Your AI cofounder.

Comma gets the job done in your apps and learns how you work through personalised reinforcement learning. Run it on our service or on your own servers.

Comma at work for a company

An example of Comma's Home on an instance a company runs itself, at work on what comes in from outside the company. You ask Comma to handle what came in from customers, partners and suppliers. It reads your email, your shared channels and the contracts in Drive, and checks your security docs. It lists the internal work it finished this morning, starts a Task to answer Northwind's security questionnaire from your security docs, and leaves its replies to Initech and Globex for you to send. In the Tasks rail, Legal reviews Globex's contract changes against your standard terms, Security prepares for the audit, and Finance pays this month's supplier invoices. This week it answered 64 customer emails and 31 partner questions, reviewed 9 contracts and updated 14 supplier records.

Hire your first AI partner.

Train your first private AI model with RLaaS.

Comma for Teams

Comma for Teams is your AI partner. It works in your apps, takes on tasks, and gets the job done.

  • Find work in your Slack channels and open a Task for it
  • Carry it out in Linear, GitHub, Gmail and Slack
  • Hand the result to a person to review and accept

Grows with the teams and people that use it.

An example of RLaaS at work: your model, at version 3, labels a refund request in Linear as a bug. Priya corrects the label to Billing. The model learns from your team's corrections, and version 4, which beats version 3 on your test cases, labels the next refund request Billing itself.

RLaaS continuous learning

SOTA-level capability for your business: more kinds of tasks, a better understanding of how you work, and safer execution.

RLaaS trains your first private AI model through personalised reinforcement learning, using your team's work and feedback.

  • Evals and reward signals built from your own work
  • A new version only when it beats the version in use
  • Compute quota, update scope and SLA set in your contract

Grows with the workflows it learns and where it runs.

Comma keeps your tools up to date

Slack channels

Comma follows the channels you choose. It answers questions, shares notes and drafts the replies that you approve.

Linear issues

Comma triages and assigns new issues, and it closes an issue when its fix merges. A decision that is yours waits for you.

Email

In Gmail and Outlook, Comma drafts replies, files invoices and unsubscribes from newsletters. Set it to draft only, and you send each reply yourself.

Notion pages

Comma keeps plans, notes and checklists in Notion current, with a link to each source. Changes that need review wait for you.

Comma joins your meetings

It joins Google Meet calls on the calendars you choose, keeps the transcript, and turns the call into notes and next steps.

Before the call

Comma posts a brief to the team's channel: what changed since the last meeting, with links.

In the call

Comma joins as a named participant and keeps the transcript.

After the call

The summary, action items, transcript and recording arrive in one thread. Ask Comma there to file the action items in Linear.

How continuous learning works

A large model thinks a problem through. A small model makes what your team has already worked out cheap and steady.

When your team does a kind of work the same way every time, the small model learns it and takes over that workflow, as your contract sets. All other work stays with the large model.

Data from your work becomes test cases and reward signals: the agents' tasks, what people approved or edited, and the outcomes. They train the next small model, which is released only if it does better than the version in use. Back in your work, the small model does the workflows your contract names, a large model does the rest, and people approve or correct the results.
  1. Data from your work

    We use the record of the agents' tasks: what they did, what your team approved, changed or turned down, and the outcome.

  2. Evals and reward signals

    We turn those decisions into test cases and a score for good work, and keep both current each month.

  3. Training and release

    We train a small model against those reward signals. We release a new version only when it beats the version in use on your test cases.

  4. Back into your work

    We deploy the new version on the workflows your contract names. All other work stays with the large model.

You stay in control

Compute

We host Comma for Teams: the dashboard, chat connections and task history run on our service. The agents do their work on your own computers or on a cloud computer for your team.

Govern

People sign in with your company's single sign-on through OpenID Connect, Feishu or Lark. Admins set roles, choose the models and provider keys the team uses, and export the audit log.

Secure

Apps connect with scoped permissions that you can revoke. Agents never see raw credentials.

Security

Data

RLaaS trains your model on your data, and only under the RLaaS contract. We do not use your data to train general-purpose models, ours or anyone else's.

