AI Assistant

How do I open the assistant?

Click the views icon in the top bar and select AI Assistant - next to Calendar, Board and Notes. The same menu appears in the header of each of these windows (the first icon on the left among the buttons), so you can switch views without returning to the top bar. These four windows share the same space: selecting one closes the previous one, and the saved layout (full / docked) applies to all of them.

The window looks and works like Calendar, Board and Notes: use the icon in the header to dock it at the bottom of the screen (it collapses into a pill - click to restore it), switch between the light and dark theme (shared by all four windows), and hide the thread list when you need more room for the conversation. The layout is remembered, so the next time you open it, it will appear just as you left it.

Threads - separate conversations instead of a single stream

On the left-hand side of the window is a list of threads. Each thread is a separate conversation with its own name, history and set of knowledge sources. Your existing history will not disappear - the first time you open the assistant, it is automatically divided into threads based on the context in which each conversation took place.

• New thread - the “+ New” button above the list. It starts as general (it can only see your tasks); you add sources yourself using the button above the conversation. To start with the same set of knowledge as the current conversation, use Duplicate with sources in the ⋮ menu. The name is generated from the first question; you can change it by clicking the title above the conversation or using the ⋮ menu.
• Favourites - use the star next to a thread (or the ⋮ menu). Favourites remain at the top of the list.
• Search and filters - the search field searches the names and content of conversations (and displays the number of results). The filters button narrows the list by Workspace, time range, source type, favourites or conversations in which the assistant changed something (created a task, changed a status or set a reminder). When a filter is active, a blue dot appears on the button - even after you close the menu.
• Thread ⋮ menu: rename, add to favourites, Duplicate with sources (a new conversation with the same set of knowledge) and delete. Use the button above the conversation to change the knowledge sources.
• Drag and drop: arrange threads in the list however you like - just drag and move them. Dropping a thread into the Favourites section adds it to your favourites (and vice versa). After the first drag, the list switches to Manual sorting; use the sorting button to select another option.

Knowledge sources - what the assistant can see

There is a Sources button below the conversation title. Context is no longer a single choice (“this task OR that chat”) - it's a set: you can select several tasks, a chat, a note, an entire workspace and a calendar at once.

The selection window works like Files - you go deeper one level at a time: workspace → its tasks and chats → thread → its folders, files and notes; separately, Documents (your private folders) and Mail. The rule is the same at every level: clicking a row selects that item as a source (a tick appears on the right), while the › arrow takes you deeper. The “‹” bar at the top takes you back one level. The search field at the top searches everything at once.

Available source types:

• My tasks - the default; a list of your tasks, as before.
• Calendar - upcoming due dates (7 days by default).
• Workspace - tasks and chats from the entire workspace.
• Task / Chat / Note - a specific item selected from the tree or search results. Selecting a task or chat also includes the files uploaded to it - both those in messages and those added in the Files module (shown in the tree as “Workspace / thread name”). You don't need to look for them separately; the thread name shows how many files it contains. Long notes are read in full - the Assistant reads them in chunks and retrieves more as needed. For you, it's still one note: you don't need to split or shorten it, and notes and files are treated in the same way (from 2.2.272).
• Files - “All my Files”, a selected folder (including its subfolders), or a single file; AI reads the contents of text documents (TXT/CSV/DOCX/XLSX/PDF). Workspace folders are available after you open that workspace, and private folders after you open Documents; use the arrow to go into a subfolder, just as in the Files window.
• Mail - your inbox (a list of threads plus the latest message content) or an individual email thread (which you can find using source search). The Mail - inboxes section only appears if an administrator has enabled mail as an AI knowledge source (Settings → AI, disabled by default), and only for your inboxes - no one, including an administrator, can select someone else’s mail. Remember: the content of the selected source is sent to an external AI provider; mail is never added to the knowledge base indexed in the background.

Below the list, you can see a capacity bar showing how much knowledge fits. If you select more than the model can handle, the assistant will tell you exactly what it did not take into account (broad sources are omitted first, while explicitly selected tasks remain). You only see content you have access to - if you lose permission to a source, it will be omitted the next time you ask a question.

