YOUR AI WORKFORCE
Hire your first AI employee in under an hour.
Give each agent its own role, tools, memory, and channels. Agents keep the business running while you focus on the interesting problems.
Maya · MarketingReceptionistCustomer SupportSales AssistantExecutive Assistant
The idea
Not a chatbot. An employee.
A chatbot waits to be asked. An Actionist agent has a role, a routine, and the tools to finish the job.
A chatbot answers
It responds when you type, forgets when you close the tab, and can’t touch your tools, files, or customers. Every task starts from zero.
An Actionist agent acts
It owns a role, remembers across conversations, uses your real tools through , runs on a schedule, and escalates only when it’s genuinely stuck. Not when it’s unsure.
Agents are AI employees. They have working hours and daily routines, proactively pick up work from their tools, collaborate with each other through delegation, remember context across conversations, and escalate when stuck, not when unsure.
Follow one example
Meet Maya.
To make this concrete, we’ll build one agent and follow her through the whole page, from a blank studio to a full working day.
Maya · Marketing Manager
Owns marketing operations end to end: checks analytics every morning, monitors competitors, drafts content for review, and reports daily. Never publishes without sign-off, never approves ad spend over a threshold without you. By the end of this page she’s a real, scheduled, supervised employee.
Anatomy
What makes an agent.
Every agent is three things: who it is, what it can do, and how it’s governed. Assemble Maya layer by layer. Click through the three layers and watch her agent card build up.
MayaMarketing Manager
identity · instructions · soul · model slot
Owns marketing ops end to endNever publishes without sign-offVoice: data-informed, zero hypeModel slot: Default
tools · skills · memory · channels
File ManagementBrowserAnalytics MCPSkill: brand-contentMemory: Global readTelegram bot
approval · collaborators · schedule
Guarded autoDelegates to: Designer agentWeekdays 09:00Trigger: webhook
draft · has an identity, can’t act yetcapable · armed with tools, ungoverneddeployable · scoped, supervised, scheduled
Identity
Name, role, and a one-line description: what teammates see in Slack, Telegram, and the agent directory. Maya, Marketing Manager.
Instructions
The system prompt the agent runs under: what it always does, what it never does, and the tone it uses.
Soul
Short, vivid prose the model uses as a voice reference. This shapes personality, not behavior.
Model slot
Which brain the agent runs on. Actionist assigns a capable default, and the slot exists so model routing can be changed or tested without touching the agent’s instructions.
Tools
The built-in group holds dozens of actions: File Management, , Send Message, Ask User, Search Memory, Read Memory, Spawn Sub-Agent, Delegate Task, Manage Delegations. Scope each one on or off per agent.
Skills
Portable behavior packs: instructions plus a curated tool subset. Install from the catalogue, toggle per agent.
Memory
Global memory plus any knowledge corpus in the workspace, each set to Read, Read/Write, or No access.
Channels
Where the agent talks: the Actionist app, a Telegram bot, a Slack workspace. Each agent can own its own bot.
Approval mode
How much the agent does on its own versus pausing for your sign-off. Supervision you dial in. The full dial is below.
Collaborators
The other agents this one may delegate to, or hand a whole conversation off to.
Schedule & triggers
One-off and recurring jobs plus event triggers. The agent shows up to work without being asked.
The craft
Write the brain.
Instructions decide what an agent does. Soul decides how it sounds. Keep them separate and both stay sharp. Here’s Maya’s:
The readiness checklist, live.
The studio’s Identity tab grades your draft against four checks before it calls the agent deployable. Toggle between a first draft and Maya’s final config to see what each check wants:
Name✓
Maya, under 30 characters✓ Maya, under 30 charactersRole✗
assistant. Too generic; the check wants a specific role✓ Marketing Manager: specific, not “assistant”Instructions✗
“Help with marketing.”. 21 characters; needs over 200✓ the full always / never / escalate block above, 412 charactersSoul✗ empty. The check wants a voice of over 40 characters✓ “Creative, data-informed, genuinely excited about growth…“
1 of 4 checks passing, the studio flags this agent as not ready.4 of 4 checks passing. Deployable. This is the bar every agent should clear before its first scheduled run.
The studio
The studio, tab by tab.