Data Use Policy

You decide where your data goes

Comma reads mail, issues, documents and calls to do its work. Self-hosted, it reads them on servers you manage.

Tasks, memory, files and transcripts stay in your own PostgreSQL, ClickHouse and object storage. Model calls go to the provider you choose, with your key.

Self-host guide
Your team uses Comma inside your network. Comma's web app, Admin console and agents keep their data in PostgreSQL, Redis, ClickHouse and object storage there. Comma works in Linear, GitHub, Google Workspace, Notion, Outlook and Slack, and calls your model provider.

Your servers

One Docker Compose file starts the web app, the Admin console, the server and its data stores on a machine you choose.

Your models

Set your provider's endpoint, model and key, or let each person add a private model. Calls bill to your provider account, not to Comma credits.

Your people

Sign-up stays off until you turn it on. In the Admin console, the owner creates accounts and chooses which models people can select.

Pricing

Comma for Teams

For each person who works with the agents

$80 / seat / month

Billed quarterly, from 100 seats

Renews each quarter until you cancel

Buy seats

Included

  • Roles for who manages each workspace
  • An audit log your admins can export
  • The models and provider keys your team chooses
  • Agents that work on your own computers or a cloud computer

RLaaS continuous learning

Train your first private AI model with RLaaS.

Custom pricing

Compute quota, update scope and SLA set in your contract

Contact sales

Included

  • Evals and reward signals built from your own work
  • A new version only when it beats the version in use

RLaaS is continuous learning, not a one-time delivery. Each month we keep your data and evals current, release a new version when it beats the version in use, and track quality and cost per task.

Comma for Teams is billed per seat each quarter, through Stripe. Model subscriptions and API usage are paid separately. RLaaS is billed per company, not per seat. They are two subscriptions, not one bundle.

Initial training and integration can be quoted on their own, apart from the subscription.

FAQs

Which tools can Comma work in?

Linear, GitHub, Gmail, Google Calendar, Google Drive, Notion, Outlook and Slack, each through its own sign-in. Some need an app registration with the provider in your name, and we help you set those up. Plugins add MCP servers and Skills for other tools.

Which meetings does Comma join?

Google Meet calls on the calendars you choose, or a call you send it a link to. The meeting runtime is not part of the Compose stack, and we set it up with you.

Why a small model, and not the best large model?

Much of a team's work is settled: the same kind of decision, made the same way, many times a day. A small model trained on your decisions does that work faster, for less, and more consistently. The large model stays for what is new.

Can you build a cluster or buy hardware for us?

You do not need to. RLaaS includes the compute for training and evals, up to the quota in your contract. Compute beyond the quota is billed separately.

How are seats counted?

One seat is one person who works with the agents, whatever their role. Engineers, product managers, support, operations and sales count the same. Buy at least 100 seats. The plan renews each quarter at the same seat count until an admin cancels it. RLaaS is priced per company, not per seat.

How much does it cost to start?

Comma for Teams costs $80 per seat a month, paid each quarter through Stripe, from 100 seats. RLaaS is quoted for each company, by the workflows it covers; your contract sets its compute quota, update scope and SLA. Initial training and integration can be quoted on their own.

What runs on our servers if we self-host?

The Comma web app and Admin console, the Comma server with its agents, PostgreSQL, Redis, ClickHouse, and MinIO for stored files. One Docker Compose file starts them on one machine, and sign-in codes go out through your mail server.

Which models can we use?

The model provider you set for the instance: its endpoint, protocol, model ID and key. People can also add a private model in Settings. Calls bill to your provider account, and a self-hosted instance needs no Comma credits.

Is our data used to train AI models?

Not unless you ask. We do not use your files, conversations or prompts to train our own or third-party general-purpose AI models. Training on your data happens only in a service you ask for, such as RLaaS, under its own contract. Self-hosted, your data stays in your stores, and model calls go to the provider you set.

Contact sales

  • Pick the first team to work with the agents
  • Plan your seat count
  • Scope an RLaaS contract
  • Plan your self-hosted deployment

You can also email us at contact@comma.surf