, and posts the score trend and real quotes to Slack.
- [How we keep the office kitchen stocked](https://themachine.myapps.ai/markdown/use-cases/office-snacks.md): Anyone can ask for snacks with a Slack shortcut. Once a week an agent rounds up the requests, puts together an order, and posts it for the office manager to approve before a penny is spent.
- [How we triage on-call alerts before anyone gets paged](https://themachine.myapps.ai/markdown/use-cases/oncall-triage.md): Our triage agent on Machine reads Sentry, our logs and GitHub. It puts together a first diagnosis for every alert, and only wakes a person when it can't settle the alert or the severity is high.
- [How we run truly personal outbound](https://themachine.myapps.ai/markdown/use-cases/outbound-outreach.md): Our agent on Machine works with the CRM, enrichment and email. It researches every lead, writes a sequence that is actually personal, logs it to the CRM, and waits for a person to approve sends under a daily cap.
- [How we win back subscription payments that fail](https://themachine.myapps.ai/markdown/use-cases/payment-recovery.md): Every hour, an agent walks each failed Stripe invoice up a four-step ladder of retry and reminders, keeps the revenue team posted in Slack, and goes quiet the second the customer pays.
- [How we sort through reported phishing emails](https://themachine.myapps.ai/markdown/use-cases/phishing-triage.md): Every 15 minutes, a Machine agent opens newly reported emails, checks headers, links and attachments for warning signs, and posts a verdict with a suggested action to Slack. A person makes the final call.
- [How we stop deals from going quiet](https://themachine.myapps.ai/markdown/use-cases/pipeline-hygiene.md): A daily Machine agent combs HubSpot for deals gone silent, blank next steps, stuck stages and late tasks, pings the rep who owns each one in Slack, and sends the worst cases up to their manager.
- [How we stop code review from getting stuck](https://themachine.myapps.ai/markdown/use-cases/pr-review-nudge.md): A Machine agent spots pull requests that are overdue for review, have gone quiet, or still owe answers to requested changes, then pings the author or reviewer in Slack with what's holding them up.
- [How we test every pull request without lifting a finger](https://themachine.myapps.ai/markdown/use-cases/qa-agent.md): Our Machine QA agent works with GitHub and our test environment. For each pull request it checks out the branch, runs the tests, tries the change for real, and posts what it found.
- [How we put together first-draft QBR decks for key accounts](https://themachine.myapps.ai/markdown/use-cases/qbr-prep.md): Each week, a Machine agent reads Postgres and HubSpot for every account with a QBR coming up and builds a draft Google Slides deck plus a Google Docs briefing for the CSM to edit and present.
- [How we write release notes straight from merged PRs](https://themachine.myapps.ai/markdown/use-cases/release-notes.md): Our Machine release-notes agent works from GitHub. Each time we ship, it reads what merged since the previous release, sorts it by area, writes the notes and opens a changelog PR.
- [How we stay one step ahead of contract renewals](https://themachine.myapps.ai/markdown/use-cases/renewal-manager.md): Every day, a Machine agent finds accounts 90, 60 and 30 days from renewal, builds a packet on usage and value, drafts the outreach, and flags any at risk so the account owner can review.
- [How we give every applicant a fair first read](https://themachine.myapps.ai/markdown/use-cases/resume-triage.md): Each new application wakes an agent that checks the resume against the role's written rubric, quotes its evidence, and suggests interview times for strong fits. A person decides every case.
- [How we write first drafts of RFP responses](https://themachine.myapps.ai/markdown/use-cases/rfp-responder.md): Our RFP agent picks up each new request, breaks it into questions, answers them in a fresh Google Doc from our vetted library and product docs, and marks anything uncertain for a person to handle.
- [How we catch wasted SaaS spend](https://themachine.myapps.ai/markdown/use-cases/saas-spend-audit.md): Once a week our agent lines up card and bank charges with our subscription register and points out duplicate tools, idle seats, price rises and shadow IT. It suggests fixes and never cancels anything.
- [How we handle the follow-up after every sales call](https://themachine.myapps.ai/markdown/use-cases/sales-call-followup.md): The moment a call wraps, our agent writes the recap, updates the HubSpot deal and logs next steps in Linear. The recap email then waits for the rep to read and send it.
- [How we turn the pipeline into a forecast every week](https://themachine.myapps.ai/markdown/use-cases/sales-forecast.md): Each week our agent reads HubSpot's open deals, weights them into a forecast against quota by stage, rep and segment, names the deals slipping out of the quarter, and posts it to Slack. It only reads.
- [How we get security questionnaires drafted fast](https://themachine.myapps.ai/markdown/use-cases/security-questionnaire.md): Our agent breaks each incoming security questionnaire into questions, answers them in the vendor's own format from our vetted knowledge base, and marks anything uncertain for a person.
- [How we run day-to-day operations from a Slack thread](https://themachine.myapps.ai/markdown/use-cases/slack-control-pane.md): One agent you can call from Slack, with narrow access to our database, Stripe, Linear and GitHub. Describe the job in a thread and it carries it out across every tool involved.
- [How we turn our content calendar into social post drafts](https://themachine.myapps.ai/markdown/use-cases/social-scheduler.md): Each day our agent checks the Notion content calendar, writes posts suited to each platform for what is coming up, and parks them in Slack with their dates until a person approves and publishes.
- [How we run our standup as a Slack post](https://themachine.myapps.ai/markdown/use-cases/standup-summary.md): Each weekday an agent reads what everyone did in Linear and GitHub, nudges anyone whose day left no trace, and posts a short team standup to Slack. It never writes to either tool.
- [How we write help articles from tickets we've already solved](https://themachine.myapps.ai/markdown/use-cases/ticket-to-kb.md): Once a week an agent groups our resolved Plain tickets, spots the questions that keep coming back with no help article, drafts the biggest gaps from the real fixes, and opens one PR for a person to review.
- [How we build our roadmap from what users tell us](https://themachine.myapps.ai/markdown/use-cases/user-feedback.md): On a set schedule an agent collects feedback from support, public reviews and a Slack channel, sorts it into themes with real quotes and counts, and keeps a single Linear issue current for each theme.
- [How we get new vendors through onboarding](https://themachine.myapps.ai/markdown/use-cases/vendor-onboarding.md): Every day an agent checks new vendor requests in Gmail for a W-9, a banking form and a signed contract, logs each vendor in a Google Sheets register and flags gaps in Slack. It never approves or sets up payment.
- [How we get the weekly metrics report written for us](https://themachine.myapps.ai/markdown/use-cases/weekly-report.md): Our reporting agent is hooked up to our Postgres database and Slack. Each Monday it pulls the numbers, writes the weekly report with notes on what changed, and posts it to the team channel.
- [How we figure out why we win and lose deals](https://themachine.myapps.ai/markdown/use-cases/win-loss-analysis.md): Once a week our win-loss agent reads every HubSpot deal closed won or lost since its last run, then posts the patterns to Slack by segment, competitor, price and the stage where deals died.