All comparisons
OpenCharts · Always-on workers
Theo Agent vs dots
OpenAI's always-on agents with a cloud computer of their own, reached through ChatGPT, Slack and Teams
Dots give one person one agent that lives inside ChatGPT and works on its own cloud computer. Theo Agent gives you a roster of workers, each on a computer of its own, each with a choice of engines, each earning its autonomy, each leaving a receipt, and each reachable by text, email or a phone call.
By OpenCharts TeamPublished
Theo Agent is OpenCharts' always-on autonomous worker, comparable to OpenAI's dots: both run on a persistent cloud computer with a browser, connect to the apps you approve, carry a job on after you close the laptop, come back for approval before anything consequential, and let you look at the computer while they work. Theo Agent differs in choice, governance and reach. A worker routes across engines from several labs instead of one model, earns autonomy one kind of action at a time, records a receipt for every run, can rehearse a configuration change against its own past runs before it goes live, pauses rather than bills when credits run out, can run on your own provider key, and holds its own phone number, email address and calendar. You can hire several workers today and put up to eight of them in one room. Dots lead on the ecosystem around them: plugins for more than 4,000 apps, a home inside ChatGPT, Slack and Teams with voice calls, proactive research that brings you work before you ask, and a path into enterprise identity and governance through specialist dots.
Theo Agent vs dots✳The verdict✳When to choose✳Feature matrix✳Pricing snapshot✳Migration✳FAQ✳Theo Agent vs dots✳The verdict✳When to choose✳Feature matrix✳Pricing snapshot✳Migration✳FAQ✳
The verdict
Where each one wins
Theo Agent wins at
- A choice of engines from several labs per worker, with cost tiers, or your own provider key, instead of one model with no picker
- Several workers today, each on a computer of its own, and rooms where you and up to eight of them talk in one conversation
- Receipts for every run: the engine used, the sources read, the messages sent, the credits spent, and which actions ran on earned trust
- Autonomy that is earned: approve the same kind of action a few times in a row and the worker stops asking for that kind, and only that kind, with deleting never earnable
- Rehearse a change before it ships: replay a worker's own past runs against a new engine, persona or tool set and see what would change, without executing anything
- Out of credits is a pause that resumes on a top-up, with a warning a turn early
- A worker with its own phone number, email address, and calendar that answers calls and books meetings
- One approval for a multi-step plan, with each step marked reversible or not, and org-wide approval rules
- Deliverables land as editable decks, documents, sheets, and apps in the same workspace
dots still wins at
- Reach into more than 4,000 apps through its plugin ecosystem
- A home inside ChatGPT on desktop, web and mobile, plus Slack and Teams, with voice calls and context carried across every channel
- Proactive research: while you are away it looks for ways to help on read-only tools and brings you work before you ask
- With your permission it can connect to and use your own laptop alongside you
- An enterprise path: specialist dots with their own identity and credentials, and governance through Microsoft Agent 365, both in pilots
How they compare
Theo Agent and dots solve overlapping problems differently. The matrix below makes the trade-offs concrete, and the migration note covers what it takes to switch when you're ready.
When to choose
The right pick for your team
Choose Theo Agent when…
- You want to choose, or let Theo choose, which engine a worker thinks with, and see what each run cost.
- You want several workers today, each with its own job, its own computer and its own memory, talking in one room.
- Your team needs approvals, receipts, a trust ladder and org-level rules before it hands real work to an agent.
- You want a worker people can text, email, or call, not only a chat window.
- The output should be a deck, a document, a sheet, or an app you keep editing, not a file in a folder.
- You already run OpenCharts and want the worker inside the same plan and workspace.
Choose dots when…
- You live in ChatGPT, Slack or Teams and want the agent where you already are.
- You depend on apps that only a very large plugin catalogue reaches.
- You want an agent that researches in the background and brings you work before you ask.
- You are on a ChatGPT Pro, Business Premium or Enterprise plan and want the agent included with it.
Side by side
Feature comparison
Feature
Theo Agent
dots
Which model does the work
A Brain policy per worker: let Theo orchestrate across engines from several labs, pick economy, or pin one engine, with per-lane routing for writing, reasoning, vision, and code
One model for every dot, chosen by the vendor; no engine picker
Where the worker runs
A persistent computer per worker (browser, files, terminal) that sleeps when idle and wakes with its sign-ins intact; a code worker's computer also holds a repository clone. Deliverables it leaves on its desk are saved to your Drive
Its own cloud computer and browser per dot; you can open the computer to inspect its work, and with permission it can also connect to and use your laptop
Watching and taking over
Watch the live page beside the chat, act on its real fields and buttons, and hand it back; the worker can ask you to step in for a login, a code or a payment, and what you type is never recorded or shown to it
Open the dot's computer at any time to inspect its work; on supported sites it signs in with saved passwords the model never sees
Earning autonomy
Opt a kind of action in and a few consecutive approvals earn it; one rejection resets the streak; deleting is never earnable; every change is announced in the worker's own chat and recorded on its receipts
Built-in rules for when to act and when to ask, plus Custom Rules that allow, require approval for, or block specific actions
Testing a change before it ships
Replay a worker's own past runs against a new configuration and diff what it would do against what it did; nothing is executed, and only lost reach or gained risk counts as a regression
Not offered
Approvals
Full autonomy, ask before risky, or ask before everything; one approval covers a whole multi-step plan with reversibility marked; org rules override any worker
Auto-review checks actions that could affect your accounts or share information against your instructions, Custom Rules and safety requirements; sensitive tasks such as changing a password always stay with you
Audit trail
A receipt per run naming the engine, the web pages and company knowledge read, the messages sent, the teammates used, and the credits spent
Activity View shows progress, including background work
Spend control
A per-turn credit gate warns early and pauses the run when the balance cannot cover the next step; a top-up resumes exactly where it left off
