Home (Today)

Choose Outlook for outreach

Choosing Outlook drafts records your destination. Review each outreach message in Activity and approve its placement before it enters Outlook. Send it from your mailbox when ready. Other role output stays in the app for review.

Collected revenue evidence

Today's collected-revenue figure shares its reader with the Revenue cockpit. It includes invoices created before the quarter when their payment date falls inside it, keeps currencies separate and subtracts recorded succeeded refunds. Failed reads and histories above the 50,000-event review limit remain unmeasured instead of appearing as a zero or a partial total.

A familiar workspace

Today, Activity, Work and Team use the same top navigation, page headings and review cards. Open your account menu to choose a light, dark or system theme. Your choice follows you to the public website and guides.

Start with the decision that needs your attention. Account research, team reports and delivery settings stay available in expandable sections.

Start here: one card, then the queue

Today opens with one card called Start here, and it holds the page's only main button. What the card shows depends on your day:

• A decision is waiting. The oldest decision you owe, with the role that raised it, why it matters, how long it has waited and what happens when you open it. For a held draft you can read and edit the message inside the card. Why this comes first explains the order. Any other decisions follow under Next in your queue, every one of them, never folded away.
• No decision is waiting. The card says so in those words. If your roles suggested work, the card says how many steps there are and that they are optional, and the list below is headed Suggested next steps with "Optional" beside it. If setup is still open, the card names that separately with a link to the next step. Before 2026-10-01 this state said "You are caught up." above a list of suggestions and a setup checklist, which made it hard to tell what needed you.
• First day. The card shows how many setup steps are done and opens the next one. The full checklist is one click away inside the card. If you pressed Save and exit on the starting point of the business brief, the card offers Resume your starting point instead, and it opens that exact step with your website and description filled in. Without a seat, the seat card adds a Resume where you left off link to the same step.
• Something could not load. The card names the sources that failed and its button reloads the page. While the reload runs, the half-loaded work is hidden and the status line says your work is loading, so nothing gets approved from an incomplete view.

Suggested work shows three steps at a time; the rest sit behind Show more suggestions. Under the queue, Prepared for tomorrow holds a focus note for your next visit. Saving it does not approve anything or change an agent's schedule. The suggested note names the work that leads your day; on your first day it says to finish setup, rather than repeating the step the Start here card already shows. On a first day the setup steps also fold into Set up each step from here, and Where your work lands stays closed, because choosing a destination is one of those steps. Readiness by role, account research, where your work lands, your team, revenue, saved work and delivery settings follow, most of them behind a disclosure.

The walkthrough video on this page follows the same order: the Start here card, Next in your queue, optional suggested work, and the quiet state. It was re-recorded on 2026-10-01 for this layout.

When a mailbox is paused

If too much mail from your Gmail or Outlook bounced this week (at least 5% of what was sent, and at least three messages), new outreach drafts for that mailbox stop, its drafts stop sending, and Home says so at the top: how many bounced, from which address, and why it matters. A send button for one of its drafts is disabled with the reason; choose I checked this address beside it to send that one draft after checking the recipient. To lift the pause, remove or correct the bounced addresses, then choose Resume sending. Only bounces after that count toward another pause. If the resume fails, Home says so under the button and the pause stays. When both mailboxes are paused, each gets its own notice and its own Resume sending. If Home cannot read the mailbox state, it shows no pause notice and the rest of the page loads as usual; the pause still holds, and Connections still shows it. The same state and control are on the mailbox's card in Connections, with the domain's SPF, DKIM and DMARC records.

When drafted replies pause

When reply alerts are switched on for your Gmail, each reply a prospect sends reaches you within minutes with a drafted answer waiting for your approval. Those drafts may spend a quarter of your monthly AI budget, not all of it, so a busy month of replies cannot use up what your other work needs. Once they reach that share, replies still alert you within minutes, but without a draft, and each alert says so. Home says so at the top, with what drafted replies have spent, their share, your whole budget and the date they start again, which is the first of next month. Your other AI work keeps the rest of the budget in the meantime.

Where your work lands

Home says where your roles' reviewed work goes and lets you choose once for all of them: the in-app review queue, a Google Drive folder (which needs the Google Drive connection), Gmail drafts or Outlook drafts. Gmail drafts and Outlook drafts can be chosen only while that mailbox is connected; otherwise the option is shown disabled with the reason and a link to Connections. Choosing Gmail drafts also turns on Gmail placement for your morning queue, so each outreach draft lands in your Gmail Drafts folder, addressed and unsent, and moving to another destination turns it off again. Other work stays in the review queue. Choosing Outlook drafts places nothing on its own: you approve each outreach message in Activity, and only then is it placed in Outlook, unsent. Saving sets every role you hold, one role at a time; if one cannot be saved, Home names it and the others stay saved. Until you choose, Home asks, and your existing drafts stay in the queue. A single role can still use a different destination, set in its console.

