What brand chat can do
- Write and revise on-brand copy.
- Work on your own website, other first-party sites, social profiles, and key pages without being given the URL. Daoco carries them in brand context from the sources you used during onboarding, so “look at our pricing page” is enough.
- Generate, edit, and resize visuals.
- Create draft social posts and prepare publish approvals.
- Run research, SEO, campaign, short-form video, and analytics tasks.
- Open workflow panels for richer review and editing.
- Refresh brand context after you approve the proposed changes.
- Work with connected integrations when the workspace has them enabled.
- Copy structured text blocks, such as hooks or campaign copy, directly from assistant responses when Daoco renders them as copy cards.
- Pause, resume, stop, retry, or queue follow-up instructions while longer work is running.
- Follow a live, turn-by-turn execution ledger and stop an individual delegated branch when the control is available.
- Send a result to yourself through your assistant on WhatsApp, Slack, or Discord, or ask to be pinged there when the work finishes.
How chat routes your request
Daoco uses one main chat thread for most work. When you send a message, Daoco decides the best specialist for the job:- Slash commands. A command such as
/postor/site-auditstarts that workflow and runs its steps in order. See Assistants and slash commands. - Follow-up in the same workflow. A continued post, short-form video, campaign, or brand refresh stays with the active workflow instead of restarting.
- Natural language. For everything else, Daoco interprets the request and may run one specialist or a short sequence, such as research before writing. Mentioning social tools in a research question or asking for a short comparison does not request social-post or video work.
Organize your chats
Hover over a chat in the sidebar and click the … button, or right-click the chat, to rename, pin, archive, or delete it. On a phone the button is always shown.- Rename turns the title into a text box. Press Enter or click away to save, or Escape to keep the old name. Collapsing the sidebar with Cmd+B (Ctrl+B) also keeps the old name. You can also double-click the open chat’s title. A name you give a chat stays; Daoco no longer retitles it. Everyone on the brand sees the new name.
- Pin to top moves the chat into a Pinned group above your recent chats. Pins are yours: teammates on the same brand keep their own. You can pin up to 20 chats per brand.
- Archive moves the chat to the Archived list, opened from Archived at the end of the chat list, and offers Undo for a few seconds. Undo does nothing if someone changed or deleted the chat in the meantime.
- Delete asks first, then removes the chat from the list for everyone on the brand, Archived included, and offers Undo for a few seconds. A deleted chat is closed: messages queued in it are cancelled, nothing new can start in it, and your assistant and connected AI apps can no longer read or continue it. Drafts, assets, and anything else the chat made are kept, but calendar slots it was holding are freed for other chats. Undo puts the chat back where it was, unless someone changed it in the meantime; it doesn’t take the freed calendar slots back. A chat that is still working, paused, or waiting on you can’t be deleted until you stop or answer it.
Workflow answers
When a workflow such as/site-audit or /product-copy finishes, its answer opens with a short note from Daoco, then shows the last step’s report exactly as that specialist wrote it, then the What I couldn’t check list. Daoco does not retell the findings in its own words, so the report keeps every limit the specialist stated (“unchanged for the nine pages with an audit history”, “within the crawl’s coverage”). The earlier steps’ reports stay in their rows above. If the last step was skipped or failed, Daoco writes the answer itself and says what was left out.
If Daoco’s AI provider is unavailable when Daoco goes to write its answer, and a specialist has already finished its report, the answer is that report as the specialist wrote it, under a one-line note saying Daoco couldn’t write its usual summary. You see the work that finished instead of an error. If no specialist finished, the chat shows the error and you can try again.
