Ask About This

See a file or a task and want to ask about it right now? One button opens the employee's chat with that item already referenced, so you can just type your question instead of hunting for a link to paste. It works from the Drive file viewer and from any task card.

Every file and task in Sistava has an Ask button next to it. Click it and the employee's chat opens with the item already named, so you skip the copy-paste step between seeing something and asking about it.

On a task, the button drops you into the composer with an opening line naming the task title, cursor ready at the end, so you just finish the sentence and send. Nothing is sent for you; you always write the actual question.

A file works differently and that difference is the point. The main Ask button on a file skips typing altogether: it hands the employee a fixed instruction to open the file at its Drive path, read it, explain its current state in plain language, and ask a useful follow-up, no words of your own required. A small icon button next to it falls back to the classic version, opening chat with the reference pre-filled so you can write the first line yourself instead. Tasks only get that classic version for now.

Where you'll find it

The Ask button sits in the footer of the Drive file viewer and on task cards in your task list, next to the artifact's other actions. It is disabled with a tooltip explaining why on the rare case an employee is not available to ask.

If you open a file's viewer from inside a chat you're already having about it, the button swaps for a different one: a jump back to the file's home in Drive. You're already in the conversation, so the useful move is the other direction.

Files and tasks are the two places wired up today. Something else, like an email thread or a CRM contact, still means opening the employee's chat and describing what you mean by hand; the underlying handoff already carries file references end to end, and file and task will not be the last kinds added.

What actually gets asked

For a task, the button only ever pre-fills the reference, never the question. The employee sees exactly what you typed, not a guessed paraphrase of what you might have meant. The opening line names the task title, or the file and its Drive path when the two differ, so the employee can open the exact document instead of searching for something with a similar name.

For a file, the main button's instruction is fixed text owned by the server, not something the browser can vary. It always reads: read the document at its reference, explain its current state in plain language, and ask the most useful follow-up or take the requested next step. Only the file's title and Drive path travel with it, each capped in length before the server will accept them, so the browser can name a file but can never smuggle extra prose into what the employee is told.

Where it doesn't reach yet

A task owned by a human teammate rather than an AI employee can't be asked about yet; the button stays visible but disabled, with 'Asking a teammate is coming soon' on hover. A task that hasn't been saved yet is disabled the same way, with 'Available once the task exists.'

The instant-answer version is file-only. Tasks always open to an empty first line you write yourself; there's no task equivalent yet of the employee reading and summarizing on its own.

How It Works

From button click to a composer that already knows what you mean

Click Ask on a file in the Drive viewer or a task in your task list. Sistava builds a chat link that carries an opening line such as "About the file notes.md (/documents/notes.md): " and takes you straight to that employee's chat.

The composer reads that opening line once when the chat loads, drops it into the message box with the cursor at the end, and clears it from the URL so refreshing the page does not repeat it.

For files, the employee also receives the file's Drive path directly, so it can open and read the file itself rather than guessing from the title alone. You finish typing your question and send it like any other message.

Use Cases

Following up on a task without retyping it

You're looking at a task that's stalled. Click Ask, and the employee's chat opens with the task already named, so you can just ask why it's stuck or what's next.

Getting a same-second read on a file, no typing

You're staring at a file and just want to know what it says. Click the main Ask button and the employee opens it, reads it, and explains its current state before you've typed a single word, then asks what you want done next.

Getting a document reviewed on your own terms

You're reading a file in Drive and want to steer the conversation yourself rather than get the automatic read. Use the small icon button instead: it opens the same chat with the file referenced by its exact path, cursor ready, so you write the actual question.

Asking for a redo without re-explaining the file

A file came out wrong and you want it redone. Use the icon button on that file, name what needs to change in the composer, and send. No need to describe which file; the reference already travelled with you.

FAQ

Does clicking Ask send a message automatically?

Depends which button. On a task, and on the small icon button next to a file, no: it only opens chat with an unfinished opening line in the composer, and nothing sends until you finish typing and hit send yourself. The main 'Ask <name>' button on a file is different: it sends right away, but only a fixed instruction to open and explain the file, never words typed as if they were yours.

Which items support Ask About This?

Files in the Drive viewer and tasks in your task list. Both drop you into the relevant employee's chat with the item referenced.

What happens for a file specifically?

A file gets two buttons. The main one hands the employee a ready instruction to open the file at its Drive path, read it, explain its current state, and ask a useful follow-up, with nothing left for you to type. A smaller icon button next to it opens the same chat the classic way instead, with the file named in the composer so you write the first line yourself.

Can I still ask about something that isn't a file or task, like an email or a CRM contact?

Yes, just open the employee's chat directly and describe what you mean; you'll just be typing the reference yourself instead of having it pre-filled.

Can I ask about a task assigned to a teammate?

Not yet. Ask About This is disabled on a task owned by a human teammate rather than an AI employee, with a tooltip explaining why. An unsaved task is disabled the same way until it exists.

Could the file button be used to slip a hidden instruction to the employee?

No. The browser only sends a curated action name plus the file's title and path; the instruction text itself is a fixed file the server owns and the browser can't alter, so nothing typed anywhere in the app can add extra prose to what the employee is told to do.

Where Ask About This fits

Ask About This 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: Where your employees organize their work.

Read the guide

Guide: Ask About This

More in Workspace

Move a Team Member to the Bench: 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: 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: 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: 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: 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: 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: 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: 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: 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: 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: 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: 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.