Attachments in the assistant panel

The message field has a paperclip (📎) - you can attach files directly to your conversation with the assistant. You can also paste a file or screenshot from the clipboard (Ctrl/Cmd+V) straight into the conversation field - it will be added to the conversation like a paperclip attachment. AI will read the files when responding (supported formats are listed below). Files attached this way are session-specific (they apply to the current conversation).

What you see while waiting for a response

While the Assistant is working, a short description of the current step appears alongside the animated dots - for example, “Reading attachments…”, “Looking through sources: my tasks, mail”, “Translating…”, “Thinking…”, and, if it takes longer, “Writing a reply…”. The steps reflect the actual order in which the Assistant works and what you selected in the conversation (knowledge sources, attachments and type of request).

What can the assistant do?

The assistant knows your tasks, chats and workspaces. It can:

• Answer questions about your tasks, due dates and assigned people
• Send emails - for example, “send an email to jan@firma.pl with a summary of task X6”.
• Generate downloadable files - PDF, Word (DOCX), Excel (XLSX) or CSV. For example, "prepare a PDF summary of task X6" or "generate a Word report". The Assistant will fetch the task content, compose the document and provide a download link. When sending an email, the Assistant uses your mailbox connected in Settings → the Mail tab (Mail module, Pro plan). If you don't have one, it will let you know and won't send the email.
• Access the contents of any task or chat you have access to - without opening it. Just refer to it by name, for example, “summarise the Recruitment task” or “what was agreed in the Marketing chat?”. The Assistant will then retrieve its full contents, messages and attachments (TXT/CSV/DOCX/XLSX/PDF).
• Perform actions in the application: create tasks, open windows, filter the list and change statuses
• Reschedule calendar events - for example, “move all today's events to tomorrow” or “move Friday's meetings to the next working day at 12:00”. Before anything is moved, you'll get a confirmation card; once it's done, the Assistant will list exactly what it changed. Event times stay the same unless you provide new ones, and reminders linked to task due dates aren't changed - their timing is based on the task due date.
• Create calendar events - with start and end times, a workspace, participants and a colour, for example, “event: Offer review tomorrow from 12:45 to 13:30 in Technical, with Kasia Dąbrowska, green”. By default, there is no email notification - ask for one separately (“send it by email too”).
• Prepare automations from a rule description. A completed draft won't take you away from the conversation: a “Go to Automations” card appears below the reply - click it when you want to review and save it.
• Help you write task descriptions, emails and notes
• Inform you about overdue tasks and absent colleagues

The Assistant can access only the tasks and chats you have permission to access (administrators can access all of them). For very broad questions (“search all tasks…”), it may retrieve only a few of the most relevant items at a time.

Example commands

• “Show my overdue tasks”
• “Create task X with a deadline of Friday and assign it to Anna”
• “Change the status of task X to done”
• “Go to the HR workspace”
• “Open the settings window”
• “Show chats only”
• “Sort tasks alphabetically”
• “How do I add a new user?”

Improve text (editing in the editor)

In the toolbar of every editor (task description, task/chat message and message editing), you will find a magic wand with stars icon ✨ - Improve text.

When clicked, AI edits your text naturally directly in the editor: it corrects typos, spelling, grammar and punctuation, and improves the style - writing naturally and clearly (like a thoughtful person, without stuffy formal language). It uses the subject and description of the current task or chat to keep terminology consistent. It does not invent new facts or details, or make the text more formal.

Keeps your layout. Existing formatting stays untouched: bulleted/numbered lists, bold text, paragraphs, emojis and icons (✅, →), as well as spaces in units (“200 ms”, “5 min”). Polish only improves the text within the existing structure - it doesn’t turn paragraphs into lists or vice versa. It leaves fragments with a link in the middle of a sentence unchanged, so the link isn’t lost.

You’ll see the message “Text polished - click to undo” - clicking it restores the previous version.

The button is only visible if an administrator has configured AI and you have permission to use AI in the relevant context (tasks or chats). The feature only changes the text in the editor - nothing is sent or saved until you send or save the message yourself.

