The tone row sits ABOVE the smart-reply chips so you choose tone first, then click a chip to fire generation. The row is a single horizontal scroller at every screen width, on desktop as well as on a phone, and it never wraps to a second line. Your own default tone is always the first pill. Press Alt+T to cycle through tones from the keyboard.

• Customer-friendly: the new default. Warm but professional, like a thoughtful customer-success rep.
• Match my style: uses your writing style in full, including how formal you usually are (see Writing style below).
• Match recipient: mirrors the recipient's style based on their prior messages in the thread.
• Brand: uses the org brand-voice description set by an admin. Hidden when no brand voice is configured.
• Match sender, Warm, Professional, Direct, Formal, Casual, Brief: concrete tone presets.

Picking a tone on the strip applies to that one message. To change the voice Laureo uses from now on, open Email settings (the gear in the inbox toolbar, or Settings > My preferences > Email inbox), go to AI in your inbox, and set Default reply tone. That one picker governs every reply Laureo writes for you, including auto-drafts, unless you pick a different tone for a particular message.

Until you choose one, the row's description tells you which default you are actually inheriting, the workspace default or the app default, rather than showing an inherited value as though you had picked it.

Open Email settings (the gear in the inbox toolbar, or Settings > My preferences > Email inbox) and go to AI in your inbox. Laureo reads new email from people, never newsletters or automated mail, and prepares replies and reminders. It never sends anything for you. Every setting here is per user: it governs your own mailbox and changes nothing for your teammates.

• Draft replies for: tick whose email gets a reply draft as it arrives. People in your CRM, Everyone else who writes to you (newsletters, notifications, calendar invites, out of office replies and shared inboxes like billing@ are skipped), and Cold outreach replies, shown when your workspace has AI drafting for cold outreach. A cold reply gets a draft when the prospect is interested, wants to meet, asks a question or pushes back, and each campaign's own Draft replies with AI setting still applies. All three are ticked by default; untick all three and the row reads Drafting is off.
• Spot emails that need a reply: With AI, the default, reads each new email from a person once, as it arrives, to see if it needs your reply. Rules only decides with simple rules alone, such as the sender and a question in the message, and uses no AI. An email the rules cannot decide gets no reply draft. The same check also reads each email you send, to see if it asks for a reply.
• Remind me about emails I haven't answered: when a new email from a person needs your reply, a Reply item for it goes to My Work as it arrives, and it clears once you reply in that conversation. On by default.
• Remind me when people don't reply: a reminder when an email you sent asked for a reply and none came back. Off, People in your CRM, or Everyone I email, the default. The reminder goes to My Work as a Follow up item once your Remind after wait has passed.
• Remind after: how long that reminder waits, from 1 to 30 business days or calendar days. 3 business days by default.
• Also draft the follow-up: a follow-up draft is ready about an hour before each of those reminders, in the conversation and in Drafted for you, for you to review and send. On by default.
• Suggested actions: which emails get the one-click AI action suggestions (reply, log, create task): Off, Emails from your contacts (mail matched to a person or company in your CRM), or All real conversations, which still skips newsletters, calendar invites, out of office replies and automated mail.

In the Inbox, the first block above your mail is Needs your attention. It gathers what waits on you in three groups:

• Drafted for you: reply drafts your assistant wrote that you have not changed yet, each with the reason it was written.
• Needs reply: email from people that you have not answered. It follows your Remind me about emails I haven't answered setting.
• Awaiting reply: email you sent that nobody has answered after your Remind after wait, and the reminders you set yourself that are due. It follows your Remind me when people don't reply setting.

Each conversation shows in one group only, the first one it fits. A group shows its three newest rows and its count, which reads 25+ above 25. Click a row to open that conversation. When a group holds more than three, Show all opens the full view: the AI drafts filter in Drafts, or the Needs reply or Awaiting reply status. That view can count a few more or fewer rows, because it does not narrow to your segment or mailbox in the same way.

On a computer, the heading folds the section into one line of counts, and your choice is kept. On a phone the section starts folded; tap it to open it for that visit. It shows only in the Inbox, never while you search or while the Needs reply or Awaiting reply status is on, and it hides when nothing waits. On Cold, it lists drafted cold replies only.

A reply is drafted only for new email, as it arrives after you connect your mailbox. Connecting a mailbox never drafts replies to your older mail. Each conversation holds at most one waiting draft from your assistant: a newer email in the same conversation replaces it, and a draft you started yourself is never overwritten. Laureo never sends a draft. It waits in Drafts and in Drafted for you at the top of your inbox, and the conversation's row reads Draft with the assistant's mark. Open the conversation and one line above the reply box says why the draft was written, with Review before sending. and Discard. Your first change makes the draft your own, and the assistant does not rewrite it.

• Which email gets one: a new email from a person that the reply check finds needs your reply, when your Draft replies for row includes that sender. Newsletters, notifications, automated mail and shared inboxes like billing@ never get one.
• The reason: the line above the reply box names it, for example that the sender asked you a question, asked you to do something, mentioned a deadline or wants to find a time.
• Cold outreach replies: a draft is written when the prospect is interested, wants to meet, asks a question or pushes back, when your row includes Cold outreach replies and the campaign's Draft replies with AI setting is on.
• Follow-ups: with Also draft the follow-up on, a draft to the person you wrote to is ready about an hour before a reminder that they have not replied.
• Limits: drafting uses your workspace AI credits, and each workspace has an hourly limit that depends on its plan, so a burst of mail can leave some email without a draft. Collaborator seats get no reply drafts.