What I couldn’t check
When specialists worked on a request, the final answer can end with a short What I couldn’t check list. Daoco builds it from what each specialist’s tools actually returned, not from the summary above it: a read that failed or was declined (for example “Speed and Core Web Vitals: could not be checked (PageSpeed quota exhausted)”), a field a connected app did not return (“Product options: not returned by Shopify”), a lookup that found nothing recorded, named with what it searched (“SEO and AI-visibility fixes in the code lane taken on in the last three weeks: none recorded in Daoco”), a result or web page that was only partly read, or a step’s connected source that was never read. Treat each line as unknown, not as a problem found or ruled out. A closing Checked line says what the run did read, counting each product, page, or report once however many times it was read, such as “Site crawl (34 pages), Shopify (17 products), Web pages (6 pages: daoco.org, …)”. If a source was read by any specialist in the run, it is not listed as unread, and something one specialist could not check that another one checked is dropped or narrowed to what was checked, counting only the crawled pages it covered (“Whether Google indexed the pages: checked separately for 5 of 34 pages, and for 15 pages outside the crawl”).Run specialists at the same time
Daoco can hand parts of a request to several specialists at once, for example researching competitors while drafting a post. Adjacent specialists sit under one header. While any of them is still going it reads “Kicked off 3 specialists · 2 working”, and once they all finish it reads “Ran 3 specialists · ✓ completed”, or names what didn’t finish (“1 failed”, “1 stopped”). A specialist is only counted as completed when it actually completed. The Parallel toggle in the composer (it reads One at a time when off), next to the approvals toggle, sets this per thread. It is on by default, and specialists can work at the same time. When it is off, Daoco runs one specialist at a time. You can set it before your first message in a new chat and it applies to the thread that message creates. Specialists that can ask for your approval, such as the ones that publish, schedule, or change a connected app, always run alone, even with the toggle on. Specialists running together each use tokens at the same time. When your token balance is too low to cover them all, Daoco runs fewer at once, or one at a time, and says so in the chat with a note such as Running one step at a time. The work still finishes; it takes longer.The specialist view
Click a specialist’s row to open its view in the chat column. The view looks like the thread: the specialist’s own transcript (its tool calls, its notes, any specialists it handed work to, and its result) in the same column, with a bar where the composer usually sits. If the specialist produced something for the side panel, such as a draft or a report, the side panel shows that specialist’s items while its view is open, and the thread’s panel comes back when you return to the thread. The view’s address includes the specialist, so refreshing the page or sharing the link opens the same view. The view is read-only. The bar shows the specialist’s type and title, its status, how long it has run (frozen once it ends), and that it runs on its own. Stop ends that one specialist and leaves the rest of the run going; the specialist then reads Stopped, not failed. A specialist waiting on your approval has no Stop button: answer its approval in the thread instead. Back to thread or Escape returns to the thread with its scroll position and your draft intact.Approvals with several specialists
Every approval waiting in a thread sits above the composer, oldest first, which is the order the work is blocked in. When several are waiting, the bar shows 1/3 with arrows to move between them and Approve all 3 to answer them together, and the side panel shows the same one in full. Approve all leaves out questions, deletions, browser actions that require an individual approval, and approvals to post, schedule, or render a final video; you answer those one at a time. An approval you answer leaves the bar at once and the next one takes its place. Each lists every choice it offers, such as Post now, Schedule, Edit, and Reject, and one line on what approving does: it covers that one action, or, for changes in a connected app, it also lets Daoco keep making changes in that app for the rest of the chat. An approval raised by a specialist says which one is asking, for example “Research asks”; click the name to open that specialist. A specialist’s view shows its own approvals above its bar, and you can answer them there. If the run that asked has ended, the approval says so and offers Dismiss instead of approving something that would do nothing. If you type “approve” instead of clicking, it answers the approval only when exactly one is waiting. With more than one, none is answered and Daoco asks you to use the cards. Approving a brand document change applies it wherever you approve it: here, on its review page, or from your assistant. Approving a post publishes or schedules it the same way, wherever you approve it. An approval to render a video at final quality is answered from its own review in the chat, where you pick the clips; anywhere else it says so instead of approving. Bypass approvals and your approval preferences apply to every specialist in the thread the same way. In the sidebar, a working thread shows a spinner; which specialists are running is in the thread’s plan.Control active runs
Long-running work can involve research, publishing checks, campaign planning, or specialist tasks. When a run is active, the composer can show controls for the current state:
Some pauses are waiting for a required action, such as an approval, reconnect, or browser auth. Complete the card shown in chat instead of using Resume for those pauses.