The first dot is included in the plan with an allowance for deeper work; adding dots and scaling their output is described as coming
How you reach it
In-app chat, Slack channels, Telegram, SMS from its own phone number, email from its own address, live phone calls, a REST API, and a native phone tab where the roster shows who needs you and you approve or decline in one tap
ChatGPT on desktop, web and mobile, Slack and Teams, with voice calls; it messages you with progress and questions; texting is described as coming soon
Working while you are away
Missions that wait until a time or a page changes and wake the worker, engine-free monitoring that spends nothing while nothing changed, a daily brief, and a note when a worker handled something itself; replies can be sent, drafted or held per worker
Proactive research on the apps you connected, on tools restricted to read-only so it cannot send messages, change content or control a browser; monitoring can pause or stop a dot
Long-running work
Missions that outlive a session: wait until a time or a page changes, resume across hours or days; plus several named routines per worker, each on its own schedule, that switch themselves off after repeated failures
Works toward goals around the clock on its own computer and runs several projects at once
Teaching it a job
Take over its browser, do the job once, press Done: it saves the procedure as a skill it can edit and reuse, keeping the shape of what you typed but never the value; or describe the steps in chat; plus opt-in learning of how you write
Learns your preferences and standards from feedback over time; no show-it-once recording described at launch
Working with other agents
Rooms where you and up to eight workers talk in one conversation, address a worker by name and let them message each other, with the roster showing what each one is doing; plus delegation with a checked output contract, live steering, stop-and-keep-partial, and a cap on how many run at once
One primary dot per person today; teams of dots are described as the direction, and specialist dots for organizations are in enterprise pilots
Sharing a worker
Duplicate a tuned worker, or share its setup with your team or as a link; the template carries the goal, persona, tools and policies and never an account, a credential or a memory
Not described at launch
What it produces
Editable decks, documents, sheets, apps, images, video, and notes in the same workspace
Work lands in the apps it connected to: pull requests with videos attached, drafts of documents, posts and proposals, and files on its computer
Company knowledge
Reads a reviewed company wiki and cites the article, its space, and its review status
Through the apps you connected; specialist dots are described as integrating with a company's systems of record, in pilots
Scroll to compare
Pricing and migration
What it costs, what it takes
Pricing
Pricing snapshot
Theo Agent is included from OpenCharts Starter at $9.99/mo, with Pro at $24.99/mo and Teams at $14.99 per user per month; runs spend the same AI credits every other Theo surface uses, and a dedicated SMS number is a monthly add-on. Dots are not sold on their own: the first dot is included with ChatGPT Pro and Business Premium in eligible markets, Enterprise workspaces (including Edu and Healthcare) can enable the beta, and the plan carries an allowance for deeper work, with the option to add dots and scale their output described as coming. List pricing at time of writing (September 2026).
Migration
Migrating from dots
There is no import between the two. Recreate a dot as a Theo Agent worker from the wizard: paste its instructions as the goal and persona, turn its Custom Rules into an approval posture and an allow-list, connect the same accounts, and pick an engine policy. Anything it learned about you goes into the worker's memory, and a standing job becomes a routine on its own schedule.
Questions
Frequently asked questions
Is Theo Agent the same kind of product as dots?
Yes. Both are always-on agents with a cloud computer of their own: you give them a goal and the apps they may use, they carry multi-step work on without supervision, and they stop for your approval before anything consequential. The differences are in which engine does the work, how many workers you can run and how they are governed, and how you reach them.
Does dots let me pick the model?
Not today. Every dot runs on one model chosen by the vendor, with no picker. Theo Agent's Brain policy lets each worker orchestrate across engines from several labs, run in economy mode, or pin one engine, with separate lanes for writing, reasoning, vision, and code, and a worker can run on your own provider key.
Can I run more than one agent?
With dots you start with one primary dot; teams of dots are described as the direction, and specialist dots for organizations are in enterprise pilots. Theo Agent lets you hire several workers today, each with its own computer, memory and job, and put up to eight of them in a room with you.
How do approvals and rules compare?
Dots start with built-in rules and let you add Custom Rules that allow, require approval for, or block specific actions, with auto-review checking consequential actions and password changes always left to you. Theo Agent pauses per its posture, lets one approval cover a whole plan with each step marked reversible or not, applies org-wide rules on top of any worker, and lets a worker earn autonomy for a kind of action after consecutive approvals, with deleting never earnable.
Which one keeps a record of what the agent did?
Both. Dots show progress, including background work, in Activity View. Theo Agent writes a receipt per run naming the engine, the web pages and company knowledge read, the messages sent, the teammates used, the credits spent, and which actions ran on earned trust.
What happens when the agent runs out of budget?
A dot is included in its plan with an allowance for deeper work; beyond that, the option to scale a dot's output is described as coming. Theo Agent checks the balance every turn, warns before it runs short, and pauses the run rather than failing it; a top-up resumes the same work from where it stopped.
Can I text or call the agent?
You can talk to a dot by voice inside ChatGPT and message it in ChatGPT, Slack and Teams; texting is described as coming soon. A Theo Agent worker can hold its own phone number for texts and live calls, its own email address and calendar, a Slack channel it listens to, a Telegram chat, and a REST API.
Does either one work while I am away?
Yes, both. A dot does proactive research in the background on read-only tools and brings you work before you ask. A Theo Agent worker runs missions that wait for a time or a page change, sends you a daily brief and a note when it handled something itself, and can send, draft or hold its replies per worker.
Hire a worker that keeps working
Give a Theo Agent worker a goal, the tools it may use, and an approval policy. It works within those boundaries and reports back. Included from the Starter plan, with the whole workspace alongside it.
Included from Starter · Approvals and receipts on every run