Role drafts in Gmail (switched off for now)

Built and switched off until the app passes a Google security review of how it uses Gmail, which we have not started. Once it is on, choosing Gmail drafts also places each scheduled role draft that is a message to someone (a follow-up, a customer touch, a partner touch, a support reply, an escalation, an outbound sequence) in your Gmail Drafts folder as soon as the role writes it. Briefs, forecasts and board material stay in the review queue. Each placed draft arrives with no recipient and unsent, so nothing can go out until you open it, add the recipient and press send. Only drafts written after you chose Gmail drafts are placed. The draft stays listed in your review queue, but you edit and send it from Gmail: editing it in the queue, or approving it there to send by email, is refused with the reason, so one version exists and it goes out once. Pressing → Gmail draft on it returns the same draft rather than a second copy, and your action receipts mark the placement cron, the schedule, rather than manual. A draft held for a later date is not placed early. Nothing is placed while managed connectors are off, while Gmail is disconnected, or while your Gmail is paused for bounces. Outlook works differently: a message is placed only after you approve it in Activity. Until the switch is on, saving Gmail drafts tells you that other work stays in the review queue, and that is what happens.

Your prospecting

Once you have started a first launch, Home carries it. While research runs, a card shows how many companies, contacts and drafts are done and the one thing to do next. After you turn on daily prospecting, the section shows what the plan found: each new company with the reason it matched your customer profile and whether Attio has it, drafts waiting in your Gmail mailbox, follow-ups due in the next seven days, contacts waiting on a decision from you, and contacts removed from outreach because they replied, bounced or were stopped.

Problems come first: a disconnected Gmail or Attio, a used-up daily research allowance, or 25 drafts still pending. Each names where to fix it. The controls are the same ones the onboarding step offers: pause or resume the plan, stop follow-ups for one contact, retry an Attio lookup you have checked. Nothing on this page sends email; drafts are reviewed and sent from Gmail.

Overview

Home is where you land after signing in, and it is built to be read in the order it appears. Each role you own runs on a schedule and reports here. You get what needs your approval, then a short ranked list of what moves revenue today, then one sentence from each role.

The page is deliberately short. Nine roles checking in three times a day (morning, midday and evening) produce far more than anyone can act on, so the line is capped at what fits before your first call. Everything a role found but did not raise stays in that role's console, on the Runs tab, and the standup tells you how much each one held back.

What reaches the line is scoped to the roles you hold. A seat licenses all nine, so most accounts see all nine; an account still holding a legacy per-role subscription sees those, and the standup and the line agree about which. An account without a seat sees an honest no-seat standup with one route to pricing. It does not show inactive delivery controls or pretend that scheduled work has arrived.

Your agents run on our own servers on a schedule. There is nothing to install and no desktop app. You connect a data source once, the scheduled passes do the work, and you review what comes back. Nothing is ever sent without your click.

What's on the page

Today leads with one next action in the Start here card, then the rest of your decisions and the optional suggestions, then the Your team table. Open Where your work lands, Accounts and contact research, Revenue and your target, or Saved work when you need detail. Where your work lands opens by itself until you have chosen a destination. Current readiness is separate from historical runs. If a source fails, reload from the main action before treating the queue as complete.

Your first session asks one thing. Until we know your business, the one button on this page opens Tell your roles about the business. Point it at your website, review the draft, confirm. That fills Brand & Company too. The setup rail underneath lists the other steps (provider key, a data source, where output goes, the schedule) and does not repeat the button. Once the brief is confirmed the button becomes whatever is next: your first signal, a commitment waiting on you, or the line.

