Mast runs your business. While you sleep.
An AI teammate that learns your business, finds customers, creates and optimizes ads and social media content, books your meetings, drafts the work, and ships real products on its own. Lives on your domain, in your Slack, on your phone.
hey @mast draft a follow-up for Acme? went quiet after the 4/12 call
Drafted 3 versions. Recommend B — the Acme-style case study they asked for on 4/12.
A teammate who actually does the work.
Mast isn't a chatbot you ask things. It picks up tickets, drafts memos, sends follow-ups, reconciles books — across every tool you already use. You review. Mast ships.
Drafts replies in your voice. Books meetings, reschedules conflicts, prepares you for every call.
Sequences cold and warm leads across channels. Enriches firmographics, personalizes by role.
Triages tickets, writes empathetic first-responses, resolves within policy. Escalates edge cases with a recommendation.
Reconciles ledgers, chases AR, drafts the Monday update. Notices when something looks weird before you do.
Reads JDs, screens applicants, schedules interviews. Never lets a thank-you note go unsent.
Teach Mast a new skill with a job description. Give it tools, policies, a memory store. Starts junior, gets senior fast.
Mast lives where your team works.
Mast gets its own email address and shows up in every channel your team uses. One memory across all of them — it remembers the thread no matter where it started.
Just @ Mast in Slack.
Tag Mast in any channel and tell it what you need. It comes back with a finished thing — a draft, a doc, a calendar invite — not a chatbot reply.
hey @mast can you draft a follow-up for the Acme deal? they went quiet after the call last week
On it. Pulling thread context + your 4/12 call notes…
Drafted 3 versions, each picking up from where you left off on the 4/12 call:
Names the next step explicitly. Best if they're decision-ready.
Sends the Acme-style case study before the ask. Matches their 4/12 request.
Short, low pressure. Use if you want to keep it warm without pushing.
💡Recommended: Draft B — they asked for a case study on the 4/12 call
Pick the brain behind Mast.
Bring your own model — or connect your existing ChatGPT subscription and don't pay twice. Mast can switch models per task: cheap for triage, sharp for memos.
Sign in with ChatGPT. Routes through your Plus, Pro, or Team credits.
Bring your Anthropic key. Sonnet, Haiku, Opus.
Bring your OpenAI key. GPT-5 and reasoning models.
Bring your xAI key. Grok-4 reasoning.
Locked down before it wakes up.
Mast runs in its own isolated cloud VM, authenticates through OAuth scopes you grant, and only touches the tools you explicitly allow.
Mast runs on a dedicated cloud VM. No shared filesystem, no noisy neighbors. Memory and state are scoped to your workspace.
Mast authenticates to your tools through OAuth scopes you approve. It never sees API keys, never stores passwords.
Choose exactly which actions each integration exposes. Mast can read Gmail but only send to allowed domains.
It learns by working with you.
Mast doesn't ship with a fixed playbook. It watches how you handle things, picks up your voice, and turns one-off tasks into repeatable workflows — without you writing a single prompt.
Edit a draft once and Mast mirrors it next time. It studies the changes you make — not the settings you don't.
Handle the same kind of task a few times and Mast offers to take it over. You stay in the approval loop until you don't need to be.
Your refund cap, meeting preferences, tone with VIPs — all learned from past calls. No config file, no rules engine.
Heads up — you've handled the "deal stuck > 14 days" follow-up three times this week, each one about ~85% the same. Want me to draft these in your voice and ping you for approval before they go out?
It gets sharper every week.
Every edit, every approval, every "actually, do it this way" — Mast remembers and applies next time. No prompts to maintain, no settings to tweak. You work, it learns.
Simple pricing. Pay for what you use.
Flat base — Mast runs 24/7 on every channel. Credits cover what actually consumes resources: LLM tokens, voice, image gen. Top up anytime, never expires. Bring your own keys to skip LLM credits.
Per workspace. Cancel anytime.
- Mast on every channel — email, Slack, iOS, web
- Unlimited threads, tasks, and team members
- Persistent memory across every conversation
- All integrations + tool approvals
- Audit log + human-in-the-loop controls
Top up in packs from $10 to $500. Credits never expire.
- LLM tokensClaude, GPT, Grok — at-cost pass-through.
- VoiceSpeech-to-text and synthesis on the iOS app.
- Image generationWhen Mast creates or edits visuals.
- Premium toolsWeb search, enrichment, document parsing.
Frequently asked questions
Mast is an AI teammate, not a tool. You hire it like you'd hire a coworker — it gets a name, a dedicated inbox, access to your tools, and a memory of every conversation. It runs 24/7 and ships real work: drafted emails, resolved tickets, reconciled books, scheduled calls.
Mast runs on its own dedicated cloud VM with a persistent execution loop. It wakes on a schedule or in response to triggers (new email, calendar event, CRM update), executes its tasks, and goes back to sleep. State persists across every session via the mast memory engine.
Yes. All data is encrypted at rest and in transit. Mast's memory is isolated per workspace. We never train on your data. You can revoke any integration and wipe its memory at any time.
Your pick. Mast works with Anthropic (Claude Sonnet, Opus, Haiku), OpenAI (GPT-5 family and reasoning models), and xAI (Grok-4). It can switch models per task — cheap models for triage, sharp ones for memos. You can also connect your existing ChatGPT subscription so it routes through your Plus/Pro/Team credits.
Mast proposes actions before executing them. You review and approve or reject each one — sending an email, updating a record, scheduling a meeting. Nothing leaves your workspace without your explicit approval.
Yes. Mast is shared across your workspace. Anyone on the team can @-mention it in Slack, email it, or hand it a task. It remembers every conversation so context carries between teammates.
Mast is $50 per month per workspace, plus credits for usage. The base covers unlimited threads, all channels, memory, and integrations. Credits ($1 each, never expire) cover LLM tokens, voice, image generation, and premium tools. Bring your own model keys to skip LLM credit charges entirely.
No — Mast runs on system keys by default and you pay only in credits. If you'd rather, you can connect your own OpenAI, Anthropic, or xAI keys (or your ChatGPT subscription) and skip the LLM credit charges entirely. Switch any time from settings.
Join the Mast waitlist.
We're onboarding pilot customers in small waves. Drop your work email and we'll reach out when a spot opens up.