Attach images
You can attach up to 50 images to one message. Multiple images appear in a thumbnail grid; click a thumbnail to open the gallery and use the arrow keys to move between images. A follow-up without new files keeps the most recent upload available for up to 24 hours, including the whole set of images. Daoco also keeps track of which message each of the thread’s last 24 files came with, with no time limit, so you can say “use the video I sent this morning with this photo” and Daoco hands both to the specialist without a re-upload.Send follow-ups while work is running
You can send another instruction before the current run finishes. The follow-up appears immediately at the bottom of the transcript as a faded, dashed bubble marked Queued, under the line that shows what the current run is doing. That line always belongs to the work above it, never to your queued message. Each queued bubble carries its own controls: Steer, Redirect (when the run can be interrupted), Edit, the up and down arrows, and Cancel. Steer and Redirect only appear while the run can take a correction, and Redirect is left out while a specialist is working, since it can’t interrupt one; when the run can’t take a correction, for example while it waits on an approval or the thread is being compacted, the bubble says so and when Steer comes back. Edit changes the text inside the bubble. The message keeps its files and its place in the queue, and whatever you were typing in the composer stays where it is. Press Enter or Save to keep the change, or Escape to discard it. If the run picks the message up before you save, the original text runs, and your edited text goes to the composer so you can send it next. The arrows move a message up or down the queue, which changes the order the messages run in. Cancel removes a message before it reaches the model; for a minute afterwards, Undo in the note that appears puts it back in the same place with its files. Long messages collapse to a few lines with a Show more toggle, and attached files show as thumbnails. When the run picks the message up, the bubble becomes a normal message just above the working line. While that happens it reads Sending… and can no longer be cancelled. Each queued message says when it will run. An ordinary follow-up says Runs when this response finishes and waits for the whole answer. A message you steer into the run (click Steer, or press Cmd+Shift+Enter / Ctrl+Shift+Enter to steer the oldest queued message) says Folds in after the current step: the run picks it up at the next break between steps, usually within a step or two rather than at the end. If a specialist is working when you steer, the specialist gets your message at its own next step and applies it to the work in progress, so a correction to a post reaches the writer drafting it rather than waiting for the draft to finish. Daoco then knows the specialist already had it and doesn’t redo that work. When a steered message lands, it appears in the transcript as your full message, marked Steered, at the point the run read it. Anything the run wrote before that stays above it, and everything below it is work done after your correction. When the turn finishes, the work before the steer gets its own “Worked for” line and the work after it reads “Continued for”. Files on a steered message reach the run with it and show with the message. When a response finishes, its routine steps (looking things up, reading drafts, checking the calendar) fold into one line, such as Worked for 20s · 3 steps. Click it to see the steps. Anything you need to act on or read stays out: cards, approvals, failed steps, and the answer itself. Corrections stay with the active run across retries and continuation steps. Your latest correction can change the original plan, while approval and publishing restrictions still apply. Steering waits for the step the run is in to finish. When you would rather not wait, a queued message also offers Redirect: the run stops the step it is in, folds your message in immediately, and carries on as the same run. Because it stops work in progress, the bubble asks you to confirm first with Redirect now and names what it will throw away: the tool call it cancels, and anything the current step had written. Finished steps are kept, and your message appears in the transcript marked Redirected. If you click Stop run while the redirect is taking effect, the run stops instead of starting another step. If the run ends before it absorbs the message, the bubble clears the Redirecting label; a later run does not inherit the redirect. If the run cannot be interrupted right then, because a specialist is running, it is waiting on an approval, or it has not started work yet, the message stays a steer and the bubble says so. When the active run is safe to steer, a plain-text follow-up can guide its next step without waiting for a second turn. If the run is compacting, paused for approval, or otherwise stops being steerable before the message lands, the bubble says Couldn’t fold in; will run when this response finishes and it runs as an ordinary follow-up. Compatible plain-text messages can be combined into one follow-up turn; messages with attachments stay separate. If a message cannot start because the workspace is out of tokens, whether it is the first message in a chat or a follow-up, it stays in the chat marked Out of tokens with your text and files intact, alongside Manage billing, and runs on its own once the balance is back. It is still there after a reload. Cancel it if you would rather not wait. If your workspace already has as many runs going at once as its plan allows, a new message waits in the queue as well, and starts on its own as soon as one of those runs finishes. Use Stop run when you want the current run to end now. From the keyboard, press Escape twice: the first press asks you to press it again, and the second, within two seconds, does exactly what Stop run does. It works while you are in the chat: in the empty message box, or after clicking anywhere in the conversation to read it. Escape does nothing here while you are typing in the message box, while a menu or dialog is open, or while a specialist’s view is open (there it returns to the thread). The transcript reads Stopping… until the backend finishes checking the run, then You stopped this run. Stopping closes any approval the run was waiting on, so an old approval card can’t restart the stopped work. Messages you queued behind it are held, not sent: each bubble reads Held after you stopped and offers Send now, Edit, and Cancel. Send now runs it as the next message, or queues it behind a run that is already going; nothing held runs until you choose. A new message you send while others are held starts on its own and leaves them held. Messages that came from your team assistant or a connected AI app stay queued and run next, so the person who asked still gets an answer. If you paused the run yourself, queued follow-ups wait until you resume, and their bubbles say so.What the loading line is telling you
