No passwords to create. No configuration menus to navigate. Click one button, complete sign-in in your browser, and you are describing a task to an agent who already knows how to act on it.
Actionist delegates authentication entirely to your browser. No new password. Your browser’s existing session — including MFA, passkeys, and social login — does the work. The animation below shows every step as it happens.
Waiting for browser…
Sign-in page open in your default browser
Connection Successful
Navigating to Home screen…
actionist.ai / auth / desktop
browser · auth started
—Checking your session…
session found
—Creating desktop sign-in ticket…
ticket created
—Sending sign-in ticket to Actionist…
ticket delivered
desktop app · Generating secure token…
—Connection Successful
—You can close this tab.
Your browser’s existing session handles everything — MFA, passkeys, and social login all carry through.
If the app detects your existing browser session, it skips opening the browser entirely — you land on Home without any extra steps.
If the window expires, click Cancel on the waiting screen and try again. Brave, Safari, or Firefox users may need to click a button on the auth page to complete delivery manually.
The sign-in window times out after 5 minutes. If it expires, click Cancel on the waiting screen and try again. If your browser (Brave, Safari, or Firefox) does not hand the ticket back automatically, look for a button on the authentication page and click it to complete delivery manually.
When Actionist detects that macOS permissions are missing, a modal appears automatically. These two permissions are what let Actionist control apps on your behalf — without them, automation features are unavailable.
Screen Recording
Allows Actionist to see your screen — required for Computer Use and vision-driven automation.
Accessibility
Allows Actionist to control UI elements — required to interact with on-screen apps on your behalf.
Can skip for now
Chat, scheduling, memory, and all app integrations work immediately. Only Computer Use requires these permissions.
Grant on first launch
Grant later in Settings
The permissions modal appears automatically when you land on the Home screen for the first time. It shows two rows:
Permission
What it does
Screen Recording
Allows Actionist to see your screen
Accessibility
Allows Actionist to control UI elements
Click Grant access on each row. macOS opens System Settings to the relevant pane. Toggle the switch next to Actionist and return to the app. Once both are granted, click Continue.
Permissions required
Actionist needs access to run automations on your Mac.
Screen Recording
Allows Actionist to see your screen
Grant access
Accessibility
Allows Actionist to control UI elements
Grant access
Critical permissions required to continue
Skip for now
Continue
The modal has a “Skip for now” button. You can defer and still use the app — chat, scheduling, and memory all work immediately. Only Computer Use and screen-based automation require these permissions.To grant them later: open Settings from the left sidebar, navigate to Permissions, and click Grant access next to each item.
The permissions modal reappears each time you return to the Home screen until both permissions are granted. Click Skip for now to dismiss it without granting.
Home is where every task begins. One composer, any agent, live visibility into what is running — everything without leaving the screen. Select a zone to explore it.
What should Actionist handle today?
Choose an agent, describe the result, and let Actionist run it.
Working with Maya
Ask Maya to…
Send · new line
Agents running in the background now
M
Summarize weekly digest
Maya · 2 min ago
A
Follow up with Northwind
Alex · 5 min ago
Chats
Upcoming
Search conversations…
M
Maya
Done. The digest is ready…
2m
A
Alex
Sent follow-up to Dana Voss
7m
R
Riley
Invoice #2041 escalated
1h
Today
Daily digest · Maya
17:00
Invoice chase · Riley
18:30
The composer card
The dark frosted card in the center of the screen. It is the single launch point for any task on any agent. The “Working with” pill at the top shows the current agent — click it to switch. The textarea below shows the placeholder “Ask [name] to…”. Type your task and press Enter to send; Shift+Enter adds a new line. The gradient send button is disabled until you type something.Clicking the pill opens the agent picker. It lists all your enabled agents — each row shows the agent’s avatar, name, and role subtitle. Click any agent to select it; the picker closes and the placeholder updates. If you have no agents yet, the picker shows “Build an agent” with the hint “Create your first agent to get started.” Clicking it navigates to the Agents page.
What should Actionist handle today?
Choose an agent, describe the result, and let Actionist run it.
Working with Maya
Ask Maya to…
Return to send · Shift+Return for new line
Background agents section
Below the composer: a live section that shows every agent run currently executing in the background. A green pulsing dot in the section header means at least one agent is active right now. A dim white dot means idle; the empty state reads “No agents running in the background”. Each active row shows the agent’s avatar, the task name, the agent name and relative time, and a spinning green ring. The empty-state hint is: “Schedule an agent and its background runs will show up here.”
Agents running in the background now
M
Summarize weekly digest
Maya · 2 min ago
A
Follow up with Northwind
Alex · 5 min ago
Chats tab
The right sidebar has two tabs. Chats (shown with a live count badge) lists every conversation, most recent first. A search bar at the top accepts free text: “Search conversations…”. The filter button opens a popover with two multi-select groups: SOURCE (Desktop / Telegram / Slack) and AGENT. Active filters show as chips below the search bar with a Clear link. Each conversation row shows the agent avatar, a small source dot, the peer label (“Me” for desktop sessions), the agent name, relative time, and a two-line message preview. Clicking a row reopens that conversation in a floating chat window.
The Chats tab is a record, not a launcher. Clicking a row reopens an existing conversation — it does not start a new one. To start fresh, use the composer and send a new task.
Upcoming tab
The Upcoming tab (with its own count badge) shows every scheduled agent run within the next 60 days, grouped into TODAY, TOMORROW, and LATER. A TRIGGERS section appears when trigger-based schedules are active. Times come from the calendar-events API so they reflect per-occurrence accuracy — not the raw schedule definition. If nothing is scheduled yet, the tab shows “Nothing scheduled.”