• Waiting on you. Commitments, not suggestions: drafts held for send, and decisions only you can make. Every commitment remains available and every row carries how long it has been waiting, because an approval that quietly piles up is worse than no draft at all. Expand a draft to edit it inline, then Copy it, save your revision, or dismiss it. When you dismiss, a one-tap chooser asks why (not relevant, wrong facts, off tone, or just dismiss); the reason is captured so the role's craft library can learn, and "just dismiss" records nothing. Each draft shows a Why this draft panel naming the skill that wrote it, the sources it cited, and any claim it made without one. Approve, Save edit, Copy, Snooze and Dismiss are the same buttons with the same labels here, in the send queue and in every role console: one gesture to learn, and one sentence back when something fails that always says whether anything went out.
• The line. The ranked work, capped, with a rough time cost for the whole list. Every item names the role that raised it, gives one sentence of evidence, and carries a single verb you already use: Call, Send, Book, Draft, Decide or Read. The order is computed, not guessed, and it is deliberately something you can argue with: items rank on how close they sit to a live conversation, whether the check called them today's problem, how long they have waited, and how quickly they clear. Deal size nudges the order where you have deal sizes and never decides it, so the ranking works just as well before you have a CRM. Action items from your recorded Fathom and Zoom calls join the line too, each with the call it came from, the owner the call tool named and its due date; an overdue one counts as today's problem. Its Review button opens Deal Inspection, where the item sits under its deal; pressing Review does not close it. Mark done on the deal does.
• Your team. A table, open on the page, with one row per role: Role, Latest work (what it produced today, or its last recorded pass) and Next step (the items waiting on you, the one thing blocking it, or its next pass). A role you have handed to a teammate says who runs it; a role nobody assigned to you says so. Choose Read each role's report to expand the detailed reports, next-pass information, and console links.
• Close the day. One sentence stating what the team did today, counted from the same record Activity shows: passes ran, emails drafted, things found, notes researched, posts written, writes proposed, and what you acted on. Then what your roles raised that did not earn a place today, and a link into today's Activity. If that record cannot be read, the band says so rather than reading as a quiet day.

If a part of your day cannot be loaded, the page says which part failed rather than showing you an empty block. An empty block would read as "nothing to do", and that is the one thing this page must never say wrongly.

Have it sent to you

At the bottom of Home, pick a channel and an hour and your line arrives there at that hour every day. Email goes to your account address unless you name another. Slack posts to an incoming webhook you paste in, which needs no app install and no approval from anyone.

A quiet day is not sent. On the page, "nothing needs you" is a real report worth reading; in your inbox, a daily message that usually says nothing is how you learn to ignore the one that says something. So a message always means there is something.

The message carries the same line, in the same order, from the same renderer the page uses. It cannot disagree with what you see here. Nothing in a delivery can send anything to a customer: it is a message about your day, and every outbound still waits for your approval in the send queue.

What the page remembers

Every item that reaches your line is recorded: what it was, which role raised it, where it landed, and how high. Items you never touch are recorded too, and those matter most. An item you passed over at rank two is the clearest evidence the order was wrong, and it is the signal the ranking learns from.

Skip says "not today" and is worth using rather than ignoring a row. It costs one click, it does not delete anything, and it teaches the order faster than silence does. Dismiss on a draft asks why, and that reason reaches the role's craft library.

Nothing on this page can send. The primary button on a held draft takes you to the send queue, where the send layer's own switch and daily budget apply. That separation is deliberate: one place decides what leaves the building.

Jump anywhere: the Cmd-K palette

Press Cmd+K (Mac) or Ctrl+K (Windows), or click Search in the top bar, on any signed-in page. Type a few letters to jump to a page, one of your pending drafts by title, or a quick action (docs for the page you are on, support, service status). Arrow keys move, Enter goes, Esc closes. Picking a draft lands you on Home with that draft opened and highlighted.

Everything is in the line

Nine kinds of work compete for the same few places: what your roles found, drafts they wrote, decisions the org needs from you, your setup steps, queued outreach, questions worth asking on a live deal, accounts behaving like they are in market, and what the scheduled checks on your book turned up (a deal stalled in security review, a sequence that stopped, a cadence step now overdue). There is no second queue on another page that you are also supposed to be checking.

That last kind used to arrive as a separate email. A weekday note called the Morning Brief carried the top three of them at a fixed hour, to whoever had found the opt-in buried in Settings, and its main button opened a page that had been retired. It is gone. Those checks now go where the rest of your line goes, and answering one here closes it rather than leaving it to come back tomorrow.

Each of those still has a detail page, and the line links you to it. Queued outreach is read and sent from Activity, because sending is a decision the line deliberately cannot make for you. The full intent list, with the signals behind each score, is on Intent. A proposed change to your business brief, including a rule raised from a correction to a draft, is decided on the brief page, where its lines are listed; Decide here takes you there and accepts nothing by itself. What changed is that you no longer have to remember to open either one.

