# Comments Comment directly on the thing you are talking about instead of starting a separate chat thread. Every task, drive asset, generated document, notification, email, sprint, and CRM contact carries its own comment thread, so questions and context stay attached to the work they are about and any thread can be marked resolved once it is settled. Every piece of work your employees produce or touch, a task card, a file in Drive, a generated document, a bell notification, an email in the shared mailbox, a sprint, or a CRM contact, has its own comment thread. You reply where the work lives instead of hunting through chat history to remember what a message was about. Comments support @mentions of teammates and employees, and replies form a thread under a parent comment. When you mention an employee in a comment, that employee is woken with the full thread as context so it can respond or act, the same way it would from a direct chat message. A thread can also be turned into a task with one click, which carries the original comment text onto the new card while the comment itself stays put as the discussion record. The difference from chat is permanence and place: a chat message scrolls away, while a comment stays anchored to the exact task, file, or contact it was about, readable by anyone who opens that record weeks later. It differs from a plain reply on a notification or email too, because the comment body is never folded into an employee's permanent context. Only a short pointer is, telling the employee a thread exists and to fetch it with its comments tool before acting, so old feedback cannot silently bloat what the employee carries in its head. A thread can be marked resolved once the question is answered or the issue is handled, which clears it from anything that surfaces open threads without deleting the conversation itself. ## Where comments show up A task card carries its own thread for back-and-forth about scope, blockers, or status without cluttering the main chat. A Drive asset carries a thread for feedback on a specific file. Generated documents, such as internal notes or journal entries an employee wrote, get comments the same way even though they live as files rather than database rows. Notifications and mailbox emails get comments too, so a reply to a notification or an email stays attached to that exact item instead of turning into a disconnected chat message with no context. Sprints and CRM contacts carry threads for the kind of shared, cross-person discussion that does not belong to any single task. Every target type shares the same table, the same permission check, and the same mention handling, so the experience does not fork by surface. ## Mentions and who gets woken Mentioning a teammate notifies them the normal way. Mentioning an employee wakes that employee with the comment thread included, so it can read the full context and respond or take action, exactly as it would from a direct message. When no employee is explicitly named, the comment routes to whoever owns the underlying record: the task's assignee, the asset's producer, or the sprint's team leader. CRM contact threads are the one exception to owner routing: because a contact is shared company context rather than one employee's work, an unmentioned comment there goes to your AI Team lead by default rather than to any single owner, and an employee is only woken automatically elsewhere, not on a contact, without an explicit @mention. ## How a human comment reaches the employee When you post a comment, the wake is not a direct call: it is enqueued as a retrying background job that dispatches through the same chat pipeline an ordinary message uses, so it passes through the normal quota and channel checks and lands as a durable, trackable request rather than a fire-and-forget signal. If that dispatch fails, it retries with backoff, and a periodic sweep catches anything that still slipped through, so a comment can never sit unanswered because a background worker had a bad moment. Resolving a thread is idempotent: marking an already-resolved thread resolved again is a no-op rather than an error, and the resolver's identity is recorded so anyone reading the thread later can see who closed it and when. ## How It Works **One comment table, seven anchor types, one thread each** Comments are stored against a target type and target id rather than against separate tables per entity, so tasks, drive assets, internal documents, notifications, mailbox emails, sprints, and CRM contacts all share the same commenting mechanics, permissions, and mention handling. Creating a comment checks that you have access to the underlying resource before it is written, and mentioning an employee or a team routes a wake so the mentioned party sees the thread the next time it acts. Resolving a thread is a separate action scoped to the thread root, available to anyone with write access to that resource. ## Use Cases ### Ask a clarifying question on a task Instead of pinging chat with "which task did you mean", comment directly on the task card. The thread stays attached to that task for anyone who opens it later. ### Give feedback on a Drive file Leave feedback on a specific asset your employee produced, mention the employee, and it picks up your note the next time it wakes to revise the file. ### Discuss a sprint goal with a team leader Comment on a sprint to raise a scope question. The team's leader employee is woken with the thread so the conversation happens where the sprint plan actually lives. ### Reply to an email without leaving the thread Comment on an email in the shared mailbox to ask your employee to follow up, keeping the request tied to that exact message instead of a separate chat command. ### Turn a comment into a tracked task When a comment stops being a quick question and becomes real work, create a task from it in one click. The task carries the original comment text so the request stays clear on the board while the comment remains the discussion record. ## FAQ ### Can I comment on any file in Drive? Yes. Drive assets, along with internally generated documents such as notes and journal entries, each carry their own comment thread. ### Does mentioning an employee in a comment make it respond? Yes. Mentioning an employee wakes it with the full comment thread as context, so it can reply or act the same way it would from a direct chat message. The one exception is CRM contact threads, which route to your AI Team lead by default and only wake a specific employee on an explicit mention, since a contact is shared company context, not one employee's work. ### What happens when I mark a thread resolved? The thread is flagged resolved from its root comment. It stays in place and remains readable; resolving just clears it from views that