AI Assistant in task and chat threads

The reply field in every task and chat (as well as in Mail) has two labelled AI buttons:

• AI Assistant (the purple orb) - switches the editor to private question mode. The editor turns purple, and a bar above it says: “Question for AI Assistant - only you will see it; it won’t be shared with participants”. Only the author can see the question and answer - the answer appears in the thread with the label ONLY YOU. Click the button again to return to regular messages.
• Organise - click to open a menu with four ways to read the thread: Original content (turns AI off), Polish (the same content, shorter and tidier, in the first person), Summarise (1-2 sentences per message) and Expert (professional, with an “Expert note” - advice, a risk or a question worth asking). AI works in batches of 8 (starting with the newest); a banner showing the mode appears at the top of the thread, with a “Organise older messages (N)” button below it to load more batches. The result applies only for the current session and isn’t saved anywhere; each processed message is marked “AI can make mistakes”. Once a mode has been processed, switching to it is instant - you can switch between modes during the same session without waiting.

In question mode, the assistant can see the thread content and attachments, and can generate a downloadable file (Word/PDF/HTML), for example, “create a Word document summarising this thread”. AI writes the content, and the app assembles the finished file and adds a “Download …” button to the thread.

What you can ask for in natural language

There are no special commands - simply ask for what you need in a normal sentence, either in the AI Assistant window or in question mode in a thread. Examples:

A few rules that always apply:

• Sending emails always requires your confirmation - the AI never sends an email on its own. The email is sent from your mailbox connected in Settings → the Mail tab (Mail module, Pro plan); without a connected mailbox, the Assistant will let you know it's missing and won't send the email.
• Reminders and scheduled actions are handled by the AI Agent - as before (more details below). Relative dates (“tomorrow at 9:00”, “in a week”) are converted into specific dates.
• Filtering the list of tasks/chats works only in the assistant window (e.g. “show favourite chats”, “high priority, in progress status”).
• Cancelling a plan only works within a task or chat thread (AI Assistant mode) - plans can't be cancelled in the AI Assistant window. The message must start with the word "cancel": "cancel plan 13", "cancel everything".

Creating tasks from a thread

In a task or chat thread, turn on question mode using the “AI Assistant” button and ask for a new task - just as you would in the side panel:

• “Create a new task with the same brief and a deadline of 30 July”
• “Create a task: prepare the quarterly report, due tomorrow”
• “Create a task: Offer for Meblex, due Friday, assign Marek”

The assistant will put the details together and open the “Add task” window with the fields filled in: the current thread’s workspace, subject, content, due date, priority and assignees. The task is created only when you click “Save” - you can edit any field first or close the window (in which case nothing is created).

A few useful details:

• “with the same brief” carries over the current task description exactly as it is (without summarising it). Without this request, the assistant drafts a new description from what you wrote - it doesn’t copy someone else’s brief.
• Relative dates (“30 July”, “Friday”, “in a week”, “tomorrow”) are converted into specific dates.
• The window only opens for you - other thread participants cannot see your conversation with the assistant. Refreshing the page or reopening the thread will not open the window again.

Conversations with the assistant in a thread are always private - only you can see the question and answer (including a reminder that will notify you at the specified time). The task itself, created by clicking “Save”, is a regular task visible to participants.

Checklists you can tick off

You can ask AI to create a list with items you can tick off - either in the assistant panel or in question mode in a thread:

• “Create a checklist: call Michał, reply to NBP, issue an invoice”
• “To-do list with checkboxes: …”

The AI will return items as clickable cards with a checkbox. Click an item to tick it off (clicking again undoes it). The state of selections is shared by everyone with access to this message - when anyone ticks off an item, the other participants see the same state (saved on the server, updated live). That's why each ticked-off item shows a signature of who checked it - a mini avatar on the right, and hovering over it (on mobile: tapping it) shows the full name along with the date and time. The signature disappears if someone unticks the item. In a thread on desktop, the avatar only appears when you hover over the item. Lists from a private conversation with the Assistant in a thread are visible only to you, so the selection state also stays private (no signatures there - it would always be you anyway). Regular bulleted lists (without a request to tick items) display as before.

