Enable Autopilot and Actionist will observe your screen over several weeks, learn your real workflows, and automatically build your entire workspace — agents, workflows, schedules, skills, and app connections — without a single form.
Enable Autopilot once. Actionist will observe your screen for several weeks, learn your real workflows, and build your entire workspace automatically — agents, schedules, skills, and app connections — with no configuration forms.
Every other tool makes you describe your workflows first.
That is a tax. Most people cannot accurately articulate their own work patterns — and no onboarding form captures the edge cases, real app sequences, and true priorities of how a person actually operates.
Without Autopilot
You fill out forms, describe workflows from memory, manually wire up agents, and still end up with a workspace that does not match how you actually work. Setup takes days. The result is a template, not your reality.
With Autopilot
You enable it once. Actionist watches you work for several weeks — passively, without interrupting anything — then builds the whole workspace from what it actually observed. Setup takes minutes of your attention.
Autopilot is coming soon and is not yet available in the app. This page documents the intended design so you know what to expect when it ships.
Autopilot will run quietly in the background — no prompts, no interruptions. A single recording indicator in the menu bar is all you will notice. Over several weeks it watches your screen, accumulating the raw signal that will become your workspace.
Observation window — illustrative
Wk 1
Wk 2
Wk 3
Wk 4
Build
morning email triage
Notion updates after standups
Slack mentions -> Linear tasks
Friday digest drafts
client follow-ups post-call
Linear status syncs
weekly report compile
Pattern chips above represent the kinds of repeated sequences Autopilot will identify. Specific workflows will reflect your actual behaviour, not these examples.
Passive by design. Autopilot will require macOS Screen Recording and Accessibility permissions, then run silently. Nothing is uploaded anywhere — all observation stays on your machine.
Representative period. A few weeks of ordinary work will produce richer agent configuration than a day of typical use. Vacation weeks or atypical crunch will skew patterns toward outlier behaviour.
Primary machine only. Autopilot will observe the device where it is running. Enable it on the machine where you do the majority of your real work.
Raw screen observations are not workflows yet. Actionist will process the signal in three passes — lifting sequences from noise, matching them against app context, then naming the patterns that repeat reliably. Pick a pass to see what each one finds.
observation stream — raw
09:07GmailOpened unread thread from Dana Voss
09:09GmailReplied with follow-up question, moved to Waiting label
09:11NotionUpdated deal status for Northwind in CRM page
09:13LinearCreated task: Send Q3 proposal to Northwind
09:14SlackPosted update in #sales-pipeline
Pass 1 captures every significant screen event with a timestamp and app context. No interpretation yet — just signal accumulation.
sequence extractor — pass 2
sequence detected · count: 11 occurrences
step 1GmailRead email from client contact
step 2GmailReply with follow-up question
step 3NotionUpdate deal record for that client
step 4LinearCreate follow-up task with deadline
Pass 2 clusters raw observations into repeating sequences. The same 4-step pattern appeared 11 times across 3 weeks — enough signal to become a workflow.
pattern namer — pass 3
workflow · draft complete
nameclient-email-follow-up
trigger”when a client email arrives and needs a response”
appsGmail, Notion CRM, Linear
stepsread → reply → update record → create task
Result: a named workflow with a precise trigger phrase, connected tools, and a concrete step sequence. Autopilot will generate this for every reliable pattern it identifies. You will review all of them before anything runs.
At the end of the observation period, Actionist will generate everything it takes to run your work — tuned to your real patterns, not a generic template. The workspace assembles itself from the signals it collected.
Agents
AI employees matched to your observed roles, pre-configured with tools and instructions
Workflows
Repeatable multi-step processes derived from sequences you run again and again
Schedules
Recurring jobs built from your timing patterns — daily reports, weekly sweeps
Skills
Reusable named actions extracted from your workflows, ready across multiple agents
App connections
Connections to apps Actionist sees you using — Slack, Notion, Linear, and more
Everything Autopilot will generate is a full Actionist object. Open any agent, workflow, or schedule in the studio after the observation period and adjust, extend, or delete freely.
After watching a month of ordinary work, Autopilot will surface the sequences you repeat on autopilot and turn each one into a live agent or workflow — ready for you to review before anything runs.