Whichever path you took, every agent is tuned in the same place. Click a tab to see what it controls.
Identity
Name, role, description, Instructions, and an optional Soul. A live preview and readiness checklist confirm the agent is deployable. It checks: Name under 30 characters; Role is specific (not “assistant”); Instructions longer than 200 characters; Soul describes a voice (over 40 characters). You can also personalize the avatar: click the pencil badge on hover to choose a shape and color applied workspace-wide.
Maya · Marketing Manager
Tools
Expand Built-in Tools and you get the full group: File Management, Browser, Send Message, Ask User, Search Memory, Read Memory, Spawn Sub-Agent, Delegate Task, Manage Delegations, and more. In the tested workspace the built-in group listed 38 tools. Each is toggleable per agent, and MCP servers and skills add more on top. The global approval mode sets the default; per-tool overrides let you trust the safe tools and gate the risky ones.
approval mode lives here
Skills
Portable behavior packs: instructions plus a curated tool subset. A behavior you perfected on one agent becomes reusable across your whole workforce. Enable it under Apps → Skills globally, then wire it here per agent.
key icon appears when credentials are needed
Memory
Permissioned per scope. Every workspace has Global memory, and a Knowledge corpus appears alongside it once one is configured. Each scope is set to Read, Read/Write, or No access. Memory instructions tell the Memory Agent what’s worth keeping, so the agent sharpens over time instead of forgetting.
brain icon
Channels
Bind the agent to a Telegram bot or a Slack workspace. Each agent can have its own bot, or share a company-level Slack app and route by mention name. Tokens are stored encrypted in your workspace vault, only this agent can read them.
encrypted vault tokens
Collaboration
List the agents this one can delegate to. A manager agent can hand a task to a specialist, or hand off the whole conversation so the specialist talks to the user directly. Recent delegations and hand-offs show here so you can trace who did what.
delegate_task and hand_off tools
Schedule
Give the agent a heartbeat. Scheduled jobs run recurring work, like Maya’s 9am analytics check. Recurrence is built from structured controls rather than cron: pick Daily, Weekly, Monthly, Yearly, Hourly, or Every N minutes, set the interval, and choose when it ends. Set the timezone once and the schedule stays anchored to it.
Weekly · every 1 week · Mon-Fri 09:00
Triggers
Fire the agent on external events: an inbound webhook, a new Slack message, an email arriving, or another agent completing a task. Triggers let the agent react to the world without polling.
webhook · email · agent-complete
Runs
A per-agent run history. Every run this agent has taken (status, start time, duration, and tool calls) scoped so you can audit its track record without wading through workspace-wide logs. Use it to spot patterns: why a scheduled job failed last Tuesday, which tool call took the longest.
status · duration · tool calls
Settings
Enable or disable the agent, set a Critical Reminder (up to 400 characters) prepended to every turn, and find the danger zone. Deleting an agent requires typing its name and can’t be undone.
critical reminder · danger zone
Get started
Three ways to create one.
Open Agents in the sidebar, hit New agent, and pick the path that fits.
Describe what you need; the assistant configures tools, memory, and channels as you chat. Best when you know the job, not the settings. Watch Maya get built:
youA marketing manager that checks analytics every morning, drafts content for review, and reports daily. Never publishes without my sign-off.
designing identity
aiMeet Maya, Marketing Manager. I’ve drafted her instructions with your sign-off rule as a hard “never”. Tools she’ll need:
Analytics MCPFile ManagementBrowserTelegram
youAdd a $500 ad-spend approval threshold.
aiAdded under “You never”: approve ad spend over $500 without approval. Anything else?
saved · maya appears under My Agents
aiDone. Open her in the studio anytime to fine-tune.
Do the job once yourself while Actionist records it, then turn the recording into an agent. Best when the work is easier to demonstrate than to describe, and when the steps live in a tool with no clean API.
How it works
Start the recorder, complete the task the way you normally would, and stop. Actionist reads the captured steps and proposes an agent built around them, which you then review and adjust in the studio like any other agent.
One recording, two outputs
The same Record process flow can produce either an agent or a skill. Choose an agent when the work needs its own role and schedule; choose a skill when it is a behavior you want several agents to share.