Scheduled runs beyond 60 days are not shown until they move inside that window.
Sam runs his solo business from a single inbox. Here is exactly what happened the first time he typed a task.
S
@sam_actionist_bot
ONLINE
Triage my inbox — flag anything urgent, archive newsletters, and give me a summary of what needs a reply today.
09:07
SEEN · READING CONTEXT
TOOL · LIST_EMAILS
Scanned 34 unread emails. Found 3 that need a reply today, archived 11 newsletters, and flagged 1 message from your accountant as urgent.
09:07
TOOL · APPLY_LABELS
Reply today — Northwind contract (due Friday), investor update request, and a support escalation from Priya’s team. Urgent — Q2 invoice from your accountant needs approval before end of day.
09:08
This is the whole loop in sixty seconds. Follow it once and the rest of the app makes sense.
Home
Working with Maya
Summarize the three most recent items in our Slack #announcements channel and draft a short email I can send to the team.
tool · mcp_slack_list_messages
mayaReading #announcements… found 3 recent posts.
tool · mcp_slack_get_message ×3
mayaSummarized. Drafting your email now.
mayaSubject: Team announcements — this week
mayaThree highlights attached. Ready to send or edit.
Task complete — conversation saved to Chats
Check the welcome header
Home loads with the heading “What should Actionist handle today?” and the subtitle “Choose an agent, describe the result, and let Actionist run it.” The composer card is centered below.
Choose your agent
Look at the “Working with” pill at the top of the composer. If the right agent is already selected, skip this step. If not, click the pill, find your agent in the dropdown, and click it. The textarea placeholder updates to “Ask [name] to…”.
Only enabled agents appear in the picker. If an agent you expect is missing, open Agents in the left sidebar and check whether it has been disabled.
Describe the task
Click inside the textarea and type what you want the agent to do. Be direct — describe the outcome, not the steps. For example:
“Summarize the three most recent items in our Slack #announcements channel and draft a short email I can send to the team.”
Use Shift+Enter to add a new line if your task needs more than one sentence.
Send it
Press Enter (or click the gradient send button). The textarea clears and a floating chat window opens beside the Home screen, showing your agent’s response building in real time.
Watch the background section update
While the agent runs, the BackgroundAgentsSection shows it as an active row — green pulsing dot, spinning ring, task name. When the run finishes, the section returns to idle.
Find the conversation in Chats
Every task you send creates a permanent record. Open the Chats tab in the right sidebar to find it. Search or filter by source or agent whenever your history grows.
You have sent your first task. The agent handled the work; the conversation is saved; the app is ready for the next one.
On your first launch, a floating assistant called Pip appears and guides you through a five-turn setup wizard. Answer each prompt and you will have a working agent set configured before your first task.
Pip · setup wizard
pip · first launch
pipHi — I’m Pip. Let’s get your workspace ready. What’s your company name?
youNorthwind Trading
pipGot it. Want me to create a starter set — a receptionist, a support agent, and an executive assistant?
youYes please.
pipDone — 3 agents created. Want to connect Telegram or Slack so they can reach you outside the app?
pipYou’re all set. Tap the composer to send your first task.
What Pip asks
Your company name.
Whether to create a starter agent set: a receptionist, a customer-support agent, and an executive assistant.
Whether to connect Telegram or Slack so agents can reach you outside the app.
Your preference for proactive nudges.
A brief tip and a “Got it” to finish.
What you get
A named workspace, up to three pre-configured starter agents, and optionally a messaging channel connected — all before you type a single prompt. Skip any step and configure it manually later.
If you arrived at Actionist through the demo at demo.actionist.ai, your personalised context from that session is applied automatically after sign-in.
The agent picker only shows enabled agents. If an agent you created is missing from the list, navigate to Agents in the left sidebar and look for a disabled toggle next to its name. Re-enable it and it will appear in the picker immediately.
The sidebar width resets every time I restart
The sidebar width (default 300 px, drag to resize between 240 px and 420 px) is session-only — it is not saved when the app closes. Drag the resize handle to your preferred width each session. This is expected behavior.
Clicking a Chats row opened the old conversation, not a new one
That is intentional. The Chats tab is a history viewer — clicking a row reopens the existing conversation thread. To start a fresh task with the same agent, go back to the composer, type your new task, and send it. A new conversation is created automatically.
How do I know if an agent is actively running?
The green pulsing dot in the BackgroundAgentsSection header is your ambient signal. Green and glowing = at least one agent is running right now. Dim white = nothing is active. You do not need to open any other panel to check.
I filtered by source and agent but got unexpected results
The conversation filter uses AND logic across the two groups (Source and Agent) and OR logic within each group. Selecting “Telegram” under Source and “Alice” under Agent shows only Alice’s Telegram conversations — not all Telegram conversations and not all Alice conversations. To clear filters, click the Clear link that appears below the search bar.
I skipped permissions — what still works?
Skipping macOS permissions at first launch is fine. Chat, scheduling, memory, and all app integrations work immediately without them. The only features that require Screen Recording and Accessibility are Computer Use (vision-driven screen automation). The permissions modal reappears each time you visit the Home screen until both are granted. You can also grant them any time from Settings → Permissions.
No passwords. No configuration menus. One click, one browser window, you’re in.
macOS desktop app · Browser-delegated auth · Permissions always skippable