Maya · Marketing Manager
It will notice a Friday afternoon compile-and-send sequence — Gmail drafts pulled from Notion metrics, formatted, and distributed to 12 stakeholders — repeated every week for four weeks. It will build a scheduled Friday-digest agent that drafts the report at 16:00, surfaces it for one-click approval, and sends on confirm.
will save ~90 min/wk
Felix · Finance & Ops
It will notice the same vendor portal navigation — open browser, log in, locate the invoice table, copy three fields into a spreadsheet — done manually 8 times across the month. It will build a Computer Use workflow that navigates the portal, extracts the fields, and writes them to the sheet without any manual steps.
will save ~40 min/wk
Sam · Solo founder
It will notice a morning inbox triage pattern — open Gmail, flag anything from leads, move newsletters to a folder, reply to support threads with a standard acknowledgement — run every weekday before 09:30. It will build a morning digest agent that triages the inbox by 08:45, surfaces a prioritised summary, and queues draft replies for review.
The steps below describe the intended flow. UI labels and button names will be confirmed when the feature ships.
Install the Actionist desktop app
Autopilot will require the macOS desktop app — screen observation is a desktop-only capability. Download from the dashboard and sign in.
Enable Autopilot
During or after sign-in, Actionist will present an option to enable Autopilot. Enabling it will start the observation session.
Grant Screen Recording and Accessibility permissions
Autopilot will need two macOS permissions before observation can begin. If they are not already granted, Actionist will walk you through the permission screens. See granting permissions below for the exact steps.
Work normally for several weeks
Autopilot will run quietly in the background — no interruptions, no prompts. Use Actionist on your primary machine during a representative period of your normal work.
Review your generated workspace
When the observation period ends, Actionist will notify you that your workspace is ready. Every object it creates will be editable — Autopilot will generate a starting point, not a locked configuration.
Actionist — onboarding
Enable Autopilot
Actionist will learn your workflows by watching you work for a few weeks, then build your workspace automatically.
Autopilot will need two macOS permissions — Screen Recording and Accessibility. These are the same permissions Actionist uses for Computer Use today. If you have already granted them, you are all set.
Screen Recording
Sees what is on screen — the raw visual signal Autopilot analyses
Accessibility
Reads UI element labels, turning raw screen content into meaningful workflow context
Grant Screen Recording
In the sidebar, open Settings > Permissions. Find the Screen Recording row and click Grant access. macOS will open System Settings > Privacy & Security > Screen Recording — toggle Actionist on. Return to the app and the row will show a green indicator.
Grant Accessibility
Still in Settings > Permissions, find the Accessibility row and click Grant access. macOS will open System Settings > Privacy & Security > Accessibility — enable the toggle next to Actionist (your macOS password may be required). Return to the app and confirm both rows are green.The toast “Permissions granted! All system features are now active.” confirms both permissions are active.
Settings — Permissions
Screen Recording
Required for Autopilot and Computer Use
Granted
Accessibility
Required for Autopilot and Computer Use
Granted
Both Screen Recording and Accessibility must be granted before Autopilot can begin. Granting only one of the two will prevent the observation session from starting.
A week of vacation or an atypical crunch will shape agents around outlier behaviour. A few ordinary weeks of everyday work give Actionist the patterns that actually matter.
Grant both permissions before you start
Screen Recording sees what is on screen; Accessibility reads UI element labels that turn raw screen content into meaningful workflow context. Both are required — neither alone is sufficient.
Enable it on your primary machine
Autopilot will only observe the device where it is running. Choose the machine where you do the majority of your real work — a secondary laptop will produce a partial picture.
Let the full observation window run
A longer window means more patterns identified. A full month will produce richer workflows and more accurate agent configuration than a single week of use.
Everything it creates is editable
Auto-generated agents, workflows, and schedules are full Actionist objects. Open any of them in the studio after the period and adjust, extend, or delete freely — Autopilot generates a starting point.
Autopilot will be available on the macOS desktop app. Screen observation is not available in the web app. Platform availability at launch is still being confirmed.
Vision page
This is a vision page. Autopilot has not shipped yet. The flows, UI labels, and timings described here reflect the intended design as confirmed by the Actionist team. Exact button names, observation window duration, recording storage handling, and platform scope will be updated when the feature releases. All capability claims use future tense intentionally.