File generation - how it works

When you ask for a file (in the assistant panel or in question mode in a thread), AI prepares the content, and Task Manager assembles the file automatically (Word, PDF, Excel/CSV, HTML) and provides a download link. This means the file is generated reliably - even if AI “forgets” the format. Word/PDF/HTML files are built directly from AI’s response; spreadsheets (Excel/CSV) require tabular data.

When something goes wrong

If AI does not respond, the thread (or panel) will display the specific reason, e.g. timeout (try again or select a faster model under Settings → AI), invalid API key, request limit exceeded or unavailable model. You will not be left without an explanation - you will always be told what to do next.

Reading attachment contents

AI can see attachments added to a task/chat and read their contents - both in question mode in a thread (using the “AI Assistant” button) and in the assistant panel (for the currently open task/chat), for example:

• “summarise the contents of the attachment abc.docx” (question mode in a thread)
• “summarise the contents of the attachment raport.pdf” (in the assistant panel, with that task open)

Tip: the assistant can access the content and attachments of any available task/chat by its name or from the open view - you do not need to open it. If an attachment was added just a moment ago, the assistant will see it when you ask your next question (the context is retrieved live from the database).

Supported text formats: TXT, CSV, MD, JSON, XML, HTML, DOCX (Word), XLSX/XLS (Excel) and PDF. Images (JPG/PNG/GIF/WebP) are analysed visually if the AI model supports images - including large images (they are automatically resized before being sent to the model, so even large photographs can be described).

Once summaries are enabled, the assistant panel can also answer questions about attachments from MANY tasks/chats at once (e.g. “summarise the information in the attachments from all tasks”) - within the limits of your permissions (only tasks and chats you have access to).

Lots of attachments in one thread? An administrator can enable “AI attachment summaries” in Settings → AI. The app then creates a short summary of each file (text or image), helping the assistant handle even dozens of attachments (e.g. “summarise all attachments”). Modes: automatic (in the background, requires cron) or manual (the admin clicks “Process now”). Each summary costs one API call per file. Files that haven’t been indexed yet are read on the fly (with a limit), and if there’s too much data, the assistant will ask you to narrow things down / specify a file by name.

It reads long documents in sections. When a file cannot be processed in one go (for example, a document dozens of pages long), the assistant receives the first section together with clear information about how much text has been omitted - and retrieves further sections itself when needed. Previously, the text would cut off mid-sentence without any indication, which could lead the assistant to suggest that the file was corrupted or incomplete.

Limitations: older DOC (binary) files are not read. PDFs that are scans (an image with no text layer) won't be read (no OCR). Very large files are trimmed, but the ceiling depends on how the file reaches the assistant: an attachment from a message is read up to about 50 KB of text, a file set as a knowledge source - up to 300,000 characters (the assistant receives it in chunks of about 24,000 characters and fetches more as needed), and the knowledge base index stores up to 54,000 characters from a single file. Above these thresholds, the AI only sees the beginning of the document.

Conversation history

The assistant remembers the context of the current thread - each conversation has its own history and is kept separate from the others. The history may be stored in the database (depending on the administrator’s settings) or reset when the window is closed. Threads are private - no one else can see them, including the administrator.

AI settings (administrators only)

Go to Settings → AI tab. Set:

• AI provider: OpenAI, Gemini, Claude or Grok
• The provider’s API key
• AI model - select one from the list retrieved from the provider’s API
• Maximum response length - token limit (1024-16384)

Reminders

The assistant can set your personal reminders (separate from tasks and chats):

• “Remind me about my meeting with Marek today at 18:15”
• “Remind me to send the report in 30 minutes”
• “Remind me about the invoice tomorrow at 9”

The assistant will display a confirmation with the date and time - once approved, the reminder is saved. At the specified time, you will receive an in-app notification (toast).

Email only on request. Events created by the assistant have email notifications turned off by default - you’ll receive them in the app, and that’s all. If you also want an email, say so explicitly: “remind me about the invoice tomorrow at 9 and send an email too”. (In Calendar, the same option is a checkbox labelled “Also send an email notification”.)