The line spreads across kinds as well as across roles. If you have forty queued drafts and a busy intent feed, you still will not get a line that is five of the same thing, because a second item from the same source is worth slightly less than the first.

When an account is off limits, the line says so. The outreach rules track who you have contacted and how recently. If an item points at someone you touched a few days ago who has not replied, the row carries a short warning saying to hold off. It is still shown, because you may know something the rules do not; it is never quietly removed and never quietly offered.

Somebody who engaged with your content goes first. Anyone who liked, commented on or reshared one of your posts in the last seven days sits at the top of the line, newest first, with the post they engaged with named on the row. They still count against the cap, so a busy week fills the line with the newest five and holds the rest. Review opens Warm leads on Studio, where the drafted reply waits for you.

Your best accounts come to you as a call, not a draft. Each account's tier starts from fit (size, past activity, how much it looks like deals you won). Fresh buying signals from the last 30 days can lift it one tier and never two: a funding round, hiring into your buying centre, a job change, a website visit, third-party intent or engagement with your content. Two different signals lift it; a single one lifts it only when the buyer asked directly, with a demo request or a reply. A tier 1 account gets no automated draft. It reaches the line as a task to work it yourself, carrying one sentence that names its fit and its signals. A tier 2 account gets an email draft that opens on its newest signal, plus a task to connect on LinkedIn by hand, because nothing is sent on LinkedIn for you. A tier 3 account gets the email draft only. An account that has never been tiered keeps the email draft it had before.

What came of it

For a week after you act on something, Home watches for three things and reports what it sees: a real reply from that person or their company, a meeting on your calendar with them, or the deal moving stage. That block sits under Close the day and only appears once you have acted on something.

It never asks. There is no "did this work?" prompt anywhere, because the answer you would get is whoever bothers to reply. Everything reported is read from your own connected mail, calendar and CRM records. An out-of-office does not count as a reply.

Nothing seen is not the same as nothing happened. Items still inside the window with nothing observed are counted separately and are never shown as failures. Work you did outside the product, a reply on a channel we are not connected to, and a genuine dead end all look identical from here, and pretending otherwise would be the easiest lie for this page to tell.

Seven days, then it stops looking. A reply three weeks after a call is a real thing and a poor claim about why it happened.

The order learns from you

The line is ordered by four things: how close an item is to a real conversation, whether it is today's problem or this week's, how long it has been waiting, and how quick it is to clear. There is no model deciding the order. You can read it, and you can disagree with it.

Once you have used it for a few weeks, a daily pass compares the items you acted on against the ones you passed over and shifts how much each of those four counts, for your account only. An item that visibly led somewhere counts for more than one you merely opened, and one where nothing was observed still counts fully on the side you put it: absent evidence is never read as bad evidence. Being shown something and doing nothing counts as passing over it, which is the whole reason every item you are offered is recorded and not just the ones you touch. Snoozing counts as neither, because it says the timing was wrong, not the ordering.

When it moves, Home says so and names what changed, under The order learned something. Nothing about it is hidden, and nothing it does is a decision: it changes what comes first, never what happens. A weight can only drift so far from where it started, so a strange fortnight cannot turn your line upside down.

It needs real use before it does anything, several weeks of use with both items you acted on and items you passed over. Until then you get the ordering everyone starts with, which is not a placeholder.

When you hire someone

You can hand a role to a teammate from Team admin. They run it: their console, their drafts, their schedule. Assigning a role is not a purchase and changes no price; what costs money is the seat the teammate holds.

A teammate on someone else's team, a cofounder for example, sees a notice under the headline: You are working in (team) as a teammate. Their Home shows their own work. Anything that sends from the owner's mailbox still needs the owner to approve it, and team access never opens anyone's private mailbox. Under the team table they also see Private mailbox remains private: the owner reviews and places a draft that goes out from the owner's mailbox, and a shared output preference never grants mailbox access.

Coming back. A founder who holds a seat, has confirmed a brief and has work running sees Welcome back. Your work is where you left it. beside that notice. It says the confirmed brief, connected tools and earlier onboarding steps carry over and no new purchase is needed, and it counts what is running: contacts in your daily prospecting plan, sends waiting on a receipt, active Instantly enrolments and connected tools. These are the same counts the business brief page shows as Already running. A count that could not be read says so instead of showing zero. A first-time founder does not see it.

Your standup keeps a row for it, and that row changes what it does. Instead of asking you to act on salescron, it tells you how salescron is going: that it ran, how many passes, and when the last one was. That is the whole point of delegating, and it is the difference between doing the job and owning the outcome.

