Your automations, tailor-made
Your repetitive busywork handles itself. Describe it once in plain language, and Altmind takes it from there, on schedule or at the right moment.
Skill vs. automation: what's the difference?
They're easy to mix up. A skill is what to do. An automation is when to do it, on its own.
A reusable capability
A task you describe once, in plain language: "summarize this thread", "draft a reply in my voice." Run it anytime, by hand, from chat, or via the API.
- Written in plain language, versioned automatically.
- Cheaper to run: no re-explaining means fewer tokens each time.
- Uses your connected tools and shared memory.
A skill that runs on its own
Add a trigger to a skill, and it fires without you, on a schedule, an event, a message, or an API call.
- One trigger turns a skill into an automation.
- Runs in the background, on Altmind's schedule.
- Pause, edit or replay any run, anytime.
Trigger, steps, output: that's the whole shape
Every automation reads top to bottom. Something kicks it off, a few steps run in order with shared context, and a result lands wherever you asked. No diagrams to draw, no glue to wire.
- Trigger, the "when": schedule, event, message or API.
- Steps, the "do": read, think, act, using your tools.
- Output, the "where": a message, a doc, a stored note.
Four things every skill draws on
You don't configure these by hand. You mention them in plain language and Altmind wires them up. Knowing the four makes it easy to describe exactly what you want.
When it runs
A schedule (cron), an inbound message, a webhook event, or a direct API call. One skill can have several ways in.
What it can touch
Your connected apps: inbox, calendar, Sheets, Docs, Telegram and more. Skills act through the tools you've granted, nothing else.
What it remembers
Shared memory carries context between steps and across runs: your preferences, past decisions, the people and projects you work with.
What does the thinking
Choose a model per skill: a cheap one for triage, a frontier one for drafting. Bring your own key and there's no token ceiling.
If it speaks API or MCP, Altmind can automate it
Altmind acts through tools. Any service that exposes an API or an MCP server can be wired into a skill: your inbox, calendar, CRM, docs, databases or internal systems. If you can reach it programmatically, Altmind can automate it.
- Email, calendar, chat: Gmail, Telegram, and the apps you live in.
- CRMs, Sheets, Docs and storage: read, write, file away.
- Databases and your own internal APIs.
- Anything exposed over an MCP server, instantly in reach.
Some platforms gate their own API.
Social media is the classic case. Posting to Instagram or Facebook isn't as simple as "call the API." Meta only allows publishing from Professional accounts linked to a Facebook Page, through an app that has passed Meta's review with the right permissions. Personal accounts can't post at all. That's Meta's design, not a limit in Altmind.
The fix is the one every social tool uses: connect a compliant publishing service (a social-media scheduler like Upload-Post) that has already cleared Meta's requirements and exposes its own API. Altmind drives that tool, and your post goes out.
Rule of thumb: when a platform restricts automation, the limit lives in the platform, and the way through is a tool that bridges it.
Three sentences from idea to live automation
There's no builder to learn. You describe the outcome, confirm the trigger, and turn it on. Altmind handles compiling, scheduling and running it, and shows you each run so you can tune the wording.
- Edit the plain-language description anytime; it recompiles.
- Test on demand before you schedule it.
- Roll back to an earlier version in one click.
Nothing runs in the dark
Every run is recorded with its inputs, outputs and the steps it took. Inspect what happened, replay it with a tweak, or pause an automation entirely. Set a budget per skill so costs never surprise you.
- Full run log: inputs, outputs, tokens, timing.
- Replay any run, or pause an automation in one click.
- Per-skill budgets and cost across providers.
A few people set up on day one
Each is a single plain-language skill with a trigger attached. Copy the idea, change the words, make it yours.
Morning command center
Summarize inbox + calendar, flag what needs a reply, and push one message before you wake up.
Always-on triage
Every inbound email gets labeled, prioritized, and, if routine, auto-drafted in your voice.
Reporting on autopilot
Pull numbers from Sheets, write the narrative, drop a ready-to-share doc in Drive.
Catch every thought
Forward a voice note, photo or link from anywhere; it's transcribed, tagged and filed to memory.
Never drop a thread
Spot promises you made in email and nudge you (or draft the follow-up) before they slip.
Background research
Hand it a question; it gathers, cross-checks and returns a sourced brief to your vault.
Common questions
Do I need to write any code?
No. You describe what you want in plain language and Altmind compiles it into a running skill. Power users can still drop into the API and per-step settings for fine control when they want it.
What's the difference between a skill and an automation, really?
A skill is the capability: the thing to do. An automation is a skill with a trigger attached, so it runs on its own. The same skill can be run by hand and scheduled as an automation at the same time.
What can trigger an automation?
A schedule (like a cron time), an inbound message, a webhook event, or a direct API call. A single skill can be set up with more than one trigger.
Can I see and undo what an automation did?
Yes. Every run is logged with its inputs, outputs and steps. You can inspect it, replay it with a change, pause the automation, or roll the skill back to an earlier version.
Which model runs my skills?
Whichever you choose, per skill. Connect your own key for OpenAI, Anthropic, Gemini or a local model and run without a token ceiling. See For power users for the full picture.
Describe your first automation
One sentence in. A skill that runs itself out. Check the log whenever you're curious.