An event with full details. In one sentence, you can provide everything you would set manually in the calendar:

• start and end times - “event Offer review tomorrow from 12:45 to 13:30”
• workspace - “...in the Techniczne workspace” (the name is enough)
• participants - “...with Kasia Dąbrowska and Ola Wójcik”; each person gets their own copy of the event (and their own notification)
• marker colour - orange, purple, pink, blue, green, grey

You can add participants only from among people you share a workspace with. If a first name matches several people (e.g. just “Piotr”), the assistant will ask for a full name - it won’t invite anyone at random.

Important: the reminder is created only after you click “Yes, do it” in the confirmation window. The assistant’s reply alone doesn’t save anything - if the confirmation window didn’t appear, there is no reminder. Check which reminders have actually been saved by saying “show my reminders”.

E-mail requires CRON (an administrator task). In-app toast notifications always work, but sending an e-mail when the application is closed requires a recurring server task:

* * * * * /usr/bin/php /ścieżka/do/aplikacji/ai_agent_runner.php >> /ścieżka/do/aplikacji/logs/ai_agent.log 2>&1

Hosting services with HTTP cron support (cyberfolks, nazwa.pl) can instead request https://domena/ai_agent_runner.php?token=… every minute (the token is in includes/config.php). If the application detects that cron has never run, it will display a warning when you set a reminder - without cron, e-mails will only be sent when someone happens to be using the application.

Reminders linked to a task’s DUE DATE

Instead of providing a date, you can link a reminder to the task’s due date:

• “remind me about this task the day before it’s due” (question mode in a task thread)
• “remind me 2 hours before the task is due - Offer for Meblex” (assistant panel)
• “remind me in the morning on the due date” / “...when the task is due today”
• “remind me at the due date” - at the exact time it's due

The app calculates the time from the task's due date (if there's no time, it uses 9:00). If you change the task's due date, the reminder moves with it - you don't need to set it up again. If the “before the due date” time has already passed after a change, but the due date is still in the future, the reminder will go off at the next opportunity; if the due date has passed or has been removed, the reminder is cancelled.

A task without a due date can't be “kept on track” - the assistant will tell you and suggest a regular reminder for a specific date and time.

Daily task summary (“today / overdue”)

In Settings → Profile → Daily task summary, you can enable one notification per day at a chosen time (8:00 by default), summarising how many tasks are due today and how many are overdue, together with their titles. The summary only includes tasks assigned to you (not completed or archived), arrives once a day and is delivered in the same way as reminders

• as an in-app notification, or by e-mail when the application is closed (requires CRON).

Managing reminders: “show my reminders” (a list with due dates and IDs) and “cancel reminder …” (cancel by ID from the list). If you give a time that has already passed today, the assistant will ask if you mean tomorrow; if you don't give a time, it uses 9:00. Limit: 50 active reminders.

Verifying AI actions

The app makes sure AI doesn't tell you it has done something when it hasn't. If the reply confirms an action (for example, “I've set a reminder”) but the action wasn't actually carried out, you'll see a yellow “Correction” box below the reply explaining what really happened and how to achieve what you wanted (for example, which phrase to use to open the task form or create a real reminder). Sending emails always requires your confirmation by clicking “Send”.

Mail as a knowledge source

Mailboxes and email threads can be selected as a knowledge source only after an administrator enables this in Settings → AI (“Allow mail to be used as an AI knowledge source”). It's disabled by default because email content contains third-party personal data and is sent to an external AI provider. Once enabled, everyone will see only their own mailboxes in the source selector.

By selecting a folder from Documents, you give the assistant access to both the files and notes it contains (including those in subfolders).

Internet access

If an administrator has given you permission to use the AI Assistant with internet access (in the Users window), the assistant can retrieve the content of a specific website - for example, check whether a domain in a customer's email exists and what's on the site. Just ask: “check example.com and tell me what this company does”.

This is not a search engine - the assistant must know the website address (either provided by the user or derived from the domain in an e-mail address). Without the permission, the assistant will clearly state that it does not have internet access.