You see that it ran, never what they wrote. The row reports counts and times only, and that limit is enforced by the database rather than by us remembering: the account that reads it has no access to any table holding a draft, a message or a note.

Reversible from the same place, and from the card on Home. If they leave your team, the role comes back to you automatically rather than leaving with them.

Want the role back for yourself and for them? That is a second seat of that role at its listed price. Delegating is free; two people running the same role is two seats.

If you hold every role

For somebody holding every role the Work tab holds one entry, Workspaces, and it brings you back to the standup. Eight equal tabs is the problem this page was built to answer, so the menu stops asking you to pick and the standup does the ranking instead. Each role card there links straight into that role's panels.

Nothing is hidden. Every workspace keeps its own address, its own in-page tabs, and its place in the Cmd-K palette, so Cmd+K then a few letters still goes anywhere in one step. What changed is the menu, which is where you choose; the palette is where you go when you already know.

A seat buyer sees no difference. Work already shows only the workspaces you own, and it collapses only for an account holding all nine roles.

Look around before you sign up

The sample workspace is this page, open to anyone without an account. It shows one morning for a made-up company: two decisions waiting, a prepared first message you can open and read, the optional suggestions below them, and the team table. The order and the wording come from the same code that builds your own Today.

Everything there is fictional, and nothing on it works. Buttons and text boxes are switched off and say why when you point at them, and links into the app are switched off too. The sample saves nothing, sends nothing and makes no AI request, and it never opens anyone's real workspace. When you want it on your own business, choose Start with your business.

Before you buy anything

Home shows what a seat starts and what it costs. A seat licenses every role and starts their schedules. Until then, Home has one primary action, buying a seat, with a quiet link for a team purchase.

Delivery preferences and the end-of-day record appear after there is scheduled work to deliver or review. The no-seat state does not ask you to configure either one.

Your number

Under the greeting sits one band: your target for the quarter, what has closed, what you marked commit, what is open, and the coverage between them. It appears once you have a target or an opportunity, so a new account is not shown a row of zeroes.

It is not a forecast. Nothing is predicted, weighted by stage, or adjusted by a model. Won is what closed, committed is what you marked commit, and open pipeline is the rest, each a sum of amounts on opportunities you already store. An opportunity with no readable amount is counted out of every total and named, because a silent exclusion is how a total quietly stops being the total.

Coverage is measured against the gap, not the target. Coverage on the full target ignores what is already banked, which makes a nearly finished quarter look thin. Once the target is met there is no gap and no coverage, and the band says so.

A forecast category is read off the opportunity, never inferred from its stage. A stage-to-category mapping is a guess about your process, and this number's whole claim is that it guesses nothing. Set or clear the target from the band itself; the figure lives on this screen, so the field that changes it does too.

Below the target row, a second row shows what was actually collected. "Collected" sums paid invoices from your own connected Stripe account for the same quarter, never this platform's, and is distinct from "Closed won" above it: won is what a seller marked closed, collected is what a customer's card actually cleared. Without Stripe connected the cell reads not connected rather than a $0 that would look like a real answer; connect it from Settings, Connect. The figure is per currency and net of refunds: an invoice counts on the day it was paid (an old invoice paid this quarter is this quarter's money), a partial payment counts what was paid, a succeeded refund is subtracted in the period it was made, and a customer paying in EUR shows as a second line rather than being added to USD. Two currencies are never one number. Next to it, Sourced pipeline and Influenced pipeline repeat the first-touch and any-touch split from Revenue Attribution, so the day's landing screen and the full attribution page never disagree about what a channel gets credit for.

One number per hire

Under your number, What each hire should move gives every role you hold one sentence, such as "Reply rate: 3.1% at hire, 4.4% at day 60, target 5%." Pick the bucket the hire is for (more customers, each customer worth more, or lower cost), one number from that role's list, and a target for day 60. Until you pick, the role's first number shows with no target.

How it is measured. The hire date is when your account first held the role. The baseline is the first week of data from your connected tools after that date; if you connected the tool later, the baseline starts when its data does. Day 30 and day 60 are the week ending on that day after the hire, so all three readings cover one week. Reply rate and satisfaction wait a further week before they are read, because replies and ratings arrive after the send or the ticket. Once a reading is taken it does not change, even if your CRM later rewrites its history.

Nothing is estimated. A week with no data shows as not measured, with a note naming the connection that would supply it. A rate with nothing to divide by is not measured, never 0%.