While a run is working, there is always one line under the transcript. It names what the run is doing now: understanding the request, planning, drafting, working through the steps, handing off to a named specialist, reviewing what that specialist found, writing, or continuing when a long turn picks back up in a fresh step. Beside it are the tool in use and how long the turn has been going. The line stays on its stage for as long as that stage is true, and only says “Working on your request” when nothing more specific is known. Between a finished run and a queued follow-up starting, it reads “Starting your follow-up”. When a specialist’s row is already showing its own progress, or Daoco’s reply is streaming in, the line shrinks to just “Working” and the elapsed time, so you never see two spinners and never see none. Once the answer is written and the run is only wrapping up, it reads “Finishing up”. A follow-up you queued starts its own clock when its turn starts, not when you typed it.Interactive visuals
Daoco shows charts, tables, diagrams, and comparisons as interactive visuals directly in a reply. The orchestrator and the question, research, SEO, and campaign specialists create them; writing and social specialists answer in text. Visuals can open in the workflow panel and remain available when you return to the thread. Charts in replies from before this change keep their original look. Charts built from stored brand data read the saved figures for published posts, content analysis, keyword ranks, and AI visibility. Use the HTML and PNG buttons above a visual to download it. Reports sent through an assistant on WhatsApp, Slack, or Discord include a PNG when rendering succeeds. The page runs in a sandbox that blocks access to your dashboard and external resource requests. Browser sandboxing does not fully prevent a page from navigating itself to another URL, so it does not guarantee that data embedded in a visual stays offline.Work safely
Daoco asks for confirmation before sensitive actions such as publishing, scheduling, applying brand updates, or making provider changes through connected integration tools. The approval card identifies the requested operation, target connection, and relevant scope. Review those details with any previews, diffs, attachments, and dates before approving. Approving an ordinary provider write runs exactly that action and also lets Daoco keep making updates on the same provider for the rest of the thread without asking again, so one approval covers the whole job. Destructive changes, such as deleting something in a connected app, are always approved one at a time. The approvals toggle in the composer reads Approvals on normally; turning it on bypasses approvals for the current thread and it reads Skipping approvals: gated actions, including publishing, run without asking until you turn it off. Turning it on while a connected-app write approval is already waiting answers that approval too, so the paused run resumes on its own; other kinds of waiting approvals keep their card and still need your answer. Deletes still ask, actions that always require confirmation (like a paid final render) still ask, and a connection that is turned off or read-only still refuses. The toggle is per thread, requires the workspace owner or admin role, and stays on across refreshes. Turning it off also withdraws the provider access the thread was granted while it ran open, so the thread goes back to asking. A workspace admin can turn the feature off entirely under Settings → Workspace → General, which hides the toggle and puts already-bypassed threads back to asking. Brand owners and admins set approval preferences per brand. Ask before acting is the default. Work autonomously allows ordinary connected-app updates without asking, while Full autonomy can also publish and send. Per-connection exceptions can make access stricter or allow ordinary updates on one connection.Browser sign-in and the live browser
Some tasks run in a signed-in browser: on LinkedIn, Instagram, Facebook, X, Threads, TikTok, YouTube, and Bluesky, or on any other site you added as a site profile. When a sign-in is needed, Daoco shows a sign-in card in chat. Open the secure browser, sign in, then confirm on the card so Daoco can resume the request. While Daoco works in the browser, the workflow panel’s Browser tab shows what it is doing, and you can take control and hand it back. See Browser automation. You can clear the browser session from Connections without disconnecting the platform’s OAuth or API connection. See Browser profiles.Chat activity signals
