From a message to done
this+that turns an incoming message into finished work. A message lands, the AI pulls out the task, a workflow acts on it, you approve anything that needs a person, and the work is complete.
Connect your tools. Extract the work. Remember what matters. Handle it automatically.
Four steps, and the last two feed each other. The brain is your company's memory, a set of pages holding what it knows about your customers, your pricing and your playbooks. Your workflows read from it instead of guessing, and write back as things change.
One stream. Less than a minute to set up.
Bring in Gmail, Outlook, Slack, Microsoft Teams, and Google Chat. Instagram and Facebook Messenger are awaiting platform approval. Every message, every thread, every notification. One stream, one place.
Gmail
Outlook
Slack
Teams
Google Chat AI reads every message. Work surfaces automatically.
Requests, deadlines, follow-ups, commitments. this+that reads the full context and identifies every action hiding inside, before you've even opened the thread.
Everyone knows what anyone knows.
The details that used to live in somebody's head land in a shared brain: what's going on with a customer, who owns what, what you last quoted and why. Your workflows write to it as they run, your contacts keep themselves current from your messages, and we're building one workflow to maintain the rest.
Explore the Brain →- Renewal date is March 14from Slack, Tuesday
- 15 seats at $24, quoted last weekfrom the quote workflow
- Priya owns the legal reviewfrom email
Workflows handle the work, grounded in what the company knows.
Route leads, chase follow-ups, label and forward, notify the right person. Because every workflow reads from the brain, it acts on your real pricing and your real history instead of generic guesses, and what it learns goes back in.
Example: an invoice arrives → AI classifies it → forwards to finance automatically.
Example: a quote request arrives → AI checks your current pricing in the brain → drafts the reply for you to send.
When a task needs doing and your machine is the best place for it to get done, hand it to Claude Code, Codex, or a local model. It runs on the subscription you already pay for, and the work comes back as a draft for a person to review.
Example: a bug lands at support@ → routed to whoever owns that code → an agent drafts the fix on their machine → they review, and the reporter gets a reply.
Learn about Workflows →Workflows and the brain make each other smarter
The brain holds your company's real context, from your pricing and playbooks to what's going on with each customer. Every workflow acts on it instead of guessing, and writes back what it learns as it runs, so the brain grows the more you use it. A knowledge base alone goes stale and automation alone has nothing to go on, which is why neither half works without the other.
Keep what your company knows in one place.
More than a wiki. The operational knowledge that lives in people's heads and Slack history, in one place, grounding every workflow so it acts on your real context. Your workflows write back to it as they run, closing the loop, and we're building toward one workflow that keeps most of it current.
Automate the work hiding in your messages.
this+that turns messages into clear tasks and runs the workflows that handle them, from drafting replies to routing leads and chasing follow-ups. And because they read from your brain, they act with your real context, not generic guesses.
Company knowledge comes in three layers
Two are handled well by tools you already have. The third, the operational middle, is the one big companies staff whole teams to keep current.
What the published research says about how much of it never gets written down: Unrecorded Knowledge →
What happens at each step
What happens when a message arrives?
this+that reads your messages across Gmail, Outlook, Slack, Microsoft Teams, and Google Chat (Instagram is coming soon). The moment one lands, the AI reads it and decides whether there is work inside. When there is, a request, a decision, a deadline, a commitment, the AI pulls that out. The rest stay in your inbox as normal messages.
How does a message become a task?
When the AI finds work, it extracts it into DoBox, a task manager that fills itself. A task keeps the context from its source thread, and you can assign it to a teammate, set a due date and priority, add a checklist, comment, or attach a file. The message became a tracked task on its own.
What can a workflow actually do with it?
The workflow acts. You describe what you want in plain language and this+that builds it, with conditional logic, loops, and AI decisions made mid-run. A workflow can draft a reply in your voice, route a lead, create a calendar event, update an external tool over MCP, through a built-in server or any MCP-compatible tool, or hand the task to a person. One incoming message can start a multi-step sequence rather than a single canned reply.
When does it ask for approval?
Whenever you want it to. You can run a workflow fully automatically, or put an approval gate in front of any action so nothing goes out until you say yes. Most teams start with approval on everything and remove the gates as they come to trust what the AI does. The autonomy is yours to set, one step at a time.
Where does the brain come in?
Anything the AI does can be grounded by the brain, an editable knowledge layer that holds the facts, decisions, and processes you want it to rely on. It is what makes a drafted reply sound like your team and a routing decision match how you actually work. Agents and workflows also write back to the brain as they run, so it grows as the work happens. One part of it already keeps itself current with no setup at all. Contacts assembles the people you deal with from the accounts you connected and attaches your correspondence to each of them. (For the rest, we are building toward one workflow that maintains most of the brain, and the prebuilt Company Brain workflow is an early version of it.)
That is the spine.
And every branch off it
Real work does not always run straight down the spine. The same machinery handles the variants:
- Message → task → assigned to a teammate, where a person picks it up
- Message → workflow → action in an external tool, through MCP
- Message → workflow → drafted reply → approval → sent
- Message → workflow → agent writes the result back to the brain
- A schedule or an event rather than a message → workflow, like a weekly digest
- Message → filtered as noise, no task and no action
Same pieces, different connections. The product is really one loop, and you decide how much of it runs without you.
Each part has its own page:
See it on your own inbox
Connect your inbox and watch what this+that would pull out and act on. Free for 30 days, including 3,000 credits, no credit card required. Then $35 per user per month, or $29 billed annually, with 3,000 credits a month per person.