Some numbers are left off on purpose. Positive reply rate needs a judgement on each reply that is not stored. Renewal or retention rate needs a renewal outcome over time, and the connected tools give today's renewal date only. New opportunities per week would count every existing deal on the first CRM sync.

Showing it on /watch. Each role's form has a checkbox to show its day 60 result on the public /watch board. It is off until you tick it. The board shows the role and the numbers, never your company name, and only once both the baseline and day 60 exist. Untick it and the result leaves the board on the next page load. Signups from your content never go on the board, because anyone can raise that count by signing up through their own link; it stays a private number on Home.

The same sentences open the weekly recap email, and each role's console shows its own under the heading. Change them here.

Your first login

On day one, Home leads with one next action rather than a full configuration list. Start with Tell your roles about the business, then continue through Add your AI provider key, Connect a data source, Choose where output goes, and Turn the runtime on. Each opens the page where the work is actually finished.

When the line first contains a recommendation from your account, Home leads with Your first live standup is ready. The card names the specific signal, why it matters, where it came from, when it was raised, and one action. It is shown once. Setup then becomes a compact disclosure, so the result stays ahead of the remaining configuration.

A quiet line is a report, not a blank state. Once setup is complete and no commitment or recommendation needs you, Home says that plainly, gives the next scheduled pass, and offers Activity for the record of what ran.

You only do those once, not once per role. A founder holding several seats is still one person, so turning the runtime on for any seat counts, and so does choosing one destination.

Before a live result, the rail shows how many steps are done, and every role card says what that role will do once it can run and how often. That is read from the role's own primary skill and cadence rather than a sentence written about it, so it stays true when a role changes.

What each role card tells you. Besides the figure and the sentence, every card names where that role's finished work lands (the in-app queue, a Google Drive folder, or your own self-hosted kernel), and marks the figure not current when the last run is more than 36 hours old. A number you cannot date is a number you cannot act on, and the cards used to show one. A role that ran and found nothing says so rather than showing a zero, because a quiet report and a broken role look identical as a number. Readiness is three separate answers, not one word: whether the role can read enough to run its checks, whether it can draft (which needs an AI provider key), and whether it is allowed to send. Sending is never implied by the other two and stays off until you turn it on.

Readiness by role. Under the rail, one row per role you hold says where that role stands: ready, waiting on data (naming the records it needs, for example opportunities), waiting on key, runtime off, or manual entry for a seat whose checks read records you enter in its console, which no CRM feeds. Each row carries one sentence and a link to where that step is finished. The read is derived from what each role's free checks declare they read, so a role that starts reading a new record type changes its own row, and sample rows never count as data. The same read drives the blocker on each role card, so a CSM with accounts connected is not told to connect a source because another role's table is empty. The list stays while any role is short of ready and goes when all are.

A key is drafting, not sending. Adding a provider key turns the AI tier on for drafting. Sending stays off until you turn the send layer on, and each role's readiness sentence says which it is.

Every item that names a company carries a link into that company's record, so the line is a way into the business rather than a list of tasks.

On a draft, that company link and the Dismiss button sit beside the title rather than inside the expander (2026-09-06). Before, clicking either one also expanded or collapsed the draft underneath, because both were inside the native disclosure that the title toggles.

A held draft in Waiting on you shows its title, how long it has waited and why it is there while it is closed, with Open the company and Dismiss beside it (2026-09-26). Before, the draft read only "Details" and its title and Dismiss appeared only after you opened it. The line under the headline now says how many decisions wait whenever the headline says your next decision is ready.

The rail also links to the dossier scan, the signed-in business brief that stays inside the app and needs no connection. The rail disappears once every step is done.

A clear next step. New accounts see the next setup action in the Start here card. Once the team is ready, the card holds your next decision and the queue follows it. Schedule details, full role reports and daily delivery settings expand when you need them; the next-focus note sits open under the queue.

Home is also where a new account lands the moment it is created. Until the account holds a seat, the page explains what will start and keeps the next action to buying one.

The guided setup at /onboarding begins with the business brief and sample standup, then offers the configuration steps in one place. Under Choose where output goes the in-app queue is always on and needs no setup; the step counts as done once Deliver to Google Drive is on for a seat or a self-hosted kernel is connected, because those are the two choices the product stores. Gmail drafts and Outlook drafts can be chosen on Home once that mailbox is connected (see Where your work lands above).

Related

• Persona Console: run and tune one role (schedule, drafts, runs, and settings).
• Activity: the full run history and what each pass produced.
• Receipts: what got written, the data it used, and why.