When a background run finishes in another thread, the sidebar can highlight that thread until you open it. This is useful for long research, scheduling, brand refresh, and generation work that may complete after you switch surfaces. While you are on another chat or another page, a short note appears when a chat in this brand needs you, finishes, or stops with an error. Select Open to go to that chat. Chats started by an assistant or a brief inbox only notify you when they need you. The browser tab title shows how many chats are waiting on you, for example (2) Daoco. To get a system notification while the tab is in the background, turn on Desktop notifications in your account settings. System notifications only say which brand the chat is in and what happened, never the chat’s title or content. With several Daoco tabs open, you get one alert, and none for a chat you already have on screen. Your browser asks for permission when you turn it on. Chat alerts in the same place turns the in-app notes off. Both settings apply only to the browser you set them in. Each thread in the sidebar shows its state. A paused thread says what it is waiting on: Needs approval, Reconnect needed, Sign-in needed, Out of tokens, or Paused by you. A run that runs out of tokens while it works pauses and picks up where it stopped once you add tokens; see Understand token usage. A thread you stopped shows Stopped, not Failed or Done. A run that ended because the workspace is out of credits, or because a usage limit was reached, shows Limited with the reason, in the sidebar and in the thread’s status row. That is not an error in the work: add credits or wait for the limit to reset, then retry. How chat looks is set in your account settings. Theme is Light, Dark, or System (follows your computer) and follows your account to other devices. Text size (Small, Default, Large), Chat width (Comfortable, Wide, Full), and Time format (Automatic, 12-hour, 24-hour) apply to the browser you set them in. Text size changes every Daoco page in that browser, including the website and review pages, not only chat. Hover over a reply to see when it was sent and to copy it. Work that happens outside the thread you have open shows up under Needs you in the sidebar, below Assistants. On Growth it is called For you. It covers assistant tasks that reported back or are waiting on you, and open items in the brand’s queue. The section appears only while something is in it and shows the first four items; Show more lists the rest, and Clear dismisses everything except the approvals, questions, and reviews still waiting on you, which you dismiss one at a time. Selecting an update takes you to its thread. Dismissing an update hides it for you only. It does not approve, cancel, or resolve anything. Updates about the thread you are viewing are left out. On Growth, the list follows Mine and Team above the chats: Mine shows updates about chats you started, approvals assigned to you, and brand-wide updates that belong to no chat, such as a connection that needs attention, and Team shows the whole brand’s. On Starter, it always shows every update. To hide the section, turn off Show Needs you in the sidebar (Show For you in the sidebar on Growth) under Settings > Preferences. While the sidebar is collapsed, the items show as their status icons above the chats. Updates you already dismissed stay dismissed if you turn it back on. While a turn is running, the transcript shows a single live status and elapsed time. The execution panel breaks the request into plain-language steps such as Understanding the request, Researching, or Writing the copy. A required approval changes the relevant step to Waiting for you. Finished turns keep their duration and can be reopened in the ledger. When Daoco plans a request in more than one step, a bar above the composer shows the step it is on, which specialist is doing it, and how many steps are done, for example Now: Researching · Research · 1 of 4 done. The whole plan is in the Progress panel. A step that is waiting on your approval reads Waiting. The bar goes away when the run finishes or stops. As a multi-page SEO audit grows, consecutive updates appear as one audit entry that opens the latest combined report. Separate audits and failed steps remain visible. The composer context meter shows current context pressure and, once usage has been billed, how many basic tokens the thread has charged so far. Hover it for in, out, and total thread usage. See Understand token usage. Long tasks can continue across execution windows using saved progress. Image sets are tracked by saved item, so later windows can finish missing items without replacing completed ones. A run that reaches a limit or stops making progress reports the remaining work. Review the saved outputs if the run stops early. Stopped runs show a stopped state instead of a generic failure. When the run stopped part-way through a step, the composer offers Continue run: Daoco picks up from the interrupted step and reuses everything that already finished instead of starting over. Retry run is offered when there is nothing to pick up from, and starts a fresh attempt from the latest request. If the run already posted, sent, or changed something outside Daoco before it stopped, Continue run and Retry run are both off, so the change is not made twice. Ask in the chat to pick up where it left off; Edit and resend stays available. Edit and resend, above the composer, reruns the same request with wording you change; any files on the original message are kept. After a run finishes, Retry next to its “Worked for” line sends your last message again as a new run, with the same files. If that turn already posted, sent, or changed something outside Daoco, such as a publish, an email, or an edit in a connected app, Retry is off and a short line says so: ask again in the chat if you want it done again. A processing-limit error means the agent run stopped; it does not by itself mean an attached file is invalid. Saved outputs remain available for the unfinished work. If your connection drops, a note above the composer says Daoco is reconnecting, or that you are offline. Work keeps running on Daoco’s side, and the chat catches up when the connection is back. A request on a thread your assistant started does not offer Retry; ask the assistant again in the same chat app so the answer goes back there. A resumed turn, after a reconnect, a sign-in, or a Continue, is marked in the transcript with a short “Continued” divider rather than a message that looks like you sent it. If a connected-tool step fails, Daoco separates connection setup problems, expired authorization, provider refusals, and temporary transport errors when it can. A retry keeps the original connection and approval scope. Reconnect only when the recovery card says the provider authorization needs attention.Use chat with product surfaces
See Workflow panels for the right-side review surfaces and Assistants and slash commands when you want explicit routing.
Click an image attachment to enlarge it in chat. Close the preview or press Escape to return to the conversation.