Manual setup
Start with a blank agent in the studio and configure identity, tools, and skills yourself. Best when you know exactly what you want. Every tab from the explorer above is yours from the first second, and the readiness checklist keeps score as you go.
Already know the role? Open the Templates tab from the Agents list view to browse 8 pre-wired role templates and open one directly in the studio, no chooser needed.
Create agent
Recommended
◆
AI-guided setup
Describe the job: the assistant configures tools, memory, and channels as you chat.
●
Record to Build
Do the task once while Actionist records it, then turn the recording into an agent.
⊞
Manual setup
Start with a blank agent in the studio and configure each setting yourself.
The recommended path: build Maya with AI-guided setup
Open the Agent creator
Choose AI-guided setup. The Agent creator opens, “Chat to design your agent — refine identity, tools, and skills step by step."
Describe the job
Refine by chatting
The assistant proposes Maya’s name, role, instructions, tools, and memory access. Tap a suggestion or type your own until it’s right.
Save and open
Maya is saved and appears under My Agents. Open her in the studio anytime to fine-tune tools, skills, schedule, and memory.
Trust
Supervision is a dial, not a switch.
Start every agent cautious. Loosen the leash one notch at a time as it earns your trust. Select a mode below to see which action classes auto-execute and which pause for your sign-off.
Suggest: Maya proposes every tool call and you run them manually. Maximum oversight. Start here while you learn what an agent will do.
Ask each time: Maya requires your approval before every tool execution. Nothing happens without an explicit yes.
Guarded auto: Maya runs safe reads and writes automatically; sensitive writes and anything destructive pause for your sign-off. The sweet spot for most production agents.
Full auto: Maya runs every tool without prompting. Fast and hands-off, for agents you’ve already learned to trust. Destructive actions still always prompt; this floor cannot be removed.
Action class behavior in this mode
Readmanualpromptauto-executeauto-executeSearch memory, read files, fetch URLs
Safe writemanualpromptauto-executeauto-executeDraft saves, memory writes, internal notes
Sensitive writemanualpromptpromptauto-executeSend email, post to Slack, create CRM records
Destructivemanualpromptalways promptalways promptDelete files, cancel subscriptions, drop records
Even in Full auto, any action flagged as destructive always prompts for approval. This floor cannot be removed, so you can never accidentally authorize a silent delete.
Templates
Start from a role, not a blank page.
The Templates tab holds eight role templates, each prewired with identity, tools, and skills. Adjust everything before saving.
Receptionist
Greets visitors, answers FAQs, and routes people to the right specialist.
Customer Support
Handles tickets end to end and escalates the ones that need a human.
Sales Assistant
Qualifies leads and runs the follow-ups that usually slip through the cracks.
CRM Manager
Keeps accounts, contacts, and deals clean and up to date.
Technical Lead
Provides engineering oversight and keeps delivery on track.
Developer Agent
Generates and debugs code against your stack and conventions.
Operations Assistant
Automates the recurring process work that runs the business.
Executive Assistant
Triages email, manages the calendar, and coordinates across people.
More roles
More seats you can fill today.
Maya is one example. The same pattern (role, tools, schedule, supervision) works for every function in the business.
Dario · Sales
Each morning Dario pulls the CRM, identifies deals with no activity in 5+ days, drafts personalised follow-up emails for each one, and queues them for your review. Replies that come in during the day are logged against the right deal automatically, no manual data entry.
saves ~3 hrs/day on pipeline hygiene
Priya · Support lead
Priya watches the support queue, classifies and triages each ticket against your policy docs, resolves the clear-cut ones directly, and surfaces the edge cases with a recommended action. Agents on Guarded auto: she never changes a subscription without your sign-off.
saves ~5 hrs/day on first-touch resolution
Felix · Finance and Ops
Felix runs a weekday close: pulls invoices from the inbox, reconciles against the ledger, flags any mismatch above a set threshold, and drops a one-page cash-flow summary into the shared drive before 08:00. Nothing is posted without an approval gate.
saves ~2 hrs/day on reconciliation and reporting
One agent rarely owns the whole outcome.