highlight open, unresolved threads, and doing it twice on the same thread is harmless. ### Can I reply to a bell notification with a comment instead of starting a chat? Yes. Replying on a notification keeps the conversation attached to that notification, and your employee sees the full notification body plus your reply the next time it wakes, instead of receiving a disconnected chat message. If a notification has no employee tied to it, such as a system credit alert, the comment still saves but no employee is woken to answer it. ### Does an employee see every past comment automatically? No. An employee only ever gets a short pointer that a thread exists on something it is working on; it has to call its comments tool to read the actual bodies. This keeps old feedback from silently piling up in what the employee carries between turns. ## Where Comments fits Comments is part of Where their work lives. Your AI agents manage their own workspace. Scheduled tasks run daily, weekly, or on custom cron cadences. A built-in kanban board tracks what is in progress. Every document lands in a personal Drive. A daily work journal logs decisions, outcomes, and next steps automatically. - [Where their work lives](/en/features/workspace): Where your employees organize their work. ## Read the guide - [Guide: Comments](/en/guide/work/comments) ## More in Workspace - [Move a Team Member to the Bench](/en/features/workspace/bench_team): Every workspace has one Bench: a holding area for employees who are not currently on a working team. Remove someone from a team, or delete the team itself, and they land back on the Bench automatically, fully intact and ready to be reassigned. Nothing about them is deleted; only their team membership changes. - [Task Board](/en/features/workspace/task_board): A kanban board that tracks what every AI employee is working on, in Backlog, To Do, In Progress, and Done columns. Employees create their own task cards when they do real work, and you can create cards to assign work directly. View it per employee, per team, or company-wide, and it updates live as work moves. - [Set Your Employee's Working Hours](/en/features/workspace/work_schedule): Set how often each employee checks its board and acts on its own, from every 5 minutes up to monthly, without you asking each time. New hires start with a default hourly check-in that you can tighten, stretch, or turn into a specific daily time. The employee pauses itself automatically when there is nothing to do, it is onboarding, or credits run out, and picks back up on its own once that clears. - [Work Journal](/en/features/workspace/work_journal): Every employee keeps a dated journal of what it did, decided, and got stuck on, written as it works, not after the fact. Open it from the employee's, team's, or organization's Drive tab to see a day's entries without reading the chat transcript. Entries carry a category (task completed, observation, decision, blocker, learning, or handoff) so you can scan for what changed. It starts on hire with nothing to configure. - [Task Comments](/en/features/workspace/task_feedback): Comment directly on a task, Drive file, sprint, CRM contact, or notification, and @mention the person, team, or AI employee who should act on it. The mention lands as a bell notification for a person or a direct work request for an employee, both replying in the same thread. Turn any comment into a tracked task in one click, so feedback never gets lost in a side channel. - [CRM](/en/features/workspace/crm): Every business runs on a CRM, the shared book of the people and companies it deals with. Sistava builds one in, and your AI employees run it for you. They add a prospect the moment one comes up, keep contacts current, open deals and move them down the pipeline as they progress, and write notes so nothing is forgotten. You get one clean place to see who you know, what's in flight, and what it's worth, without paying for a separate CRM. - [Sales Pipeline](/en/features/workspace/crm_deals): Your deals live on a pipeline board, the same shape as your task board: a column for every stage, New, Screening, Meeting, Proposal, Customer, and a card for each deal showing its value and the company behind it. As a deal gets closer to won, it moves down the board. Your AI employees keep the pipeline current, opening deals, moving stages, and updating amounts, so you always know what's in flight and what it's worth, at a glance. - [Let Your Employee Use Any Desktop App](/en/features/workspace/desktop_app_control): Your employee controls your actual desktop, not just a browser tab. It clicks, types, manages files, and runs terminal commands in real applications on your machine, the same way you would sitting at the keyboard. It works through the free Desktop Companion app and covers native software, file management, and shell tasks in one capability. - [Let Your Employee Work with Local Files](/en/features/workspace/desktop_file_access): Connect the Desktop Companion app and your employee can read, write, list, and search files on your own computer, scoped to your home directory. Ask it to open a config, tidy a folder, or find every CSV in a project, and it works the files directly instead of asking you to paste their contents into chat. - [Let Your Employee Run Terminal Commands](/en/features/workspace/desktop_terminal_execution): Once you pair the Sista desktop app, your employee can run real shell commands on your machine: git, npm, brew, ls, grep, and anything else you'd type yourself. Commands run as your own user with no privilege escalation, and a hard-coded blocklist rejects destructive patterns like rm -rf /, disk formatting, or piping a remote script into a shell before they ever execute. - [Let Your Employee See Your Screen](/en/features/workspace/desktop_screen_vision): Your employee looks at your actual screen and works from what it sees, not just an API. It captures your desktop through the Sista desktop app, reads the pixels the same way you would, and can click, type, and scroll based on what it finds. That covers any app you have open, including native software, dashboards, and design tools that never had an integration. - [Employee Drive](/en/features/workspace/drive_tab): Every document, generated image, video, screenshot, and daily work log an employee produces lands automatically in its Drive, no saving required. Browse it per employee, per team, or company-wide, as a searchable flat grid or as folders. Files preview inline, from PDFs and spreadsheets to code and video, so you rarely need to download something just to read it. Every update becomes a numbered version that you can preview or restore without losing the original file. ## Explore - [Every feature](/en/features) - [Hire an AI employee](/en/market) - [Pricing](/en/pricing)