Writing help is the AI button on the formatting row of the compose window and of the reply box under a message. It works on any draft, one you typed as well as one Laureo wrote, and only on the words above your signature: your signature and the quoted message below it are never changed.

• Proofread and Polish open a list of suggested changes you accept one by one or all at once (see Proofread below).
• Shorter, Longer, More formal, More casual and Match my style rewrite the draft in place. Press Cmd+Z once to put it back.
• Review suggestions appears first in the menu while writing suggestions are underlined in the draft, and lists them (see Writing suggestions below).

Writing help is off while a draft is being written for you, on an empty draft, and on a draft longer than 4,000 characters. After Laureo writes a reply in the reply box, the refinement bar below it still offers Shorten, Elaborate, Polish, Formalize, Casual and Match my style, and its Undo keeps up to 3 earlier versions.

Proofread fixes spelling, grammar and punctuation, and rewrites a sentence only when it is unclear. It keeps your wording, your tone, names, links and numbers. The suggestions open in a panel beside the button, each one shown as the old words struck through followed by the new words underlined. Polish opens the same panel with smoother phrasing and word choice.

• Accept applies one change, Reject drops it, and Accept all applies every change at once. Each is a single Undo step, and a word you corrected inside a link or in bold stays linked or bold.
• A change that runs across a line break says Edit this one by hand.
• If you edit the draft while the panel is open, it says Your draft changed. Run Proofread again.
• No changes needed. means the draft is fine as it is.

While you write in the compose window or the reply box, Laureo checks the paragraphs you changed a few seconds after you stop typing, and underlines spelling and grammar fixes with a wavy line. Hover an underline, or rest the cursor in it, to see the change, for example folow → follow:

• Accept makes the change, as one Undo step.
• Ignore hides that suggestion for the rest of the draft.
• Ignore until edited hides it until you change those words.
• From the keyboard, open Writing help and choose Review suggestions to work through every underlined change in a list.

Your signature, the quoted message, tables, code and lines with {{placeholders}} are never checked, and the underlines never change what is sent or saved. Only the paragraphs you changed are checked again, up to 15 checks per draft, and each one uses your AI credits the way Proofread does. Writing suggestions are on by default. To turn them off, open Email settings, then AI in your inbox, and switch off Writing suggestions; Proofread keeps working.

Your writing style is learned only from emails you wrote from your own mailbox. Cold sequence sends, campaigns and templates are never used. It applies to every draft written for you: a draft from the AI button, a reply chip or a custom reply, an auto-draft, and a draft the assistant writes for you. It is separate from the customer context, which says what a draft is about and who it is to; the writing style only says how you write.

• What it covers: how formal you usually are, how long your emails usually run (only once enough of your sent emails have their full text stored), how you usually greet people, and a short note on your style. A tone you pick yourself still decides how formal a draft is.
• Your own openings and closing lines: add up to three of each, one line of 200 characters or fewer, and drafts use one when it fits.
• Turn it on or off in Settings > Laureo AI preferences, under Writing style. If you have no writing style yet, turning it on builds one from your recent sent emails. Owners and power users in a workspace that stores email bodies may find one built automatically; the page then says when.
• Delete it in Data controls. A deleted writing style is not rebuilt automatically.

Select a sentence or paragraph, then choose a rewrite action. The AI streams a replacement with the same meaning but a different shape: shorter, longer, more formal, more casual, or matched to your style. You can also type a free-form instruction.

Click the AI button in the compose toolbar, type a short instruction (“ask about pricing”), pick a tone, and the draft streams character-by-character. Two separate things shape it. Your writing style is how you write, learned from emails you wrote. The customer context is about the person you are writing to: their CRM record, notes, meetings, activities and your prior emails with this person, in both directions. When the recipient is not in your CRM yet, the customer context is your prior emails with them alone, and a brand new address has none, so the draft does not pretend to know them. The draft also knows who is writing: your name, your workspace and what your business does.

Writing a reply from the compose window? The draft reads the message you are answering and the conversation before it from your own mailbox, with their full text rather than only a preview.

Inside an inbound thread, click Auto-draft reply next to the inline- reply textarea. The AI streams a full draft using the recipient's engagement signal, recent activities, and the prior message in the thread (no instruction text from you). Edit before sending; the AI never auto-sends.

Each generated draft, from the AI button or a reply, surfaces a Why this draft panel under the editor. It shows what was used in separate groups: Writing style (how you write, learned from emails you wrote; shown only when it was applied), Customer context (the CRM record, notes, meetings, activities and your prior emails with this person, for example “5 past emails with this address”) and Your business (what your business does and your saved preferences). Click any cited item to open the underlying entity in a new tab. Items dropped because of space appear in a collapsed list below.

A conversation of two messages or more carries an AI summary available bar above the message. Open it and you get the key points first, then any action items, written as they arrive. Nothing is generated until you open it, so a thread you only glance at costs nothing. Once you have opened one summary in a browsing session, later threads are prepared just ahead of your click so the panel fills faster.

A single message gets the same bar once it is long enough to be worth summarising: about 1,200 characters of readable text, counted after quoted replies and forwarded copy are stripped out, so a two-line note under a long quoted history is not treated as long. The bar reads AI summary available (this email) in that case, and Summarize Thread in the message menu scrolls to the same card and follows the same rule.

The two universal chips (Quick thanks and Custom…) are pre-rendered when the email opens, so you can act in under 100 ms. Context-aware dynamic chips stream in alongside them as the LLM responds. Most inbound emails are warmed at sync time, so dynamic chips usually land in under 200 ms on the first open; a cold-cache open (rare) takes 1 to 2 seconds. Once chips exist for an email they are cached for 7 days and re-served instantly on subsequent opens.