A manager agent delegates to specialists, runs them in parallel, and assembles the result. The pulse below shows delegation flowing from you through the manager to three specialist agents.
delegation flow
YouSend the task. The manager handles the rest.
Manager agentBreaks the work into parallel sub-tasks.
delegate_taskEach specialist receives scoped instructions and tools.
Assembled resultThe manager merges the outputs and reports back.
Generates and tests code against your stack.
Runs acceptance tests and flags regressions.
spawn_subagent, spawns with a fork context for long-running analysis.
A product-manager agent can take a feature from spec to shipped: it delegates the build to a developer agent, the testing to a QA agent, and the deploy to an operations agent, coordinating the whole team in parallel. A solo founder ships like a full team.
Before and after
Tuesday, before and after Maya.
The same marketing responsibilities, two very different mornings.
Before · the manual grind
08:55Open four browser tabs, wait for dashboards to load.
09:10Copy yesterday’s numbers into the weekly spreadsheet by hand.
09:28Write standup update from memory, three Slack threads deep.
10:05Draft a launch post, then spend 20 minutes checking brand-voice guidelines.
11:30Realize the anomaly from Monday was never followed up on.
14:00Pull the campaign report. Discover it needs a manual CSV merge.
17:00Forget to escalate the ad-spend decision before end of day.
After · what you actually do now
Review Maya’s 09:00 analytics brief and flag one decision that needs you.
Approve or tweak the launch post draft she held for sign-off.
Respond to the escalated ad-spend question she surfaced by 17:00.
schedule · daily-analytics · 09:00
09:00Pulled yesterday’s analytics. Signup rate down 24%: flagged with likely cause (landing page variant B).
09:01Posted to #marketing-daily. Awaiting your response before any campaign changes.
schedule · standup · 09:30
09:30Standup sent: what shipped, what’s blocked, what she’s picking up today: in her own voice, by design.
schedule · midday-sweep · 13:00
13:00Checked campaign performance. Drafted launch post for Product Hunt: held for your review, never auto-published.
schedule · eod-report · 17:00
17:00Day summary sent. Budget decision escalated, ad spend approval needed for Tuesday push.
17:00Everything else wrapped. No surprises.
Nobody tells her to start. The schedule fires automatically. She shows up, does the work, and reports back.
Never auto-publishes. Approval mode is set to Guarded auto: content drafts wait for your explicit sign-off before anything ships.
Escalates budget calls. Instructions say never approve ad spend over $500 without you, so she doesn’t, and flags it clearly.
That’s one agent. Now imagine the support, sales, and operations seats filled too.
The same agent runs everywhere.
In the web app or desktop
Pick an agent from the chat selector and work side by side. Every step, tool call, and screenshot streams live.
As a Telegram or Slack bot
Bind a bot and the agent answers your team where they already are: DMs, channels, threads, mentions.
On a schedule or trigger
Recurring jobs and event triggers mean the agent shows up without anyone asking it to.
Unattended in the cloud
Headless Runtime keeps agents firing when your laptop is closed: local, cloud, or hybrid.
States and controls
Why a control might not be there.
Much of Agent Studio is conditional. A tab or option that is missing usually means a prerequisite is unmet rather than that the feature is unavailable to your account.
Approval mode is the setting most worth checking when an agent behaves unexpectedly. An agent that pauses constantly and an agent that acts without asking are usually the same agent with a different approval mode, not a different agent.
Quickstart
Your first agent, in five minutes.
Open Actionist in your browser
Go to app.actionist.ai and sign in with email or Google. The full app runs in the browser, so there is nothing to install. Desktop builds for Mac and Windows are available too if you prefer one.
Describe the job
“Summarize my unread Slack DMs every morning and post the digest to my #daily channel.” Answer the questions and save.
Ready when you are
Build your first agent today.
Describe the job. Actionist wires up the tools, memory, and channels, you supervise.
Your agents do exactly what you allow, no more.
Scoped permissions · Approval gates · Full audit trail.
Keep going
Next steps.
Skills
Turn a behavior into a reusable, publishable pack every agent can load.
Memory
Give agents permissioned recall, company context that sharpens over time.
Workflows
Chain agents and steps into repeatable, schedulable processes.
Channels
Put an agent on Telegram or Slack so it works where your team already is.